Search

The purpose of image dehazing is to remove the interference from weather factors in degraded images and enhance the clarity and color saturation of images to maximize the restoration of useful features. Single image dehazing is one of the most important tasks in the field of image restoration. In recent years, due to the progress of deep learning, single image dehazing has made great progress. With the success of Transformer in advanced computer vision tasks, some research studies also began to apply Transformer to image dehazing tasks and obtained surprising results. However, both the deconvolution-neural-network-based dehazing algorithm and Transformer based dehazing algorithm magnify their advantages and disadvantages separately. Therefore, this paper proposes a novel Transformer–Convolution fusion dehazing network (TCFDN), which uses Transformer's global modeling ability and convolutional neural network's local modeling ability to improve the dehazing ability. In the Transformer–Convolution fusion dehazing network, the classic self-encoder structure is used. This paper proposes a Transformer–Convolution hybrid layer, which uses an adaptive fusion strategy to make full use of the Swin-Transformer and convolutional neural network to extract and reconstruct image features. On the basis of previous research, this layer further improves the ability of the network to remove haze. A series of contrast experiments and ablation experiments not only proved that the Transformer–Convolution fusion dehazing network proposed in this paper exceeded the more advanced dehazing algorithm, but also provided solid and powerful evidence for the basic theory on which it depends. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) fault detection is crucial because undetected PV faults can lead to significant energy losses, with some cases experiencing losses of up to 10%. The efficiency of PV systems depends upon the reliable detection and diagnosis of faults. The integration of Artificial Intelligence (AI) techniques has been a growing trend in addressing these issues. The goal of this systematic review is to offer a comprehensive overview of the recent advancements in AI-based methodologies for PV fault detection, consolidating the key findings from 31 research papers. An initial pool of 142 papers were identified, from which 31 were selected for in-depth review following the PRISMA guidelines. The title, objective, methods, and findings of each paper were analyzed, with a focus on machine learning (ML) and deep learning (DL) approaches. ML and DL are particularly suitable for PV fault detection because of their capacity to process and analyze large amounts of data to identify complex patterns and anomalies. This study identified several AI techniques used for fault detection in PV systems, ranging from classical ML methods like k-nearest neighbor (KNN) and random forest to more advanced deep learning models such as Convolutional Neural Networks (CNNs). Quantum circuits and infrared imagery were also explored as potential solutions. The analysis found that DL models, in general, outperformed traditional ML models in accuracy and efficiency. This study shows that AI methodologies have evolved and been increasingly applied in PV fault detection. The integration of AI in PV fault detection offers high accuracy and effectiveness. After reviewing these studies, we proposed an Artificial Neural Network (ANN)-based method for PV fault detection and classification. [ABSTRACT FROM AUTHOR]

Recent technological developments have enabled computers to identify and categorize facial expressions to determine a person's emotional state in an image or a video. This process, called "Facial Expression Recognition (FER)", has become one of the most popular research areas in computer vision. In recent times, deep FER systems have primarily concentrated on addressing two significant challenges: the problem of overfitting due to limited training data availability, and the presence of expression-unrelated variations, including illumination, head pose, image resolution, and identity bias. In this paper, a comprehensive survey is provided on deep FER, encompassing algorithms and datasets that offer insights into these intrinsic problems. Initially, this paper presents a detailed timeline showcasing the evolution of methods and datasets in deep facial expression recognition (FER). This timeline illustrates the progression and development of the techniques and data resources used in FER. Then, a comprehensive review of FER methods is introduced, including the basic principles of FER (components such as preprocessing, feature extraction and classification, and methods, etc.) from the pro-deep learning era (traditional methods using handcrafted features, i.e., SVM and HOG, etc.) to the deep learning era. Moreover, a brief introduction is provided related to the benchmark datasets (there are two categories: controlled environments (lab) and uncontrolled environments (in the wild)) used to evaluate different FER methods and a comparison of different FER models. Existing deep neural networks and related training strategies designed for FER, based on static images and dynamic image sequences, are discussed. The remaining challenges and corresponding opportunities in FER and the future directions for designing robust deep FER systems are also pinpointed. [ABSTRACT FROM AUTHOR]

Edge detection is a crucial issue in computer vision, with convolutional neural networks (CNNs) being a key component in various systems for detecting edges within images, offering numerous practical implementations. This paper introduces a hybrid approach for edge detection in color images using an enhanced holistically led edge detection (HED) structure. The method consists of two primary phases: edge approximation based on parallel convolutional neural networks (PCNNs) and edge enhancement based on social spider optimization (SSO). The first phase uses two parallel CNN models to preliminarily approximate image edges. The first model uses edge-detected images from the Otsu-Canny operator, while the second model accepts RGB color images as input. The output of the proposed PCNN model is compared with pairwise combination of color layers in the input image. In the second phase, the SSO algorithm is used to optimize the edge detection result, modifying edges in the approximate image to minimize differences with the resulting color layer combinations. The experimental results demonstrate that our proposed method achieved a precision of 0.95. Furthermore, the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values stand at 20.39 and 0.83, respectively. The high PSNR value of our method signifies superior output quality, showing reduced contrast and noise compared to the ground truth image. Similarly, the SSIM value indicates that the method's edge structure surpasses that of the ground truth image, further affirming its superiority over other methods. [ABSTRACT FROM AUTHOR]

Precise measurement of fiber diameter in animal and synthetic textiles is crucial for quality assessment and pricing; however, traditional methods often struggle with accuracy, particularly when fibers are densely packed or overlapping. Current computer vision techniques, while useful, have limitations in addressing these challenges. This paper introduces a novel deep-learning-based method to automatically generate distance maps of fiber micrographs, enabling more accurate fiber segmentation and diameter calculation. Our approach utilizes a modified U-Net architecture, trained on both real and simulated micrographs, to regress distance maps. This allows for the effective separation of individual fibers, even in complex scenarios. The model achieves a mean absolute error (MAE) of 0.1094 and a mean square error (MSE) of 0.0711 , demonstrating its effectiveness in accurately measuring fiber diameters. This research highlights the potential of deep learning to revolutionize fiber analysis in the textile industry, offering a more precise and automated solution for quality control and pricing. [ABSTRACT FROM AUTHOR]

Simple Summary: The use of computer vision technology has improved the effectiveness of individual sheep identification, but existing methods face challenges such as large parameter sizes, slow recognition speeds, and difficult deployment. To address this issue, we have made improvements and optimizations based on the Retinaface face recognition model to create a balanced speed-accuracy sheep face recognition model. The optimized model has fewer parameters, simpler computations, faster inference speeds, and higher recognition accuracy, making it well-suited for deployment on resource-constrained edge devices. This research is expected to promote the application of deep learning-based sheep face recognition methods in production. The recognition of sheep faces based on computer vision has improved the efficiency and effectiveness of individual sheep identification, providing technical support for the development of smart farming. However, current recognition models have problems such as large parameter sizes, slow recognition speed, and difficult deployment. Therefore, this paper proposes an efficient and fast basic module called Eblock and uses it to build a lightweight sheep face recognition model called SheepFaceNet, which achieves the best balance between speed and accuracy. SheepFaceNet includes two modules: SheepFaceNetDet for detection and SheepFaceNetRec for recognition. SheepFaceNetDet uses Eblock to construct the backbone network to enhance feature extraction capability and efficiency, designs a bidirectional FPN layer (BiFPN) to enhance geometric location ability, and optimizes the network structure, which affects inference speed, to achieve fast and accurate sheep face detection. SheepFaceNetRec uses Eblock to construct the feature extraction network, uses ECA channel attention to improve the effectiveness of feature extraction, and uses multi-scale feature fusion to achieve fast and accurate sheep face recognition. On our self-built sheep face dataset, SheepFaceNet recognized 387 sheep face images per second with an accuracy rate of 97.75%, achieving an advanced balance between speed and accuracy. This research is expected to further promote the application of deep-learning-based sheep face recognition methods in production. [ABSTRACT FROM AUTHOR]

Simple Summary: Constructing a contactless pig mass estimation method through computer vision technology can help us to adjust our pig breeding program to improve production efficiency. Due to the complexity of the actual production environment, there are few reports on pig mass estimation in an unconstrained environment. In this study, we constructed a pig mass estimate model based on deep learning without constraint. The experimental results proved that the pig body mass estimation model constructed in this paper can quickly and accurately obtain the body mass of pigs. The model can evaluate the body quality of sows in real-time in an unconstrained environment, thereby providing data support for grading and adjusting breeding plans, and has broad application prospects. The body mass of pigs is an essential indicator of their growth and health. Lately, contactless pig body mass estimation methods based on computer vision technology have gained attention thanks to their potential to improve animal welfare and ensure breeders' safety. Nonetheless, current methods require pigs to be restrained in a confinement pen, and no study has been conducted in an unconstrained environment. In this study, we develop a pig mass estimation model based on deep learning, capable of estimating body mass without constraints. Our model comprises a Mask R-CNN-based pig instance segmentation algorithm, a Keypoint R-CNN-based pig keypoint detection algorithm and an improved ResNet-based pig mass estimation algorithm that includes multi-branch convolution, depthwise convolution, and an inverted bottleneck to improve accuracy. We constructed a dataset for this study using images and body mass data from 117 pigs. Our model achieved an RMSE of 3.52 kg on the test set, which is lower than that of the pig body mass estimation algorithm with ResNet and ConvNeXt as the backbone network, and the average estimation speed was 0.339 s·frame−1 Our model can evaluate the body quality of pigs in real-time to provide data support for grading and adjusting breeding plans, and has broad application prospects. [ABSTRACT FROM AUTHOR]

Automatic image description, also known as image captioning, aims to describe the elements included in an image and their relationships. This task involves two research fields: computer vision and natural language processing; thus, it has received much attention in computer science. In this review paper, we follow the Kitchenham review methodology to present the most relevant approaches to image description methodologies based on deep learning. We focused on works using convolutional neural networks (CNN) to extract the characteristics of images and recurrent neural networks (RNN) for automatic sentence generation. As a result, 53 research articles using the encoder-decoder approach were selected, focusing only on supervised learning. The main contributions of this systematic review are: (i) to describe the most relevant image description papers implementing an encoder-decoder approach from 2014 to 2022 and (ii) to determine the main architectures, datasets, and metrics that have been applied to image description. [ABSTRACT FROM AUTHOR]

Object detection is a computer vision task of detecting instances of objects of a certain class, identifying types of objects, determining its location, and accurately labelling them in an input image or a video. The scope of the work presented within this paper proposes a modern object detection network called NextDet to efficiently detect objects of multiple classes which utilizes CondenseNeXt, an award-winning lightweight image classification convolutional neural network algorithm with reduced number of FLOPs and parameters as the backbone, to efficiently extract and aggregate image features at different granularities in addition to other novel and modified strategies such as attentive feature aggregation in the head, to perform object detection and draw bounding boxes around the detected objects. Extensive experiments and ablation tests, as outlined in this paper, are performed on Argoverse-HD and COCO datasets, which provide numerous temporarily sparse to dense annotated images, demonstrate that the proposed object detection algorithm with CondenseNeXt as the backbone result in an increase in mean Average Precision (mAP) performance and interpretability on Argoverse-HD's monocular ego-vehicle camera captured scenarios by up to 17.39% as well as COCO's large set of images of everyday scenes of real-world common objects by up to 14.62%. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) has become an active field of research in the computer vision community. Recognizing the basic activities of human beings with the help of computers and mobile sensors can be beneficial for numerous real-life applications. The main objective of this paper is to recognize six basic human activities, viz., jogging, sitting, standing, walking and whether a person is going upstairs or downstairs. This paper focuses on predicting the activities using a deep learning technique called Convolutional Neural Network (CNN) and the accelerometer present in smartphones. Furthermore, the methodology proposed in this paper focuses on grouping the data in the form of nodes and dividing the nodes into three major layers of the CNN after which the outcome is predicted in the output layer. This work also supports the evaluation of testing and training of the two-dimensional CNN model. Finally, it was observed that the model was able to give a good prediction of the activities with an average accuracy of 89.67%. Considering that the dataset used in this research work was built with the aid of smartphones, coming up with an efficient model for such datasets and some futuristic ideas pose open challenges in the research community. [ABSTRACT FROM AUTHOR]

Over the last decades, the field of medicine has witnessed significant progress in artificial intelligence (AI), the Internet of Medical Things (IoMT), and deep learning (DL) systems. Otorhinolaryngology, and imaging in its various subspecialties, has not remained untouched by this transformative trend. As the medical landscape evolves, the integration of these technologies becomes imperative in augmenting patient care, fostering innovation, and actively participating in the ever-evolving synergy between computer vision techniques in otorhinolaryngology and AI. To that end, we conducted a thorough search on MEDLINE for papers published until June 2023, utilizing the keywords 'otorhinolaryngology', 'imaging', 'computer vision', 'artificial intelligence', and 'deep learning', and at the same time conducted manual searching in the references section of the articles included in our manuscript. Our search culminated in the retrieval of 121 related articles, which were subsequently subdivided into the following categories: imaging in head and neck, otology, and rhinology. Our objective is to provide a comprehensive introduction to this burgeoning field, tailored for both experienced specialists and aspiring residents in the domain of deep learning algorithms in imaging techniques in otorhinolaryngology. [ABSTRACT FROM AUTHOR]

In image classification with Deep Convolutional Neural Networks (DCNNs), the number of parameters in pointwise convolutions rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer. Existing studies demonstrated that a subnetwork can replace pointwise convolutional layers with significantly fewer parameters and fewer floating-point computations, while maintaining the learning capacity. In this paper, we propose an improved scheme for reducing the complexity of pointwise convolutions in DCNNs for image classification based on interleaved grouped filters without divisibility constraints. The proposed scheme utilizes grouped pointwise convolutions, in which each group processes a fraction of the input channels. It requires a number of channels per group as a hyperparameter C h . The subnetwork of the proposed scheme contains two consecutive convolutional layers K and L, connected by an interleaving layer in the middle, and summed at the end. The number of groups of filters and filters per group for layers K and L is determined by exact divisions of the original number of input channels and filters by C h . If the divisions were not exact, the original layer could not be substituted. In this paper, we refine the previous algorithm so that input channels are replicated and groups can have different numbers of filters to cope with non exact divisibility situations. Thus, the proposed scheme further reduces the number of floating-point computations (11%) and trainable parameters (10%) achieved by the previous method. We tested our optimization on an EfficientNet-B0 as a baseline architecture and made classification tests on the CIFAR-10, Colorectal Cancer Histology, and Malaria datasets. For each dataset, our optimization achieves a saving of 76%, 89%, and 91% of the number of trainable parameters of EfficientNet-B0, while keeping its test classification accuracy. [ABSTRACT FROM AUTHOR]

Autism spectrum disorder (ASD), or autism, can be diagnosed based on a lack of behavioral skills and social communication. The most prominent method of diagnosing ASD in children is observing the child's behavior, including some of the signs that the child repeats. Hand flapping is a common stimming behavior in children with ASD. This research paper aims to identify children's abnormal behavior, which might be a sign of autism, using videos recorded in a natural setting during the children's regular activities. Specifically, this study seeks to classify self-stimulatory activities, such as hand flapping, as well as normal behavior in real-time. Two deep learning video classification methods are used to be trained on the publicly available Self-Stimulatory Behavior Dataset (SSBD). The first method is VGG-16-LSTM; VGG-16 to spatial feature extraction and long short-term memory networks (LSTM) for temporal features. The second method is a long-term recurrent convolutional network (LRCN) that learns spatial and temporal features immediately in end-to-end training. The VGG-16-LSTM achieved 0.93% on the testing set, while the LRCN model achieved an accuracy of 0.96% on the testing set. [ABSTRACT FROM AUTHOR]

Automatic weight detection is an essential step in the factory production of Pleurotus eryngii. In this study, a data set containing 1154 Pleurotus eryngii images was created, and then machine vision technology was used to extract eight two-dimensional features from the images. Because the fruiting bodies of Pleurotus eryngii have different shapes, these features were less correlated with weight. This paper proposed a multidimensional feature derivation method and an Attention-Based CNN model to solve this problem. This study aimed to realize the traditional feature screening task by deep learning algorithms and built an estimation model. Compared with different regression algorithms, the R2, RMSE, MAE, and MAPE of the Attention-Based CNN were 0.971, 7.77, 5.69, and 5.87%, respectively, and showed the best performance. Therefore, it can be used as an accurate, objective, and effective method for automatic weight measurements of Pleurotus eryngii. [ABSTRACT FROM AUTHOR]

In recent years, advances in deep learning (DL) techniques for video analysis have developed to solve the problem of real-time processing. Automated face recognition in the runtime environment has become necessary in video surveillance systems for urban security. This is a difficult task due to face occlusion, which makes it hard to capture effective features. Existing work focuses on improving performance while ignoring issues like a small dataset, high computational complexity, and a lack of lightweight and efficient feature descriptors. In this paper, face recognition (FR) using a Convolutional mixer (AFR-Conv) algorithm is developed to handle face occlusion problems. A novel AFR-Conv architecture is designed by assigning priority-based weight to the different face patches along with residual connections and an AdaBoost classifier for automatically recognizing human faces. The AFR-Conv also leverages the strengths of pre-trained CNNs by extracting features using ResNet-50, Inception-v3, and DenseNet-161. The AdaBoost classifier combines these features' weighted votes to predict labels for testing images. To develop this system, we use the data augmentation method to enhance the number of datasets using human face images. The AFR-Conv method is then used to extract robust features from images. Finally, to recognize human identity, an AdaBoost classifier is utilized. For the training and evaluation of the AFR-Conv model, a set of face images is collected from online data sources. The experimental results of the AFR-Conv approach are presented in terms of precision (PR), recall (RE), detection accuracy (DA), and F1-score metrics. Particularly, the proposed approach attains 95.5% PR, 97.6% RE, 97.5% DA, and 98.5% of F1-score on 8500 face images. The experimental results show that our proposed scheme outperforms advanced methods for face classification. [ABSTRACT FROM AUTHOR]

With the rapid development of sensor technologies and the widespread use of laser scanning equipment, point clouds, as the main data form and an important information carrier for 3D scene analysis and understanding, play an essential role in the realization of national strategic needs, such as traffic scene perception, natural resource management, and forest biomass carbon stock estimation. As an important research direction in 3D computer vision, point cloud semantic segmentation has attracted more and more researchers' attention. In this paper, we systematically outline the main research problems and related research methods in point cloud semantic segmentation and summarize the mainstream public datasets and common performance evaluation metrics. Point cloud semantic segmentation methods are classified into rule-based methods and point-based methods according to the representation of the input data. On this basis, the core ideas of each type of segmentation method are introduced, the representative and innovative algorithms of each type of method are elaborated, and the experimental results on the datasets are compared and analyzed. Finally, some promising research directions and potential tendencies are proposed. [ABSTRACT FROM AUTHOR]

Plant diseases have been one of the most threatening scenarios to farmers. Although most plant diseases can be identified by observing leaves, it often requires human expertise. The recent improvements in computer vision have led to introduce disease classification systems through observing leaf images. Nevertheless, most disease classification systems are specific to diseases and plants, limiting method's usability. The methods are also costly as they require vast labeled data, which can only be done by experts. This paper introduces a self-supervised leaf disease clustering system that can be used for classifying plant diseases. As self-supervision does not require labeled data, the proposed method can be inexpensive and can be implemented for most types of plants. The method implements a siamese deep convolutional neural network (DCNN) for generating clusterable embeddings from leaf images. The training strategy of the embedding network is conducted using AutoEmbedder approach with randomly augmented image pairs. The self-supervised embedding model training involves three different data pair linkage scenarios: can-link, cannot-link, and may-link pairs. The embeddings are further clustered using k-means algorithm in the final classification stage. The experiment is conducted to individually classify diseases of eight different fruit leaves. The results indicate that the proposed leaf disease identification method performs better than the existing self-supervised clustering systems. The paper indicates that end-to-end siamese networks can outperform well-designed sequentially trained self-supervised methods. [ABSTRACT FROM AUTHOR]

Recognition and classification for construction activities help to monitor and manage construction workers. Deep learning and computer vision technologies have addressed many limitations of traditional manual methods in complex construction environments. However, distinguishing different workers and establishing a clear recognition logic remain challenging. To address these issues, we propose a novel construction activity recognition method that integrates multiple deep learning algorithms. To complete this research, we created three datasets: 727 images for construction entities, 2546 for posture and orientation estimation, and 5455 for worker re-identification. First, a YOLO v5-based model is trained for worker posture and orientation detection. A person re-identification algorithm is then introduced to distinguish workers by tracking their coordinates, body and head orientations, and postures over time, then estimating their attention direction. Additionally, a YOLO v5-based object detection model is developed to identify ten common construction entity objects. The worker's activity is determined by combining their attentional orientation, positional information, and interaction with detected construction entities. Ten video clips are selected for testing, and a total of 745 instances of workers are detected, achieving an accuracy rate of 88.5%. With further refinement, this method shows promise for a broader application in construction activity recognition, enhancing site management efficiency. [ABSTRACT FROM AUTHOR]

Advances in deep learning techniques for remote sensing as well as the increased availability of high-resolution data enable the extraction of more detailed information from aerial images. One promising task is the semantic segmentation of roof segments and their orientation. However, the lack of annotated data is a major barrier for deploying respective models on a large scale. Previous research demonstrated the viability of the deep learning approach for the task, but currently, published datasets are small-scale, manually labeled, and rare. Therefore, this paper extends the state of the art by presenting a novel method for the automated generation of large-scale datasets based on semantic 3D city models. Furthermore, we train a model on a dataset 50 times larger than existing datasets and achieve superior performance while applying it to a wider variety of buildings. We evaluate the approach by comparing networks trained on four dataset configurations, including an existing dataset and our novel large-scale dataset. The results show that the network performance measured as intersection over union can be increased from 0.60 for the existing dataset to 0.70 when the large-scale model is applied on the same region. The large-scale model performs superiorly even when applied to more diverse test samples, achieving 0.635. The novel approach contributes to solving the dataset bottleneck and consequently to improving semantic segmentation of roof segments. The resulting remotely sensed information is crucial for applications such as solar potential analysis or urban planning. [ABSTRACT FROM AUTHOR]

The strain field can reflect the initiation time of solidification cracks during the welding process. The traditional strain measurement is to first obtain the displacement field through digital image correlation (DIC) or optical flow and then calculate the strain field. The main disadvantage is that the calculation takes a long time, limiting its suitability to real-time applications. Recently, convolutional neural networks (CNNs) have made impressive achievements in computer vision. To build a good prediction model, the network structure and dataset are two key factors. In this paper, we first create the training and test sets containing welding cracks using the controlled tensile weldability (CTW) test and obtain the real strain fields through the Lucas–Kanade algorithm. Then, two new networks using ResNet and DenseNet as encoders are developed for strain prediction, called StrainNetR and StrainNetD. The results show that the average endpoint error (AEE) of the two networks on our test set is about 0.04 , close to the real strain value. The computation time could be reduced to the millisecond level, which would greatly improve efficiency. [ABSTRACT FROM AUTHOR]

Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to train a road anomaly manhole cover detection model. The number of anomalous manhole covers is usually small, which makes it a challenge to create training datasets quickly. To expand the dataset and improve the generalization of the model, researchers usually copy and paste samples from the original data to other data in order to achieve data augmentation. In this paper, we propose a new data augmentation method, which uses data that do not exist in the original dataset as samples to automatically select the pasting position of manhole cover samples and predict the transformation parameters via visual prior experience and perspective transformations, making it more accurately capture the actual shape of manhole covers on a road. Without using other data enhancement processes, our method raises the mean average precision (mAP) by at least 6.8 compared with the baseline model. [ABSTRACT FROM AUTHOR]

Deep learning approaches based on convolutional neural networks (CNNs) have recently achieved success in computer vision, demonstrating significant superiority in the domain of image processing. For hyperspectral image (HSI) classification, convolutional neural networks are an efficient option. Hyperspectral image classification approaches are often based on spectral information. Convolutional neural networks are used for image classification in order to achieve greater performance. The complex computation in convolutional neural networks requires hyper-parameters that attain high accuracy outputs, and this process needs more computational time and effort. Following up on the proposed technique, a bio-inspired metaheuristic strategy based on an enhanced form of elephant herding optimization is proposed in this research paper. It allows one to automatically search for and target the suitable values of convolutional neural network hyper-parameters. To design an automatic system for hyperspectral image classification, the enhanced elephant herding optimization (EEHO) with the AdaBound optimizer is implemented for the tuning and updating of the hyper-parameters of convolutional neural networks (CNN–EEHO–AdaBound). The validation of the convolutional network hyper-parameters should produce a highly accurate response of high-accuracy outputs in order to achieve high-level accuracy in HSI classification, and this process takes a significant amount of processing time. The experiments are carried out on benchmark datasets (Indian Pines and Salinas) for evaluation. The proposed methodology outperforms state-of-the-art methods in a performance comparative analysis, with the findings proving its effectiveness. The results show the improved accuracy of HSI classification by optimising and tuning the hyper-parameters. [ABSTRACT FROM AUTHOR]

Weeds are a crucial threat to agriculture, and in order to preserve crop productivity, spreading agrochemicals is a common practice with a potential negative impact on the environment. Methods that can support intelligent application are needed. Therefore, identification and mapping is a critical step in performing site-specific weed management. Unmanned aerial vehicle (UAV) data streams are considered the best for weed detection due to the high resolution and flexibility of data acquisition and the spatial explicit dimensions of imagery. However, with the existence of unstructured crop conditions and the high biological variation of weeds, it remains a difficult challenge to generate accurate weed recognition and detection models. Two critical barriers to tackling this challenge are related to (1) a lack of case-specific, large, and comprehensive weed UAV image datasets for the crop of interest, (2) defining the most appropriate computer vision (CV) weed detection models to assess the operationality of detection approaches in real case conditions. Deep Learning (DL) algorithms, appropriately trained to deal with the real case complexity of UAV data in agriculture, can provide valid alternative solutions with respect to standard CV approaches for an accurate weed recognition model. In this framework, this paper first introduces a new weed and crop dataset named Chicory Plant (CP) and then tests state-of-the-art DL algorithms for object detection. A total of 12,113 bounding box annotations were generated to identify weed targets (Mercurialis annua) from more than 3000 RGB images of chicory plantations, collected using a UAV system at various stages of crop and weed growth. Deep weed object detection was conducted by testing the most recent You Only Look Once version 7 (YOLOv7) on both the CP and publicly available datasets (Lincoln beet (LB)), for which a previous version of YOLO was used to map weeds and crops. The YOLOv7 results obtained for the CP dataset were encouraging, outperforming the other YOLO variants by producing value metrics of 56.6%, 62.1%, and 61.3% for the mAP@0.5 scores, recall, and precision, respectively. Furthermore, the YOLOv7 model applied to the LB dataset surpassed the existing published results by increasing the mAP@0.5 scores from 51% to 61%, 67.5% to 74.1%, and 34.6% to 48% for the total mAP, mAP for weeds, and mAP for sugar beets, respectively. This study illustrates the potential of the YOLOv7 model for weed detection but remarks on the fundamental needs of large-scale, annotated weed datasets to develop and evaluate models in real-case field circumstances. [ABSTRACT FROM AUTHOR]

Global solar photovoltaic capacity has consistently doubled every 18 months over the last two decades, going from 0.3 GW in 2000 to 643 GW in 2019, and is forecast to reach 4240 GW by 2040. However, these numbers are uncertain, and virtually all reporting on deployments lacks a unified source of either information or validation. In this paper, we propose, optimize, and validate a deep learning framework to detect and map solar farms using a state-of-the-art semantic segmentation convolutional neural network applied to satellite imagery. As a final step in the pipeline, we propose a model to estimate the energy generation capacity of the detected solar energy facilities. Objectively, the deep learning model achieved highly competitive performance indicators, including a mean accuracy of 96.87%, and a Jaccard Index (intersection over union of classified pixels) score of 95.5%. Subjectively, it was found to detect spaces between panels producing a segmentation output at a sub-farm level that was better than human labeling. Finally, the detected areas and predicted generation capacities were validated against publicly available data to within an average error of 4.5% Deep learning applied specifically for the detection and mapping of solar farms is an active area of research, and this deep learning capacity evaluation pipeline is one of the first of its kind. We also share an original dataset of overhead solar farm satellite imagery comprising 23,000 images (256 × 256 pixels each), and the corresponding labels upon which the machine learning model was trained. [ABSTRACT FROM AUTHOR]

Audio segmentation and sound event detection are crucial topics in machine listening that aim to detect acoustic classes and their respective boundaries. It is useful for audio-content analysis, speech recognition, audio-indexing, and music information retrieval. In recent years, most research articles adopt segmentation-by-classification. This technique divides audio into small frames and individually performs classification on these frames. In this paper, we present a novel approach called You Only Hear Once (YOHO), which is inspired by the YOLO algorithm popularly adopted in Computer Vision. We convert the detection of acoustic boundaries into a regression problem instead of frame-based classification. This is done by having separate output neurons to detect the presence of an audio class and predict its start and end points. The relative improvement for F-measure of YOHO, compared to the state-of-the-art Convolutional Recurrent Neural Network, ranged from 1% to 6% across multiple datasets for audio segmentation and sound event detection. As the output of YOHO is more end-to-end and has fewer neurons to predict, the speed of inference is at least 6 times faster than segmentation-by-classification. In addition, as this approach predicts acoustic boundaries directly, the post-processing and smoothing is about 7 times faster. [ABSTRACT FROM AUTHOR]

Passive video forensics has drawn much attention in recent years. However, research on detection of object-based forgery, especially for forged video encoded with advanced codec frameworks, is still a great challenge. In this paper, we propose a deep learning-based approach to detect object-based forgery in the advanced video. The presented deep learning approach utilizes a convolutional neural network (CNN) to automatically extract high-dimension features from the input image patches. Different from the traditional CNN models used in computer vision domain, we let video frames go through three preprocessing layers before being fed into our CNNmodel. They include a frame absolute difference layer to cut down temporal redundancy between video frames, a max pooling layer to reduce computational complexity of image convolution, and a high-pass filter layer to enhance the residual signal left by video forgery. In addition, an asymmetric data augmentation strategy has been established to get a similar number of positive and negative image patches before the training. The experiments have demonstrated that the proposed CNN-based model with the preprocessing layers has achieved excellent results. [ABSTRACT FROM AUTHOR]

Many scientific studies deal with person counting and density estimation from single images. Recently, convolutional neural networks (CNNs) have been applied for these tasks. Even though often better results are reported, it is often not clear where the improvements are resulting from, and if the proposed approaches would generalize. Thus, the main goal of this paper was to identify the critical aspects of these tasks and to show how these limit state-of-the-art approaches. Based on these findings, we show how to mitigate these limitations. To this end, we implemented a CNN-based baseline approach, which we extended to deal with identified problems. These include the discovery of bias in the reference data sets, ambiguity in ground truth generation, and mismatching of evaluation metrics w.r.t. the training loss function. The experimental results show that our modifications allow for significantly outperforming the baseline in terms of the accuracy of person counts and density estimation. In this way, we get a deeper understanding of CNN-based person density estimation beyond the network architecture. Furthermore, our insights would allow to advance the field of person density estimation in general by highlighting current limitations in the evaluation protocols. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have been widely used to obtain high-level representation in various computer vision tasks. However, in the field of remote sensing, there are not sufficient images to train a useful deep CNN. Instead, we tend to transfer successful pre-trained deep CNNs to remote sensing tasks. In the transferring process, generalization power of features in pre-trained deep CNNs plays the key role. In this paper, we propose two promising architectures to extract general features from pre-trained deep CNNs for remote scene classification. These two architectures suggest two directions for improvement. First, before the pre-trained deep CNNs, we design a linear PCA network (LPCANet) to synthesize spatial information of remote sensing images in each spectral channel. This design shortens the spatial “distance” of target and source datasets for pre-trained deep CNNs. Second, we introduce quaternion algebra to LPCANet, which further shortens the spectral “distance” between remote sensing images and images used to pre-train deep CNNs. With five well-known pre-trained deep CNNs, experimental results on three independent remote sensing datasets demonstrate that our proposed framework obtains state-of-the-art results without fine-tuning and feature fusing. This paper also provides baseline for transferring fresh pre-trained deep CNNs to other remote sensing tasks. [ABSTRACT FROM AUTHOR]

Predicting the compressive strength of cement-stabilized rammed earth (CSRE) using current testing machines is time-consuming and costly and may harm the environment due to the samples' waste. This paper presents an automatic method using computer vision and deep learning to solve the problem. For this purpose, a deep convolutional neural network (DCNN) model is proposed, which was evaluated on a new in-house scanning electron microscope (SEM) image database containing 4284 images of materials with different compressive strengths. The experimental results show reasonable prediction results compared to other traditional methods, achieving 84% prediction accuracy and a small (1.5) oot Mean Square Error (RMSE). This indicates that the proposed method (with some enhancements) can be used in practice for predicting the compressive strength of CSRE samples. [ABSTRACT FROM AUTHOR]

Celiac disease (CD) is a gluten-sensitive immune-mediated enteropathy. This proof-of-concept study used a convolutional neural network (CNN) to classify hematoxylin and eosin (H&E) CD histological images, normal small intestine control, and non-specified duodenal inflammation (7294, 11,642, and 5966 images, respectively). The trained network classified CD with high performance (accuracy 99.7%, precision 99.6%, recall 99.3%, F1-score 99.5%, and specificity 99.8%). Interestingly, when the same network (already trained for the 3 class images), analyzed duodenal adenocarcinoma (3723 images), the new images were classified as duodenal inflammation in 63.65%, small intestine control in 34.73%, and CD in 1.61% of the cases; and when the network was retrained using the 4 histological subtypes, the performance was above 99% for CD and 97% for adenocarcinoma. Finally, the model added 13,043 images of Crohn's disease to include other inflammatory bowel diseases; a comparison between different CNN architectures was performed, and the gradient-weighted class activation mapping (Grad-CAM) technique was used to understand why the deep learning network made its classification decisions. In conclusion, the CNN-based deep neural system classified 5 diagnoses with high performance. Narrow artificial intelligence (AI) is designed to perform tasks that typically require human intelligence, but it operates within limited constraints and is task-specific. [ABSTRACT FROM AUTHOR]

Deep learning-based sheep face recognition improves the efficiency and effectiveness of individual sheep recognition and provides technical support for the development of intelligent livestock farming. However, frequent changes within the flock and variations in facial features in different views significantly affect the practical application of sheep face recognition. In this study, we proposed the Li-SheepFaceNet, a method for open-set sheep face recognition in multi-view. Specifically, we employed the Seesaw block to construct a lightweight model called SheepFaceNet, which significantly improves both performance and efficiency. To enhance the convergence and performance of low-dimensional embedded feature learning, we used Li-ArcFace as the loss function. The Li-SheepFaceNet achieves an open-set recognition accuracy of 96.13% on a self-built dataset containing 3801 multi-view face images of 212 Ujumqin sheep, which surpasses other open-set sheep face recognition methods. To evaluate the robustness and generalization of our approach, we conducted performance testing on a publicly available dataset, achieving a recognition accuracy of 93.33%. Deploying Li-SheepFaceNet on an open-set sheep face recognition system enables the rapid and accurate identification of individual sheep, thereby accelerating the development of intelligent sheep farming. [ABSTRACT FROM AUTHOR]

Background: Open surgery relies heavily on the surgeon's visual acuity and spatial awareness to track instruments within a dynamic and often cluttered surgical field. Methods: This system utilizes a head-mounted depth camera to monitor surgical scenes, providing both image data and depth information. The video captured from this camera is scaled down, compressed using MPEG, and transmitted to a high-performance workstation via the RTSP (Real-Time Streaming Protocol), a reliable protocol designed for real-time media transmission. To segment surgical instruments, we utilize the enhanced U-Net with GridMask (EUGNet) for its proven effectiveness in surgical tool segmentation. Results: For rigorous validation, the system's performance reliability and accuracy are evaluated using prerecorded RGB-D surgical videos. This work demonstrates the potential of this system to improve situational awareness, surgical efficiency, and generate data-driven insights within the operating room. In a simulated surgical environment, the system achieves a high accuracy of 85.5% in identifying and segmenting surgical instruments. Furthermore, the wireless video transmission proves reliable with a latency of 200 ms, suitable for real-time processing. Conclusions: These findings represent a promising step towards the development of assistive technologies with the potential to significantly enhance surgical practice. [ABSTRACT FROM AUTHOR]

The aim of this article is to introduce a novel approach to identifying flow regimes and void fractions in microchannel flow boiling, which is based on binary image segmentation using digital image processing and deep learning. The proposed image processing pipeline uses adaptive thresholding, blurring, gamma correction, contour detection, and histogram comparison to separate vapor from liquid areas, while the deep learning method uses a customized version of a convolutional neural network (CNN) called U-net to extract meaningful features from video frames. Both approaches enabled the automatic detection of flow boiling conditions, such as bubbly, slug, and annular flow, as well as automatic void fraction calculation. Especially CNN demonstrated its ability to deliver fast and dependable results, presenting an appealing substitute to manual feature extraction. The U-net-based CNN was able to segment flow boiling images with a Dice score of 99.1% and classify the above flow regimes with an overall classification accuracy of 91%. In addition, the neural network was able to predict resistance sensor readings from image data and assign them to a flow state with a mean squared error (MSE) < 10−6. [ABSTRACT FROM AUTHOR]

Computer vision is currently experiencing success in various domains due to the harnessing of deep learning strategies. In the case of precision agriculture, computer vision is being investigated for detecting fruits from orchards. However, such strategies limit too-high complexity computation that is impossible to embed in an automated device. Nevertheless, most investigation of fruit detection is limited to a single fruit, resulting in the necessity of a one-to-many object detection system. This paper introduces a generic detection mechanism named FruitDet, designed to be prominent for detecting fruits. The FruitDet architecture is designed on the YOLO pipeline and achieves better performance in detecting fruits than any other detection model. The backbone of the detection model is implemented using DenseNet architecture. Further, the FruitDet is packed with newer concepts: attentive pooling, bottleneck spatial pyramid pooling, and blackout mechanism. The detection mechanism is benchmarked using five datasets, which combines a total of eight different fruit classes. The FruitDet architecture acquires better performance than any other recognized detection methods in fruit detection. [ABSTRACT FROM AUTHOR]

The timely identification and early prevention of crop diseases are essential for improving production. In this paper, deep convolutional-neural-network (CNN) models are implemented to identify and diagnose diseases in plants from their leaves, since CNNs have achieved impressive results in the field of machine vision. Standard CNN models require a large number of parameters and higher computation cost. In this paper, we replaced standard convolution with depth=separable convolution, which reduces the parameter number and computation cost. The implemented models were trained with an open dataset consisting of 14 different plant species, and 38 different categorical disease classes and healthy plant leaves. To evaluate the performance of the models, different parameters such as batch size, dropout, and different numbers of epochs were incorporated. The implemented models achieved a disease-classification accuracy rates of 98.42%, 99.11%, 97.02%, and 99.56% using InceptionV3, InceptionResNetV2, MobileNetV2, and EfficientNetB0, respectively, which were greater than that of traditional handcrafted-feature-based approaches. In comparison with other deep-learning models, the implemented model achieved better performance in terms of accuracy and it required less training time. Moreover, the MobileNetV2 architecture is compatible with mobile devices using the optimized parameter. The accuracy results in the identification of diseases showed that the deep CNN model is promising and can greatly impact the efficient identification of the diseases, and may have potential in the detection of diseases in real-time agricultural systems. [ABSTRACT FROM AUTHOR]

With the rapid development of surveying and spatial information technologies, more and more attention has been given to positioning. In outdoor environments, people can easily obtain positioning services through global navigation satellite systems (GNSS). In indoor environments, the GNSS signal is often lost, while other positioning problems, such as dead reckoning and wireless signals, will face accumulated errors and signal interference. Therefore, this research uses images to realize a positioning service. The main concept of this work is to establish a model for an indoor field image and its coordinate information and to judge its position by image eigenvalue matching. Based on the architecture of PoseNet, the image is input into a 23-layer convolutional neural network according to various sizes to train end-to-end location identification tasks, and the three-dimensional position vector of the camera is regressed. The experimental data are taken from the underground parking lot and the Palace Museum. The preliminary experimental results show that this new method designed by us can effectively improve the accuracy of indoor positioning by about 20% to 30%. In addition, this paper also discusses other architectures, field sizes, camera parameters, and error corrections for this neural network system. The preliminary experimental results show that the angle error correction method designed by us can effectively improve positioning by about 20%. [ABSTRACT FROM AUTHOR]

Simple Summary: While melanoma accounts for 4% of skin cancer cases, it causes 75% of skin-cancer-related deaths. The survival rate for melanoma is higher for early-identified cases, so improved access to diagnosis and screening programs is essential for addressing skin cancer deaths. Computer-aided diagnosis utilizing machine learning can be used to differentiate malignant and benign skin lesions. There is significant research into the use of convolutional neural networks to classify skin lesions from dermoscopic images. However, to provide cost-effective and accessible options for early detection of malignant melanoma, smartphone applications capable of accurately classifying skin lesions from images taken on a smartphone would be beneficial. This research investigates a previously underexplored dataset of smartphone images and develops a novel multi-layer deep convolutional neural network model, named SkinLesNet, to classify three types of skin lesions, including melanoma. Further studies to validate the model should be conducted as other image datasets become available. Skin cancer is a widespread disease that typically develops on the skin due to frequent exposure to sunlight. Although cancer can appear on any part of the human body, skin cancer accounts for a significant proportion of all new cancer diagnoses worldwide. There are substantial obstacles to the precise diagnosis and classification of skin lesions because of morphological variety and indistinguishable characteristics across skin malignancies. Recently, deep learning models have been used in the field of image-based skin-lesion diagnosis and have demonstrated diagnostic efficiency on par with that of dermatologists. To increase classification efficiency and accuracy for skin lesions, a cutting-edge multi-layer deep convolutional neural network termed SkinLesNet was built in this study. The dataset used in this study was extracted from the PAD-UFES-20 dataset and was augmented. The PAD-UFES-20-Modified dataset includes three common forms of skin lesions: seborrheic keratosis, nevus, and melanoma. To comprehensively assess SkinLesNet's performance, its evaluation was expanded beyond the PAD-UFES-20-Modified dataset. Two additional datasets, HAM10000 and ISIC2017, were included, and SkinLesNet was compared to the widely used ResNet50 and VGG16 models. This broader evaluation confirmed SkinLesNet's effectiveness, as it consistently outperformed both benchmarks across all datasets. [ABSTRACT FROM AUTHOR]

(1) Background: Computed tomography (CT) imaging challenges in diagnosing renal cell carcinoma (RCC) include distinguishing malignant from benign tissues and determining the likely subtype. The goal is to show the algorithm's ability to improve renal cell carcinoma identification and treatment, improving patient outcomes. (2) Methods: This study uses the European Deep-Health toolkit's Convolutional Neural Network with ECVL, (European Computer Vision Library), and EDDL, (European Distributed Deep Learning Library). Image segmentation utilized U-net architecture and classification with resnet101. The model's clinical efficiency was assessed utilizing kidney, tumor, Dice score, and renal cell carcinoma categorization quality. (3) Results: The raw dataset contains 457 healthy right kidneys, 456 healthy left kidneys, 76 pathological right kidneys, and 84 pathological left kidneys. Preparing raw data for analysis was crucial to algorithm implementation. Kidney segmentation performance was 0.84, and tumor segmentation mean Dice score was 0.675 for the suggested model. Renal cell carcinoma classification was 0.885 accurate. (4) Conclusion and key findings: The present study focused on analyzing data from both healthy patients and diseased renal patients, with a particular emphasis on data processing. The method achieved a kidney segmentation accuracy of 0.84 and mean Dice scores of 0.675 for tumor segmentation. The system performed well in classifying renal cell carcinoma, achieving an accuracy of 0.885, results which indicates that the technique has the potential to improve the diagnosis of kidney pathology. [ABSTRACT FROM AUTHOR]

Websites can improve their security and protect against harmful Internet attacks by incorporating CAPTCHA verification, which assists in distinguishing between human users and robots. Among the various types of CAPTCHA, the most prevalent variant involves text-based challenges that are intentionally designed to be easily understandable by humans while presenting a difficulty for machines or robots in recognizing them. Nevertheless, due to significant advancements in deep learning, constructing convolutional neural network (CNN)-based models that possess the capability of effectively recognizing text-based CAPTCHAs has become considerably simpler. In this regard, we present a CAPTCHA recognition method that entails creating multiple duplicates of the original CAPTCHA images and generating separate binary images that encode the exact locations of each group of CAPTCHA characters. These replicated images are subsequently fed into a well-trained CNN, one after another, for obtaining the final output characters. The model possesses a straightforward architecture with a relatively small storage in system, eliminating the need for CAPTCHA segmentation into individual characters. Following the training and testing of the suggested CNN model for CAPTCHA recognition, the experimental results demonstrate the model's effectiveness in accurately recognizing CAPTCHA characters. [ABSTRACT FROM AUTHOR]

One of the main problems in the elderly population and for people with functional disabilities is falling when they are not supervised. Therefore, there is a need for monitoring systems with fall detection functionality. Mobile robots are a good solution for keeping the person in sight when compared to static-view sensors. Mobile-patrol robots can be used for a group of people and systems are less intrusive than ones based on mobile robots. In this paper, we propose a novel vision-based solution for fall detection based on a mobile-patrol robot that can correct its position in case of doubt. The overall approach can be formulated as an end-to-end solution based on two stages: person detection and fall classification. Deep learning-based computer vision is used for person detection and fall classification is done by using a learning-based Support Vector Machine (SVM) classifier. This approach mainly fulfills the following design requirements—simple to apply, adaptable, high performance, independent of person size, clothes, or the environment, low cost and real-time computing. Important to highlight is the ability to distinguish between a simple resting position and a real fall scene. One of the main contributions of this paper is the input feature vector to the SVM-based classifier. We evaluated the robustness of the approach using a realistic public dataset proposed in this paper called the Fallen Person Dataset (FPDS), with 2062 images and 1072 falls. The results obtained from different experiments indicate that the system has a high success rate in fall classification (precision of 100% and recall of 99.74%). Training the algorithm using our Fallen Person Dataset (FPDS) and testing it with other datasets showed that the algorithm is independent of the camera setup. [ABSTRACT FROM AUTHOR]

A real-time Bangla Sign Language interpreter can enable more than 200 k hearing and speech-impaired people to the mainstream workforce in Bangladesh. Bangla Sign Language (BdSL) recognition and detection is a challenging topic in computer vision and deep learning research because sign language recognition accuracy may vary on the skin tone, hand orientation, and background. This research has used deep machine learning models for accurate and reliable BdSL Alphabets and Numerals using two well-suited and robust datasets. The dataset prepared in this study comprises of the largest image database for BdSL Alphabets and Numerals in order to reduce inter-class similarity while dealing with diverse image data, which comprises various backgrounds and skin tones. The papers compared classification with and without background images to determine the best working model for BdSL Alphabets and Numerals interpretation. The CNN model trained with the images that had a background was found to be more effective than without background. The hand detection portion in the segmentation approach must be more accurate in the hand detection process to boost the overall accuracy in the sign recognition. It was found that ResNet18 performed best with 99.99% accuracy, precision, F1 score, sensitivity, and 100% specificity, which outperforms the works in the literature for BdSL Alphabets and Numerals recognition. This dataset is made publicly available for researchers to support and encourage further research on Bangla Sign Language Interpretation so that the hearing and speech-impaired individuals can benefit from this research. [ABSTRACT FROM AUTHOR]

To achieve a non-destructive and rapid detection of oyster freshness, an intelligent method using deep learning fused with malondialdehyde (MDA) and total sulfhydryl groups (SH) information was proposed. In this study, an "MDA-SH-storage days" polynomial fitting model and oyster meat image dataset were first built. AleNet-MDA and AlxNet-SH classification models were then constructed to automatically identify and classify four levels of oyster meat images with overall accuracies of 92.72% and 94.06%, respectively. Next, the outputs of the two models were used as the inputs to "MDA-SH-storage days" model, which ultimately succeeded in predicting the corresponding MDA content, SH content and storage day for an oyster image within 0.03 ms. Furthermore, the interpretability of the two models for oyster meat image were also investigated by feature visualization and strongest activations techniques. Thus, this study brings new thoughts on oyster freshness prediction from the perspective of computer vision and artificial intelligence. [ABSTRACT FROM AUTHOR]

Winter jujube (Ziziphus jujuba Mill. cv. Dongzao) has been cultivated in China for a long time and has a richly abundant history, whose maturity grade determined different postharvest qualities. Traditional methods for identifying the fundamental quality of winter jujube are known to be time-consuming and labor-intensive, resulting in significant difficulties for winter jujube resource management. The applications of deep learning in this regard will help manufacturers and orchard workers quickly identify fundamental quality information. In our study, the best fundamental quality of winter jujube from the correlation between maturity and fundamental quality was determined by testing three simple physicochemical indexes: total soluble solids (TSS), total acid (TA) and puncture force of fruit at five maturity stages which classified by the color and appearance. The results showed that the fully red fruits (the 4th grade) had the optimal eating quality parameter. Additionally, five different maturity grades of winter jujube were photographed as datasets and used the ResNet-50 model and the iResNet-50 model for training. And the iResNet-50 model was improved to overlap double residuals in the first Main Stage, with an accuracy of 98.35%, a precision of 98.40%, a recall of 98.35%, and a F1 score of 98.36%, which provided an important basis for automatic fundamental quality detection of winter jujube. This study provided ideas for fundamental quality classification of winter jujube during harvesting, fundamental quality screening of winter jujube in assembly line production, and real-time monitoring of winter jujube during transportation and storage. [ABSTRACT FROM AUTHOR]

In turning, the wear control of a cutting tool benefits product quality enhancement, tool-related costs' optimisation, and assists in avoiding undesired events. In small series and individual production, the machine operator is the one who determines when to change a cutting tool, based upon their experience. Bad decisions can often lead to greater costs, production downtime, and scrap. In this paper, a Tool Condition Monitoring (TCM) system is presented that automatically classifies tool wear of turning tools into four classes (no, low, medium, high wear). A cutting tool was monitored with infrared (IR) camera immediately after the cut and in the following 60 s. The Convolutional Neural Network Inception V3 was used to analyse and classify the thermographic images, which were divided into different groups depending on the time of acquisition. Based on classification result, one gets information about the cutting capability of the tool for further machining. The proposed model, combining Infrared Thermography, Computer Vision, and Deep Learning, proved to be a suitable method with results of more than 96% accuracy. The most appropriate time of image acquisition is 6–12 s after the cut is finished. While existing temperature based TCM systems focus on measuring a cutting tool absolute temperature, the proposed system analyses a temperature distribution (relative temperatures) on the whole image based on image features. [ABSTRACT FROM AUTHOR]

There is no doubt that CNN has made remarkable technological developments as the core technology of computer vision, but the pooling technique used for CNN has its own issues. This study set out to solve the issues of the pooling technique by proposing conditional min pooling and a restructured convolutional neural network that improved the pooling structure to ensure efficient use of the conditional min pooling. Some Caltech 101 and crawling data were used to test the performance of the conditional min pooling and restructured convolutional neural network. The pooling performance test based on Caltech 101 increased in accuracy by 0.16~0.52% and decreased in loss by 19.98~28.71% compared with the old pooling technique. The restructured convolutional neural network did not have a big improvement in performance compared to the old algorithm, but it provided significant outcomes with similar performance results to the algorithm. This paper presents the results that the loss rate was reduced rather than the accuracy rate, and this result was achieved without the improvement of convolution. [ABSTRACT FROM AUTHOR]

Railway transportation has always occupied an important position in daily life and social progress. In recent years, computer vision has made promising breakthroughs in intelligent transportation, providing new ideas for detecting rail lines. Yet the majority of rail line detection algorithms use traditional image processing to extract features, and their detection accuracy and instantaneity remain to be improved. This paper goes beyond the aforementioned limitations and proposes a rail line detection algorithm based on deep learning. First, an accurate and lightweight RailNet is designed, which takes full advantage of the powerful advanced semantic information extraction capabilities of deep convolutional neural networks to obtain high-level features of rail lines. The Segmentation Soul (SS) module is creatively added to the RailNet structure, which improves segmentation performance without any additional inference time. The Depth Wise Convolution (DWconv) is introduced in the RailNet to reduce the number of network parameters and eventually ensure real-time detection. Afterward, according to the binary segmentation maps of RailNet output, we propose the rail line fitting algorithm based on sliding window detection and apply the inverse perspective transformation. Thus the polynomial functions and curvature of the rail lines are calculated, and rail lines are identified in the original images. Furthermore, we collect a real-world rail lines dataset, named RAWRail. The proposed algorithm has been fully validated on the RAWRail dataset, running at 74 FPS, and the accuracy reaches 98.6%, which is superior to the current rail line detection algorithms and shows powerful potential in real applications. [ABSTRACT FROM AUTHOR]

Automated pavement distress recognition is a key step in smart infrastructure assessment. Advances in deep learning and computer vision have improved the automated recognition of pavement distresses in road surface images. This task remains challenging due to the high variation of defects in shapes and sizes, demanding a better incorporation of contextual information into deep networks. In this paper, we show that an attention-based multi-scale convolutional neural network (A+MCNN) improves the automated classification of common distress and non-distress objects in pavement images by (i) encoding contextual information through multi-scale input tiles and (ii) employing a mid-fusion approach with an attention module for heterogeneous image contexts from different input scales. A+MCNN is trained and tested with four distress classes (crack, crack seal, patch, pothole), five non-distress classes (joint, marker, manhole cover, curbing, shoulder), and two pavement classes (asphalt, concrete). A+MCNN is compared with four deep classifiers that are widely used in transportation applications and a generic CNN classifier (as the control model). The results show that A+MCNN consistently outperforms the baselines by 1∼26% on average in terms of the F-score. A comprehensive discussion is also presented regarding how these classifiers perform differently on different road objects, which has been rarely addressed in the existing literature. [ABSTRACT FROM AUTHOR]

Super resolution (SR) enables to generate a high-resolution (HR) image from one or more low-resolution (LR) images. Since a variety of CNN models have been recently studied in the areas of computer vision, these approaches have been combined with SR in order to provide higher image restoration. In this paper, we propose a lightweight CNN-based SR method, named multi-scale channel dense network (MCDN). In order to design the proposed network, we extracted the training images from the DIVerse 2K (DIV2K) dataset and investigated the trade-off between the SR accuracy and the network complexity. The experimental results show that the proposed method can significantly reduce the network complexity, such as the number of network parameters and total memory capacity, while maintaining slightly better or similar perceptual quality compared to the previous methods. [ABSTRACT FROM AUTHOR]

This paper investigates the determination of secondary dendrite arm spacing (SDAS) using convolutional neural networks (CNNs). The aim was to build a Deep Learning (DL) model for SDAS prediction that has industrially acceptable prediction accuracy. The model was trained on images of polished samples of high-pressure die-cast alloy EN AC 46000 AlSi9Cu3(Fe), the gravity die cast alloy EN AC 51400 AlMg5(Si) and the alloy cast as ingots EN AC 42000 AlSi7Mg. Color images were converted to grayscale to reduce the number of training parameters. It is shown that a relatively simple CNN structure can predict various SDAS values with very high accuracy, with a R 2 value of 91.5%. Additionally, the performance of the model is tested with materials not used during training; gravity die-cast EN AC 42200 AlSi7Mg0.6 alloy and EN AC 43400 AlSi10Mg(Fe) and EN AC 47100 Si12Cu1(Fe) high-pressure die-cast alloys. In this task, CNN performed slightly worse, but still within industrially acceptable standards. Consequently, CNN models can be used to determine SDAS values with industrially acceptable predictive accuracy. [ABSTRACT FROM AUTHOR]

Diabetes is a chronic condition caused by an uncontrolled blood sugar levels in the human body. Its early diagnosis may prevent severe complications such as diabetic foot ulcers (DFUs). A DFU is a critical condition that can lead to the amputation of a diabetic patient's lower limb. The diagnosis of DFU is very complicated for the medical professional as it often goes through several costly and time-consuming clinical procedures. In the age of data deluge, the application of deep learning, machine learning, and computer vision techniques have provided various solutions for assisting clinicians in making more reliable and faster diagnostic decisions. Therefore, the automatic identification of DFU has recently received more attention from the research community. The wound characteristics and visual perceptions with respect to computer vision and deep learning, especially convolutional neural network (CNN) approaches, have provided potential solutions for DFU diagnosis. These approaches have the potential to be quite helpful in current medical practices. Therefore, a detailed comprehensive study of such existing approaches was required. The article aimed to provide researchers with a detailed current status of automatic DFU identification tasks. Multiple observations have been made from existing works, such as the use of traditional ML and advanced DL techniques being necessary to help clinicians make faster and more reliable diagnostic decisions. In traditional ML approaches, image features provide signification information about DFU wounds and help with accurate identification. However, advanced DL approaches have proven to be more promising than ML approaches. The CNN-based solutions proposed by various authors have dominated the problem domain. An interested researcher will successfully be able identify the overall idea in the DFU identification task, and this article will help them finalize the future research goal. [ABSTRACT FROM AUTHOR]