Search

This document is an editorial for a special issue titled "Machine Learning in Computer Vision and Image Sensing: Theory and Applications." The editorial highlights the diverse applications of machine learning (ML) models in various domains such as medical imaging, signal processing, remote sensing, and human activity detection. The special issue includes 11 papers that cover topics such as image segmentation, fluvial navigation, Alzheimer's disease classification, pneumothorax detection, lung cancer malignancy prediction, amniotic fluid volume detection, COVID-19 detection, and Parkinson's disease detection. The papers showcase the progress and potential of ML models in computer vision applications and provide valuable insights for future research. [Extracted from the article]

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]

Image recognition has long been one of the research hotspots in computer vision tasks. The development of deep learning is rapid in recent years, and convolutional neural networks usually need to be designed with fixed resources. If sufficient resources are available, the model can be scaled up to achieve higher accuracy, for example, VggNet, ResNet, GoogLeNet, etc. Although the accuracy of large-scale models has been improved, the following problems will occur with the expansion of model scale: (1) There may be over-fitting; (2) increasing model parameters; (3) slow model convergence. This paper proposes a design method for a modular convolutional neural network model which solves the problem of over-fitting and large model parameters by connecting multiple modules in parallel. Moreover, each module contains several submodules (three submodules in this paper) and fuses the features extracted from the submodules. The model convergence can be accelerated by using the fused features (the fused features contain more image information). In this study, we add a gate unit based on the attention mechanism to the model, which aims to optimize the structure of the model (select the optimal number of modules), allowing the model to select an optimum network structure by learning and dynamically reducing FLOPs (floating-point operations per second) of the model. Compared to VggNet, ResNet, and GoogLeNet, the structure of the model proposed in this paper is simple and the parameters are small. The proposed model achieves good results in the Kaggle datasets Cats-vs.-Dogs (99.3%), 10-Monkey Species (99.26%), and Birds-400 (99.13%). [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]

Power distribution grids are typically installed outdoors and are exposed to environmental conditions. When contamination accumulates in the structures of the network, there may be shutdowns caused by electrical arcs. To improve the reliability of the network, visual inspections of the electrical power system can be carried out; these inspections can be automated using computer vision techniques based on deep neural networks. Based on this need, this paper proposes the Semi-ProtoPNet deep learning model to classify defective structures in the power distribution networks. The Semi-ProtoPNet deep neural network does not perform convex optimization of its last dense layer to maintain the impact of the negative reasoning process on image classification. The negative reasoning process rejects the incorrect classes of an input image; for this reason, it is possible to carry out an analysis with a low number of images that have different backgrounds, which is one of the challenges of this type of analysis. Semi-ProtoPNet achieves an accuracy of 97.22%, being superior to VGG-13, VGG-16, VGG-19, ResNet-34, ResNet-50, ResNet-152, DenseNet-121, DenseNet-161, DenseNet-201, and also models of the same class such as ProtoPNet, NP-ProtoPNet, Gen-ProtoPNet, and Ps-ProtoPNet. [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]

Datasets are the basis for research on deep learning methods in computer vision. The impact of the percentage of training sets in a dataset on the performance of neural network models needs to be further explored. In this paper, a twice equal difference enumeration (TEDE) algorithm is proposed to investigate the effect of different training set percentages in the dataset on the performance of the network model, and the optimal training set percentage is determined. By selecting the Pascal VOC dataset and dividing it into six different datasets from largest to smallest, and then dividing each dataset into the datasets to be analyzed according to five different training set percentages, the YOLOv5 convolutional neural network is used to train and test the 30 datasets to determine the optimal neural network model corresponding to the training set percentages. Finally, tests were conducted using the Udacity Self-Driving dataset with a self-made Tire Tread Defects (TTD) dataset. The results show that the network model performance is superior when the training set accounts for between 85% and 90% of the overall dataset. The results of dataset partitioning obtained by the TEDE algorithm can provide a reference for deep learning research. [ABSTRACT FROM AUTHOR]

Analysis of reports published by the leading national centers for monitoring wildfires and other emergencies revealed that the devastation caused by wildfires has increased by 2.96-fold when compared to a decade earlier. The reports show that the total number of wildfires is declining; however, their impact on the wildlife appears to be more devastating. In recent years, deep neural network models have demonstrated state-of-the-art accuracy on many computer vision tasks. In this paper, we describe the design and implementation of a lightweight wildfire image classification model (LW-FIRE) based on convolutional neural networks. We explore different ways of using the existing dataset to efficiently train a deep convolutional neural network. We also propose a new method for dataset transformation to increase the number of samples in the dataset and improve the accuracy and generalization of the deep learning model. Experimental results show that the proposed model outperforms the state-of-the-art methods, and is suitable for real-time classification of wildfire images. [ABSTRACT FROM AUTHOR]

License plate identification remains a crucial problem in computer vision, particularly in complex environments where license plates may be confused with road signs, billboards, and other objects. This paper proposes a solution by modifying the standard car–license plate–letter detection approach into a preliminary license plate detection–precise license plate detection of the four corners where the numbers are located–license plate correction–letter identification. This way, the first algorithm identifies all potential license plates and passes them as input parameters to the next algorithm for more precise detection. The main difference between this approach and other algorithms is that it uses a relatively small image compared to the whole vehicle. Thus, a small but robust network is used to find the four corners and perform a perspective transformation. This simplifies the letter recognition task for the next algorithm, as no additional transformations are required. This solution could be useful for research focusing on this specific task. It allows to apply another compact but robust neural network, increasing the overall speed of the system. Publicly available datasets were used for training and validation. The CenterNet object detection algorithm was used as a basis with a modified Hourglass-type network. The size of the network was decreased by 40% and the average accuracy was 96.19%. Speed significantly increased, reaching 2.71 ms and 405 FPS on average. [ABSTRACT FROM AUTHOR]

In the past decade, deep neural networks, particularly convolutional neural networks, have revolutionised computer vision. However, all deep learning models may require a large amount of data so as to achieve satisfying results. Unfortunately, the availability of sufficient amounts of data for real-world problems is not always possible, and it is well recognised that a paucity of data easily results in overfitting. This issue may be addressed through several approaches, one of which is data augmentation. In this paper, we survey the existing data augmentation techniques in computer vision tasks, including segmentation and classification, and suggest new strategies. In particular, we introduce a way of implementing data augmentation by using local information in images. We propose a parameter-free and easy to implement strategy, the random local rotation strategy, which involves randomly selecting the location and size of circular regions in the image and rotating them with random angles. It can be used as an alternative to the traditional rotation strategy, which generally suffers from irregular image boundaries. It can also complement other techniques in data augmentation. Extensive experimental results and comparisons demonstrated that the new strategy consistently outperformed its traditional counterparts in, for example, image classification. [ABSTRACT FROM AUTHOR]

Drowning is one of the top five causes of death for children aged 1–14 worldwide. According to data from the World Health Organization (WHO), drowning is the third most common reason for unintentional fatalities. Designing a drowning detection system is becoming increasingly necessary in order to ensure the safety of swimmers, particularly children. This paper presents a computer vision and deep learning-based early drowning detection approach. We utilized five convolutional neural network models and trained them on our data. These models are SqueezeNet, GoogleNet, AlexNet, ShuffleNet, and ResNet50. ResNet50 showed the best performance, as it achieved 100% prediction accuracy with a reasonable training time. When compared to other approaches, the proposed approach performed exceptionally well in terms of prediction accuracy and computational cost. [ABSTRACT FROM AUTHOR]

Person re-identification has become an essential application within computer vision due to its ability to match the same person over non-overlapping cameras. However, it is a challenging task because of the broad view of cameras with a large number of pedestrians appearing with various poses. As a result, various approaches of supervised model learning have been utilized to locate and identify a person based on the given input. Nevertheless, several of these approaches perform worse than expected in retrieving the right person in real-time over multiple CCTVs/camera views. This is due to inaccurate segmentation of the person, leading to incorrect classification. This paper proposes an efficient and real-time person re-identification system, named ReID-DeePNet system. It is based on fusing the matching scores generated by two different deep learning models, convolutional neural network and deep belief network, to extract discriminative feature representations from the pedestrian image. Initially, a segmentation procedure was developed based on merging the advantages of the Mask R-CNN and GrabCut algorithm to tackle the adverse effects caused by background clutter. Afterward, the two different deep learning models extracted discriminative feature representations from the pedestrian segmented image, and their matching scores were fused to make the final decision. Several extensive experiments were conducted, using three large-scale and challenging person re-identification datasets: Market-1501, CUHK03, and P-DESTRE. The ReID-DeePNet system achieved new state-of-the-art Rank-1 and mAP values on these three challenging ReID datasets. [ABSTRACT FROM AUTHOR]

The paper presents a simple, yet robust computer vision system for robot arm tracking with the use of RGB-D cameras. Tracking means to measure in real time the robot state given by three angles and with known restrictions about the robot geometry. The tracking system consists of two parts: image preprocessing and machine learning. In the machine learning part, we compare two approaches: fitting the robot pose to the point cloud and fitting the convolutional neural network model to the sparse 3D depth images. The advantage of the presented approach is direct use of the point cloud transformed to the sparse image in the network input and use of sparse convolutional and pooling layers (sparse CNN). The experiments confirm that the robot tracking is performed in real time and with an accuracy comparable to the accuracy of the depth sensor. [ABSTRACT FROM AUTHOR]

The success of deep convolutional neural networks in solving age-old computer vision challenges, particularly object detection, came with high requirements in terms of computation capability, energy consumption, and a lack of real-time processing capability. However, FPGA-based inference accelerations have recently been receiving more attention from academia and industry due to their high energy efficiency and flexible programmability. This paper presents resource-efficient yet high-performance object detection inference acceleration with detailed implementation and design choices. We tested our object detection acceleration by implementing YOLOv2 on two FPGA boards and achieved up to 184 GOPS with limited resource utilization. [ABSTRACT FROM AUTHOR]

Building extraction is a popular topic in remote sensing image processing. Efficient building extraction algorithms can identify and segment building areas to provide informative data for downstream tasks. Currently, building extraction is mainly achieved by deep convolutional neural networks (CNNs) based on the U-shaped encoder–decoder architecture. However, the local perceptive field of the convolutional operation poses a challenge for CNNs to fully capture the semantic information of large buildings, especially in high-resolution remote sensing images. Considering the recent success of the Transformer in computer vision tasks, in this paper, first we propose a shifted-window (swin) Transformer-based encoding booster. The proposed encoding booster includes a swin Transformer pyramid containing patch merging layers for down-sampling, which enables our encoding booster to extract semantics from multi-level features at different scales. Most importantly, the receptive field is significantly expanded by the global self-attention mechanism of the swin Transformer, allowing the encoding booster to capture the large-scale semantic information effectively and transcend the limitations of CNNs. Furthermore, we integrate the encoding booster in a specially designed U-shaped network through a novel manner, named the Swin Transformer-based Encoding Booster- U-shaped Network (STEB-UNet), to achieve the feature-level fusion of local and large-scale semantics. Remarkably, compared with other Transformer-included networks, the computational complexity and memory requirement of the STEB-UNet are significantly reduced due to the swin design, making the network training much easier. Experimental results show that the STEB-UNet can effectively discriminate and extract buildings of different scales and demonstrate higher accuracy than the state-of-the-art networks on public datasets. [ABSTRACT FROM AUTHOR]

Facial emotion recognition (FER) is an important topic in the fields of computer vision and artificial intelligence owing to its significant academic and commercial potential. Although FER can be conducted using multiple sensors, this review focuses on studies that exclusively use facial images, because visual expressions are one of the main information channels in interpersonal communication. This paper provides a brief review of researches in the field of FER conducted over the past decades. First, conventional FER approaches are described along with a summary of the representative categories of FER systems and their main algorithms. Deep-learning-based FER approaches using deep networks enabling “end-to-end” learning are then presented. This review also focuses on an up-to-date hybrid deep-learning approach combining a convolutional neural network (CNN) for the spatial features of an individual frame and long short-term memory (LSTM) for temporal features of consecutive frames. In the later part of this paper, a brief review of publicly available evaluation metrics is given, and a comparison with benchmark results, which are a standard for a quantitative comparison of FER researches, is described. This review can serve as a brief guidebook to newcomers in the field of FER, providing basic knowledge and a general understanding of the latest state-of-the-art studies, as well as to experienced researchers looking for productive directions for future work. [ABSTRACT FROM AUTHOR]

Over the past decade, deep learning-based computer vision methods have been shown to surpass previous state-of-the-art computer vision techniques in various fields, and have made great progress in various computer vision problems, including object detection, object segmentation, face recognition, etc. Nowadays, major IT companies are adding new deep-learning-based computer technologies to edge devices such as smartphones. However, since the computational cost of deep learning-based models is still high for edge devices, research is being actively carried out to compress deep learning-based models while not sacrificing high performance. Recently, many lightweight architectures have been proposed for deep learning-based models which are based on low-rank approximation. In this paper, we propose an alternating tensor compose-decompose (ATCD) method for the training of low-rank convolutional neural networks. The proposed training method can better train a compressed low-rank deep learning model than the conventional fixed-structure based training method, so that a compressed deep learning model with higher performance can be obtained in the end of the training. As a representative and exemplary model to which the proposed training method can be applied, we propose a rank-1 convolutional neural network (CNN) which has a structure alternatively containing 3-D rank-1 filters and 1-D filters in the training stage and a 1-D structure in the testing stage. After being trained, the 3-D rank-1 filters can be permanently decomposed into 1-D filters to achieve a fast inference in the test time. The reason that the 1-D filters are not being trained directly in 1-D form in the training stage is that the training of the 3-D rank-1 filters is easier due to the better gradient flow, which makes the training possible even in the case when the fixed structured network with fixed consecutive 1-D filters cannot be trained at all. We also show that the same training method can be applied to the well-known MobileNet architecture so that better parameters can be obtained than with the conventional fixed-structure training method. Furthermore, we show that the 1-D filters in a ResNet like structure can also be trained with the proposed method, which shows the fact that the proposed method can be applied to various structures of networks. [ABSTRACT FROM AUTHOR]

Due to the rapid development of RGB-D sensors, increasing attention is being paid to depth image applications. Depth images play an important role in computer vision research. In this paper, we address the problem of inpainting for single depth images without corresponding color images as a guide. Within the framework of model-based optimization methods for depth image inpainting, the split Bregman iteration algorithm was used to transform depth image inpainting into the corresponding denoising subproblem. Then, we trained a set of efficient convolutional neural network (CNN) denoisers to solve this subproblem. Experimental results demonstrate the effectiveness of the proposed algorithm in comparison with three traditional methods in terms of visual quality and objective metrics. [ABSTRACT FROM AUTHOR]

Smoke detection technology based on computer vision is a popular research direction in fire detection. This technology is widely used in outdoor fire detection fields (e.g., forest fire detection). Smoke detection is often based on features such as color, shape, texture, and motion to distinguish between smoke and non-smoke objects. However, the salience and robustness of these features are insufficiently strong, resulting in low smoke detection performance under complex environment. Deep learning technology has improved smoke detection performance to a certain degree, but extracting smoke detail features is difficult when the number of network layers is small. With no effective use of smoke motion characteristics, indicators such as false alarm rate are high in video smoke detection. To enhance the detection performance of smoke objects in videos, this paper proposes a concept of change-cumulative image by converting the YUV color space of multi-frame video images into a change-cumulative image, which can represent the motion and color-change characteristics of smoke. Then, a fusion deep network is designed, which increases the depth of the VGG16 network by arranging two convolutional layers after each of its convolutional layer. The VGG16 and Resnet50 (Deep residual network) network models are also arranged using the fusion deep network to improve feature expression ability while increasing the depth of the whole network. Doing so can help extract additional discriminating characteristics of smoke. Experimental results show that by using the change-cumulative image as the input image of the deep network model, smoke detection performance is superior to the classic RGB input image; the smoke detection performance of the fusion deep network model is better than that of the single VGG16 and Resnet50 network models; the smoke detection accuracy, false positive rate, and false alarm rate of this method are better than those of the current popular methods of video smoke detection. [ABSTRACT FROM AUTHOR]

With the development of deep learning in the field of computer vision, convolutional neural network models and attention mechanisms have been widely applied in SAR image target recognition. The improvement of convolutional neural network attention in existing SAR image target recognition focuses on spatial and channel information but lacks research on the relationship and recognition mechanism between spatial and channel information. In response to this issue, this article proposes a hybrid attention module and introduces a Mixed Attention (MA) mechanism module in the MobileNetV2 network. The proposed MA mechanism fully considers the comprehensive calculation of spatial attention (SPA), channel attention (CHA), and coordinated attention (CA). It can input feature maps for comprehensive weighting to enhance the features of the regions of interest, in order to improve the recognition rate of vehicle targets in SAR images.The superiority of our algorithm was verified through experiments on the MSTAR dataset. [ABSTRACT FROM AUTHOR]

Skin cancer poses a serious risk to one's health and can only be effectively treated with early detection. Early identification is critical since skin cancer has a higher fatality rate, and it expands gradually to different areas of the body. The rapid growth of automated diagnosis frameworks has led to the combination of diverse machine learning, deep learning, and computer vision algorithms for detecting clinical samples and atypical skin lesion specimens. Automated methods for recognizing skin cancer that use deep learning techniques are discussed in this article: convolutional neural networks, and, in general, artificial neural networks. The recognition of symmetries is a key point in dealing with the skin cancer image datasets; hence, in developing the appropriate architecture of neural networks, as it can improve the performance and release capacities of the network. The current study emphasizes the need for an automated method to identify skin lesions to reduce the amount of time and effort required for the diagnostic process, as well as the novel aspect of using algorithms based on deep learning for skin lesion detection. The analysis concludes with underlying research directions for the future, which will assist in better addressing the difficulties encountered in human skin cancer recognition. By highlighting the drawbacks and advantages of prior techniques, the authors hope to establish a standard for future analysis in the domain of human skin lesion diagnostics. [ABSTRACT FROM AUTHOR]

The potential benefits of recognising activities of daily living from video for active and assisted living have yet to be fully untapped. These technologies can be used for behaviour understanding, and lifelogging for caregivers and end users alike. The recent publication of realistic datasets for this purpose, such as the Toyota Smarthomes dataset, calls for pushing forward the efforts to improve action recognition. Using the separable spatio-temporal attention network proposed in the literature, this paper introduces a view-invariant normalisation of skeletal pose data and full activity crops for RGB data, which improve the baseline results by 9.5% (on the cross-subject experiments), outperforming state-of-the-art techniques in this field when using the original unmodified skeletal data in dataset. Our code and data are available online. [ABSTRACT FROM AUTHOR]

In recent years, with the growing proliferation of photovoltaics (PV), accurate nowcasting of PV power has emerged as a challenge. Global horizontal irradiance (GHI), which is a key factor influencing PV power, is known to be highly variable as it is determined by short-term meteorological phenomena, particularly cloud movement. Deep learning and computer vision techniques applied to all-sky imagery are demonstrated to be highly accurate nowcasting methods, as they encode crucial information about the sky's state. While these methods utilize deep neural network models, such as Convolutional Neural Networks (CNN), and attain high levels of accuracy, the training of image-based deep learning models demands significant computational resources. In this work, we present a computationally economical estimation technique, based on a deep learning model. We utilize both all-sky imagery and meteorological data, however, information on the sky's state is encoded as a feature vector extracted using traditional image processing methods. We introduce six all-sky image features utilizing detailed knowledge of meteorological and physical phenomena, significantly decreasing the amount of input data and model complexity. We investigate the accuracy of the determined global and diffuse radiation for different combinations of meteorological parameters. The model is evaluated using two years of measurements from an on-site all-sky camera and an adjacent meteorological station. Our findings demonstrate that the model provides comparable accuracy to CNN-based methods, yet at a significantly lower computational cost. [ABSTRACT FROM AUTHOR]

Facial emotion recognition (FER) stands as a pivotal artificial intelligence (AI)-driven technology that exploits the capabilities of computer-vision techniques for decoding and comprehending emotional expressions displayed on human faces. With the use of machine-learning (ML) models, specifically deep neural networks (DNN), FER empowers the automatic detection and classification of a broad spectrum of emotions, encompassing surprise, happiness, sadness, anger, and more. Challenges in FER include handling variations in lighting, poses, and facial expressions, as well as ensuring that the model generalizes well to various emotions and populations. This study introduces an automated facial emotion recognition using the pelican optimization algorithm with a deep convolutional neural network (AFER-POADCNN) model. The primary objective of the AFER-POADCNN model lies in the automatic recognition and classification of facial emotions. To accomplish this, the AFER-POADCNN model exploits the median-filtering (MF) approach to remove the noise present in it. Furthermore, the capsule-network (CapsNet) approach can be applied to the feature-extraction process, allowing the model to capture intricate facial expressions and nuances. To optimize the CapsNet model's performance, hyperparameter tuning is undertaken with the aid of the pelican optimization algorithm (POA). This ensures that the model is finely tuned to detect a wide array of emotions and generalizes effectively across diverse populations and scenarios. Finally, the detection and classification of different kinds of facial emotions take place using a bidirectional long short-term memory (BiLSTM) network. The simulation analysis of the AFER-POADCNN system is tested on a benchmark FER dataset. The comparative result analysis showed the better performance of the AFER-POADCNN algorithm over existing models, with a maximum accuracy of 99.05%. [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]

Face recognition is one of the essential applications in computer vision, while current face recognition technology is mainly based on 2D images without depth information, which are easily affected by illumination and facial expressions. This paper presents a fast face recognition algorithm combining 3D point cloud face data with deep learning, focusing on key part of face for recognition with an attention mechanism, and reducing the coding space by the sparse loss function. First, an attention mechanism-based convolutional neural network was constructed to extract facial features to avoid expressions and illumination interference. Second, a Siamese network was trained with a sparse loss function to minimize the face coding space and enhance the separability of the face features. With the FRGC face dataset, the experimental results show that the proposed method could achieve the recognition accuracy of 95.33%. [ABSTRACT FROM AUTHOR]

Artificial neural networks have become the go-to solution for computer vision tasks, including problems of the security domain. One such example comes in the form of reidentification, where deep learning can be part of the surveillance pipeline. The use case necessitates considering an adversarial setting—and neural networks have been shown to be vulnerable to a range of attacks. In this paper, the preprocessing defences against adversarial attacks are evaluated, including block-matching convolutional neural network for image denoising used as an adversarial defence. The benefit of using preprocessing defences comes from the fact that it does not require the effort of retraining the classifier, which, in computer vision problems, is a computationally heavy task. The defences are tested in a real-life-like scenario of using a pre-trained, widely available neural network architecture adapted to a specific task with the use of transfer learning. Multiple preprocessing pipelines are tested and the results are promising. [ABSTRACT FROM AUTHOR]

Simple Summary: Aggressive behavior can cause severe harm to pigs, especially in poor housing conditions, leading to disease and even death, which causes significant losses for the pig farm. Therefore, the automatic and accurate recognition of aggressive behavior of commercially housed pigs is important for pig farm production management. In this study, we proposed a video behavior recognition method based on the temporal shift module (TSM) that can detect whether aggressive behavior occurred in pig groups automatically. TSM is a convolutional neural network module to process video sequence data. Experimental results demonstrated that the method can recognize pig aggression effectively, which helps improve the use of automated management techniques in pig farming. Aggressive behavior among pigs is a significant social issue that has severe repercussions on both the profitability and welfare of pig farms. Due to the complexity of aggression, recognizing it requires the consideration of both spatial and temporal features. To address this problem, we proposed an efficient method that utilizes the temporal shift module (TSM) for automatic recognition of pig aggression. In general, TSM is inserted into four 2D convolutional neural network models, including ResNet50, ResNeXt50, DenseNet201, and ConvNext-t, enabling the models to process both spatial and temporal features without increasing the model parameters and computational complexity. The proposed method was evaluated on the dataset established in this study, and the results indicate that the ResNeXt50-T (TSM inserted into ResNeXt50) model achieved the best balance between recognition accuracy and model parameters. On the test set, the ResNeXt50-T model achieved accuracy, recall, precision, F1 score, speed, and model parameters of 95.69%, 95.25%, 96.07%, 95.65%, 29 ms, and 22.98 M, respectively. These results show that the proposed method can effectively improve the accuracy of recognizing pig aggressive behavior and provide a reference for behavior recognition in actual scenarios of smart livestock farming. [ABSTRACT FROM AUTHOR]

The advancement of both the fields of Computer Vision (CV) and Artificial Neural Networks (ANNs) has enabled the development of effective automatic systems for analyzing human behavior. It is possible to recognize gestures, which are frequently used by people to communicate information non-verbally, by studying hand movements. So, the main contribution of this research is the collected dataset, which is taken from open-source videos of the relevant subjects that contain actions that depict confidence levels. The dataset contains high-quality frames with minimal bias and less noise. Secondly, we have chosen the domain of confidence determination during social issues such as interviews, discussions, or criminal investigations. Thirdly, the proposed model is a combination of two high-performing models, i.e., CNN (GoogLeNet) and LSTM. GoogLeNet is the state-of-the-art architecture for hand detection and gesture recognition. LSTM prevents the loss of information by keeping temporal data. So the combination of these two outperformed during the training and testing process. This study presents a method to recognize different categories of Self-Efficacy by performing multi-class classification based on the current situation of hand movements using visual data processing and feature extraction. The proposed architecture pre-processes the sequence of images collected from different scenarios, including humans, and their quality frames are extracted. These frames are then processed to extract and analyze the features regarding their body joints and hand position and classify them into four different classes related to efficacy, i.e., confidence, cooperation, confusion, and uncomfortable. The features are extracted using a combination framework of customized Convolutional Neural Network (CNN) layers with Long Short-Term Memory (LSTM) for feature extraction and classification. Remarkable results have been achieved from this study representing 90.48% accuracy with effective recognition of human body gestures through deep learning approaches. [ABSTRACT FROM AUTHOR]

Inverse halftoning acting as a special image restoration problem is an ill-posed problem. Although it has been studied in the last several decades, the existing solutions can't restore fine details and texture accurately from halftone images. Recently, the attention mechanism has shown its powerful effects in many fields, such as image processing, pattern recognition and computer vision. However, it has not yet been used in inverse halftoning. To better solve the problem of detail restoration of inverse halftoning, this paper proposes a simple yet effective deep learning model combined with the attention mechanism, which can better guide the network to remove noise dot-patterns and restore image details, and improve the network adaptation ability. The whole model is designed in an end-to-end manner, including feature extraction stage and reconstruction stage. In the feature extraction stage, halftone image features are extracted and halftone noises are removed. The reconstruction stage is employed to restore continuous-tone images by fusing the feature information extracted in the first stage and the output of the residual channel attention block. In this stage, the attention block is firstly introduced to the field of inverse halftoning, which can make the network focus on informative features and further enhance the discriminative ability of the network. In addition, a multi-stage loss function is proposed to accelerate the network optimization, which is conducive to better reconstruction of the global image. To demonstrate the generalization performance of the network for different types of halftone images, the experiment results confirm that the network can restore six different types of halftone image well. Furthermore, experimental results show that our method outperforms the state-of-the-art methods, especially in the restoration of details and textures. [ABSTRACT FROM AUTHOR]

In recent years, the technology of artificial intelligence (AI) and robots is rapidly spreading to countries around the world. More and more scholars and industry experts have proposed AI deep learning models and methods to solve human life problems and improve work efficiency. Modern people's lives are very busy, which led us to investigate whether the demand for Bento buffet cafeterias has gradually increased in Taiwan. However, when eating at a buffet in a cafeteria, people often encounter two problems. The first problem is that customers need to queue up to check out after they have selected and filled their dishes from the buffet. However, it always takes too much time waiting, especially at lunch or dinner time. The second problem is sometimes customers question the charges calculated by cafeteria staff, claiming they are too expensive at the checkout counter. Therefore, it is necessary to develop an AI-enabled checkout system. The AI-enabled self-checkout system will help the Bento buffet cafeterias reduce long lineups without the need to add additional workers. In this paper, we used computer vision and deep-learning technology to design and implement an AI-enabled checkout system for Bento buffet cafeterias. The prototype contains an angle steel shelf, a Kinect camera, a light source, and a desktop computer. Six baseline convolutional neural networks were applied for comparison on food recognition. In our experiments, there were 22 different food categories in a Bento buffet cafeteria employed. Experimental results show that the inception_v4 model can achieve the highest average validation accuracy of 99.11% on food recognition, but it requires the most training and recognition time. AlexNet model achieves a 94.5% accuracy and requires the least training time and recognition time. We propose a hierarchical approach with two stages to achieve good performance in both the recognition accuracy rate and the required training and recognition time. The approach is designed to perform the first step of identification and the second step of recognizing similar food images, respectively. Experimental results show that the proposed approach can achieve a 96.3% accuracy rate on our test dataset and required very little recognition time for input images. In addition, food volumes could be estimated using the depth images captured by the Kinect camera, and a framework of visual checkout system was successfully built. [ABSTRACT FROM AUTHOR]

Deep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than other 3D deep learning methods, and even worse than their 2D version. In this paper, we propose to improve 3D deep learning results by transferring the pretrained weights learned in 2D networks to their corresponding 3D version. Using an industrial object recognition context, we have analyzed different combinations of 3D convolutional networks (VGG16, ResNet, Inception ResNet, and EfficientNet), comparing the recognition accuracy. The highest accuracy is obtained with EfficientNetB0 using extrusion with an accuracy of 0.9217, which gives comparable results to state-of-the art methods. We also observed that the transfer approach enabled to improve the accuracy of the Inception ResNet 3D version up to 18% with respect to the score of the 3D approach alone. [ABSTRACT FROM AUTHOR]

This work aims to classify normal and carcinogenic cells in the oral cavity using two different approaches with an eye towards achieving high accuracy. The first approach extracts local binary patterns and metrics derived from a histogram from the dataset and is fed to several machine-learning models. The second approach uses a combination of neural networks as a backbone feature extractor and a random forest for classification. The results show that information can be learnt effectively from limited training images using these approaches. Some approaches use deep learning algorithms to generate a bounding box that can locate the suspected lesion. Other approaches use handcrafted textural feature extraction techniques and feed the resultant feature vectors to a classification model. The proposed method will extract the features pertaining to the images using pre-trained convolution neural networks (CNN) and train a classification model using the resulting feature vectors. By using the extracted features from a pre-trained CNN model to train a random forest, the problem of requiring a large amount of data to train deep learning models is bypassed. The study selected a dataset consisting of 1224 images, which were divided into two sets with varying resolutions.The performance of the model is calculated based on accuracy, specificity, sensitivity, and the area under curve (AUC). The proposed work is able to produce a highest test accuracy of 96.94% and an AUC of 0.976 using 696 images of 400× magnification and a highest test accuracy of 99.65% and an AUC of 0.9983 using only 528 images of 100× magnification images. [ABSTRACT FROM AUTHOR]

Monitoring damage in concrete structures is crucial for maintaining the health of structural systems. The implementation of computer vision has been the key for providing accurate and quantitative monitoring. Recent development uses the robustness of deep-learning-aided computer vision, especially the convolutional neural network model. The convolutional neural network is not only accurate but also flexible in various scenarios. The convolutional neural network has been constructed to classify image in terms of individual pixel, namely pixel-level detection, which is especially useful in detecting and classifying damage in fine-grained detail. Moreover, in the real-world scenario, the scenes are mostly very complex with varying foreign objects other than concrete. Therefore, this study will focus on implementing a pixel-level convolutional neural network for concrete surface damage detection with complicated surrounding image settings. Since there are multiple types of damage on concrete surfaces, the convolutional neural network model will be trained to detect three types of damages, namely cracks, spallings, and voids. The training architecture will adopt U-Net and DeepLabV3+. Both models are compared using the evaluation metrics and the predicted results. The dataset used for the neural network training is self-built and contains multiple concrete damages and complex foregrounds on every image. To deal with overfitting, the dataset is augmented, and the models are regularized using L1 and Spatial dropout. U-Net slightly outperforms DeepLabV3+ with U-Net scores 0.7199 and 0.5993 on F1 and mIoU, respectively, while DeepLabV3+ scores 0.6478 and 0.5174 on F1 and mIoU, respectively. Given the complexity of the dataset and extensive image labeling, the neural network models achieved satisfactory results. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have achieved great success in the field of computer vision. The high requirements for memory and storage by DNNs make it difficult to apply them to mobile or embedded devices. Therefore, compression and structure optimization of deep neural networks have become a hot research topic. To eliminate redundant structures in deep convolutional neural networks (DCNNs), we propose an efficient filter pruning framework via deep reinforcement learning (DRL). The proposed framework is based on a deep deterministic policy gradient (DDPG) algorithm for filter pruning rate optimization. The main features of the proposed framework are as follows: (1) AA tailored reward function considering both accuracy and complexity of DCNN is proposed for the training of DDPG and (2) a novel filter sorting criterion based on Taylor expansion is developed for filter pruning selection. To illustrate the effectiveness of the proposed framework, extensive comparative studies on large public datasets and well-recognized DCNNs are conducted. The experimental results demonstrate that the Taylor-expansion-based filter sorting criterion is much better than the widely used minimum-weight-based criterion. More importantly, the proposed filter pruning framework can achieve over 10× parameter compression and 3× floating point operations (FLOPs) reduction while maintaining similar accuracy to the original network. The performance of the proposed framework is promising compared with state-of-the-art DRL-based filter pruning methods. [ABSTRACT FROM AUTHOR]

Pack-ice seals are key indicator species in the Southern Ocean. Their large size (2–4 m) and continent-wide distribution make them ideal candidates for monitoring programs via very-high-resolution satellite imagery. The sheer volume of imagery required, however, hampers our ability to rely on manual annotation alone. Here, we present SealNet 2.0, a fully automated approach to seal detection that couples a sea ice segmentation model to find potential seal habitats with an ensemble of semantic segmentation convolutional neural network models for seal detection. Our best ensemble attains 0.806 precision and 0.640 recall on an out-of-sample test dataset, surpassing two trained human observers. Built upon the original SealNet, it outperforms its predecessor by using annotation datasets focused on sea ice only, a comprehensive hyperparameter study leveraging substantial high-performance computing resources, and post-processing through regression head outputs and segmentation head logits at predicted seal locations. Even with a simplified version of our ensemble model, using AI predictions as a guide dramatically boosted the precision and recall of two human experts, showing potential as a training device for novice seal annotators. Like human observers, the performance of our automated approach deteriorates with terrain ruggedness, highlighting the need for statistical treatment to draw global population estimates from AI output. [ABSTRACT FROM AUTHOR]

The interaction between humans and an NAO robot using deep convolutional neural networks (CNN) is presented in this paper based on an innovative end-to-end pipeline method that applies two optimized CNNs, one for face recognition (FR) and another one for the facial expression recognition (FER) in order to obtain real-time inference speed for the entire process. Two different models for FR are considered, one known to be very accurate, but has low inference speed (faster region-based convolutional neural network), and one that is not as accurate but has high inference speed (single shot detector convolutional neural network). For emotion recognition transfer learning and fine-tuning of three CNN models (VGG, Inception V3 and ResNet) has been used. The overall results show that single shot detector convolutional neural network (SSD CNN) and faster region-based convolutional neural network (Faster R-CNN) models for face detection share almost the same accuracy: 97.8% for Faster R-CNN on PASCAL visual object classes (PASCAL VOCs) evaluation metrics and 97.42% for SSD Inception. In terms of FER, ResNet obtained the highest training accuracy (90.14%), while the visual geometry group (VGG) network had 87% accuracy and Inception V3 reached 81%. The results show improvements over 10% when using two serialized CNN, instead of using only the FER CNN, while the recent optimization model, called rectified adaptive moment optimization (RAdam), lead to a better generalization and accuracy improvement of 3%-4% on each emotion recognition CNN. [ABSTRACT FROM AUTHOR]

Deep learning has already been proved as a powerful state-of-the-art technique for many image understanding tasks in computer vision and other applications including remote sensing (RS) image analysis. Unmanned aircraft systems (UASs) offer a viable and economical alternative to a conventional sensor and platform for acquiring high spatial and high temporal resolution data with high operational flexibility. Coastal wetlands are among some of the most challenging and complex ecosystems for land cover prediction and mapping tasks because land cover targets often show high intra-class and low inter-class variances. In recent years, several deep convolutional neural network (CNN) architectures have been proposed for pixel-wise image labeling, commonly called semantic image segmentation. In this paper, some of the more recent deep CNN architectures proposed for semantic image segmentation are reviewed, and each model's training efficiency and classification performance are evaluated by training it on a limited labeled image set. Training samples are provided using the hyper-spatial resolution UAS imagery over a wetland area and the required ground truth images are prepared by manual image labeling. Experimental results demonstrate that deep CNNs have a great potential for accurate land cover prediction task using UAS hyper-spatial resolution images. Some simple deep learning architectures perform comparable or even better than complex and very deep architectures with remarkably fewer training epochs. This performance is especially valuable when limited training samples are available, which is a common case in most RS applications. [ABSTRACT FROM AUTHOR]

Computer vision recently has many applications such as smart cars, robot navigation, and computer-aided manufacturing. Object classification, in particular 3D classification, is a major part of computer vision. In this paper, we propose a novel method, wave kernel signature (WKS) and a center point (CP) method, which extracts color and distance features from a 3D model to tackle 3D object classification. The motivation of this idea is from the nature of human vision, which we tend to classify an object based on its color and size. Firstly, we find a center point of the mesh to define distance feature. Secondly, we calculate eigenvalues from the 3D mesh, and WKS values, respectively, to capture color feature. These features will be an input of a 2D convolution neural network (CNN) architecture. We use two large-scale 3D model datasets: ModelNet10 and ModelNet40 to evaluate the proposed method. Our experimental results show more accuracy and efficiency than other methods. The proposed method could apply for actual-world problems like autonomous driving and augmented/virtual reality. [ABSTRACT FROM AUTHOR]

Deep learning methods, especially deep convolutional neural networks (DCNNs), have been widely used in high-resolution remote sensing image (HRSI) semantic segmentation. In literature, most successful DCNNs are artificially designed through a large number of experiments, which often consume lots of time and depend on rich domain knowledge. Recently, neural architecture search (NAS), as a direction for automatically designing network architectures, has achieved great success in different kinds of computer vision tasks. For HRSI semantic segmentation, NAS faces two major challenges: (1) The task's high complexity degree, which is caused by the pixel-by-pixel prediction demand in semantic segmentation, leads to a rapid expansion of the search space; (2) HRSI semantic segmentation often needs to exploit long-range dependency (i.e., a large spatial context), which means the NAS technique requires a lot of display memory in the optimization process and can be tough to converge. With the aforementioned considerations in mind, we propose a new decoupling NAS (DNAS) framework to automatically design the network architecture for HRSI semantic segmentation. In DNAS, a hierarchical search space with three levels is recommended: path-level, connection-level, and cell-level. To adapt to this hierarchical search space, we devised a new decoupling search optimization strategy to decrease the memory occupation. More specifically, the search optimization strategy consists of three stages: (1) a light super-net (i.e., the specific search space) in the path-level space is trained to get the optimal path coding; (2) we endowed the optimal path with various cross-layer connections and it is trained to obtain the connection coding; (3) the super-net, which is initialized by path coding and connection coding, is populated with kinds of concrete cell operators and the optimal cell operators are finally determined. It is worth noting that the well-designed search space can cover various network candidates and the optimization process can be done efficiently. Extensive experiments on the publicly open GID and FU datasets showed that our DNAS outperformed the state-of-the-art methods, including artificial networks and NAS methods. [ABSTRACT FROM AUTHOR]

Crowd counting, which is widely used in disaster management, traffic monitoring, and other fields of urban security, is a challenging task that is attracting increasing interest from researchers. For better accuracy, most methods have attempted to handle the scale variation explicitly. which results in huge scale changes of the object size. However, earlier methods based on convolutional neural networks (CNN) have focused primarily on improving accuracy while ignoring the complexity of the model. This paper proposes a novel method based on a lightweight CNN-based network for estimating crowd counting and generating density maps under resource constraints. The network is composed of three components: a basic feature extractor (BFE), a stacked à trous convolution module (SACM), and a context fusion module (CFM). The BFE encodes basic feature information with reduced spatial resolution for further refining. Various pieces of contextual information are generated through a short pipeline in SACM. To generate a context fusion density map, CFM distills feature maps from the above components. The whole network is trained in an end-to-end fashion and uses a compression factor to restrict its size. Experiments on three highly-challenging datasets demonstrate that the proposed method delivers attractive performance. [ABSTRACT FROM AUTHOR]

Every year, marine scientists around the world read thousands of otolith or scale images to determine the age structure of commercial fish stocks. This knowledge is important for fisheries and conservation management. However, the age-reading procedure is time-consuming and costly to perform due to the specialized expertise and labor needed to identify annual growth zones in otoliths. Effective automated systems are needed to increase throughput and reduce cost. DeepOtolith is an open-source artificial intelligence (AI) platform that addresses this issue by providing a web system with a simple interface that automatically estimates fish age by combining otolith images with convolutional neural networks (CNNs), a class of deep neural networks that has been a dominant method in computer vision tasks. Users can upload otolith image data for selective fish species, and the platform returns age estimates. The estimates of multiple images can be exported to conduct conclusions or further age-related research. DeepOtolith currently contains classifiers/regressors for three fish species; however, more species will be included as related work on ageing will be tested and published soon. Herein, the architecture and functionality of the platform are presented. Current limitations and future directions are also discussed. Overall, DeepOtolith should be considered as the first step towards building a community of marine ecologists, machine learning experts, and stakeholders that will collaborate to support the conservation of fishery resources. [ABSTRACT FROM AUTHOR]

Recent years have witnessed the widespread research of the surface defect detection technology based on machine vision, which has spawned various effective detection methods. In particular, the rise of deep learning has allowed the surface defect detection technology to develop further. However, these methods based on deep learning still have some drawbacks. For example, the size of the sample data is not large enough to support deep learning; the location and recognition of surface defects are not accurate enough; the real-time performance of segmentation and classification is not satisfactory. In the context, this paper proposes an end-to-end convolutional neural network model: the pixel-wise segmentation and image-wise classification network (PSIC-Net). With the innovative design of a three-stage network structure, improved loss function and a two-step training mode, PSIC-Net can accurately and quickly segment and classify surface defects with a small dataset of training data. This model was evaluated with three public datasets, and compared with the most advanced defect detection methods. All the performance metrics prove the effectiveness and advancement of PSIC-Net. [ABSTRACT FROM AUTHOR]

The main goal of any classification or regression task is to obtain a model that will generalize well on new, previously unseen data. Due to the recent rise of deep learning and many state-of-the-art results obtained with deep models, deep learning architectures have become one of the most used model architectures nowadays. To generalize well, a deep model needs to learn the training data well without overfitting. The latter implies a correlation of deep model optimization and regularization with generalization performance. In this work, we explore the effect of the used optimization algorithm and regularization techniques on the final generalization performance of the model with convolutional neural network (CNN) architecture widely used in the field of computer vision. We give a detailed overview of optimization and regularization techniques with a comparative analysis of their performance with three CNNs on the CIFAR-10 and Fashion-MNIST image datasets. [ABSTRACT FROM AUTHOR]

Nowadays, deep learning is the fastest growing research field in machine learning and has a tremendous impact on a plethora of daily life applications, ranging from security and surveillance to autonomous driving, automatic indexing and retrieval of media content, text analysis, speech recognition, automatic translation, and many others. Inspired by Faster R-CNN [[5]], object detection in infrared streetscape images is addressed in [[6]] by exploiting both fine- and coarse-grained image features. In particular, the authors of [[10]] propose a CNN compression method that exploits kernel density estimation to perform a fast 4-bit quantization of the network weights without impairing classification performance. As an example, in [[22]], CNN and particle swarm optimization are jointly employed to predict large-scale wind power, while in [[23]], a self-attention CNN is used to classify the heartbeat signal of hatching eggs in order to tell apart dead from alive ones in commercial poultry breeding. [Extracted from the article]

Colonoscopy, which refers to the endoscopic examination of colon using a camera, is considered as the most effective method for diagnosis of colorectal cancer. Colonoscopy is performed by a medical doctor who visually inspects one's colon to find protruding or cancerous polyps. In some situations, these polyps are difficult to find by the human eye, which may lead to a misdiagnosis. In recent years, deep learning has revolutionized the field of computer vision due to its exemplary performance. This study proposes a Convolutional Neural Network (CNN) architecture for classifying colonoscopy images as normal, adenomatous polyps, and adenocarcinoma. The main objective of this study is to aid medical practitioners in the correct diagnosis of colorectal cancer. Our proposed CNN architecture consists of 43 convolutional layers and one fully-connected layer. We trained and evaluated our proposed network architecture on the colonoscopy image dataset with 410 test subjects provided by Gachon University Hospital. Our experimental results showed an accuracy of 94.39% over 410 test subjects. [ABSTRACT FROM AUTHOR]

Nonalcoholic fatty liver disease (NAFLD) is responsible for a wide range of pathological disorders. It is characterized by the prevalence of steatosis, which results in excessive accumulation of triglyceride in the liver tissue. At high rates, it can lead to a partial or total occlusion of the organ. In contrast, nonalcoholic steatohepatitis (NASH) is a progressive form of NAFLD, with the inclusion of hepatocellular injury and inflammation histological diseases. Since there is no approved pharmacotherapeutic solution for both conditions, physicians and engineers are constantly in search for fast and accurate diagnostic methods. The proposed work introduces a fully automated classification approach, taking into consideration the high discrimination capability of four histological tissue alterations. The proposed work utilizes a deep supervised learning method, with a convolutional neural network (CNN) architecture achieving a classification accuracy of 95%. The classification capability of the new CNN model is compared with a pre-trained AlexNet model, a visual geometry group (VGG)-16 deep architecture and a conventional multilayer perceptron (MLP) artificial neural network. The results show that the constructed model can achieve better classification accuracy than VGG-16 (94%) and MLP (90.3%), while AlexNet emerges as the most efficient classifier (97%). [ABSTRACT FROM AUTHOR]

Maize is one of the essential crops for food supply. Accurate sorting of seeds is critical for cultivation and marketing purposes, while the traditional methods of variety identification are time-consuming, inefficient, and easily damaged. This study proposes a rapid classification method for maize seeds using a combination of machine vision and deep learning. 8080 maize seeds of five varieties were collected, and then the sample images were classified into training and validation sets in the proportion of 8:2, and the data were enhanced. The proposed improved network architecture, namely P-ResNet, was fine-tuned for transfer learning to recognize and categorize maize seeds, and then it compares the performance of the models. The results show that the overall classification accuracy was determined as 97.91, 96.44, 99.70, 97.84, 98.58, 97.13, 96.59, and 98.28% for AlexNet, VGGNet, P-ResNet, GoogLeNet, MobileNet, DenseNet, ShuffleNet, and EfficientNet, respectively. The highest classification accuracy result was obtained with P-ResNet, and the model loss remained at around 0.01. This model obtained the accuracy of classifications for BaoQiu, ShanCu, XinNuo, LiaoGe, and KouXian varieties, which reached 99.74, 99.68, 99.68, 99.61, and 99.80%, respectively. The experimental results demonstrated that the convolutional neural network model proposed enables the effective classification of maize seeds. It can provide a reference for identifying seeds of other crops and be applied to consumer use and the food industry. [ABSTRACT FROM AUTHOR]

Currently, video observation systems are actively used for volcano activity monitoring. Video cameras allow us to remotely assess the state of a dangerous natural object and to detect thermal anomalies if technical capabilities are available. However, continuous use of visible band cameras instead of special tools (for example, thermal cameras), produces large number of images, that require the application of special algorithms both for preliminary filtering out the images with area of interest hidden due to weather or illumination conditions, and for volcano activity detection. Existing algorithms use preselected regions of interest in the frame for analysis. This region could be changed occasionally to observe events in a specific area of the volcano. It is a problem to set it in advance and keep it up to date, especially for an observation network with multiple cameras. The accumulated perennial archives of images with documented eruptions allow us to use modern deep learning technologies for whole frame analysis to solve the specified task. The article presents the development of algorithms to classify volcano images produced by video observation systems. The focus is on developing the algorithms to create a labelled dataset from an unstructured archive using existing and authors proposed techniques. The developed solution was tested using the archive of the video observation system for the volcanoes of Kamchatka, in particular the observation data for the Klyuchevskoy volcano. The tests show the high efficiency of the use of convolutional neural networks in volcano image classification, and the accuracy of classification achieved 91%. The resulting dataset consisting of 15,000 images and labelled in three classes of scenes is the first dataset of this kind of Kamchatka volcanoes. It can be used to develop systems for monitoring other stratovolcanoes that occupy most of the video frame. [ABSTRACT FROM AUTHOR]

Archaeologists engaging with Airborne Laser Scanning (ALS) data rely heavily on manual inspection of various derived visualizations. However, manual inspection of ALS data is extremely time-consuming and as such presents a major bottleneck in the data analysis workflow. We have therefore set out to learn and test a deep neural network model for classifying from previously manually annotated ancient Maya structures of the Chactún archaeological site in Campeche, Mexico. We considered several variations of the VGG-19 Convolutional Neural Network (CNN) to solve the task of classifying visualized example structures from previously manually annotated ALS images of man-made aguadas, buildings and platforms, as well as images of surrounding terrain (four classes and over 12,000 anthropogenic structures). We investigated how various parameters impact model performance, using: (a) six different visualization blends, (b) two different edge buffer sizes, (c) additional data augmentation and (d) architectures with different numbers of untrainable, frozen layers at the beginning of the network. Many of the models learned under the different scenarios exceeded the overall classification accuracy of 95%. Using overall accuracy, terrain precision and recall (detection rate) per class of anthropogenic structure as criteria, we selected visualization with slope, sky-view factor and positive openness in separate bands; image samples with a two-pixels edge buffer; Keras data augmentation; and five frozen layers as the optimal combination of building blocks for learning our CNN model. [ABSTRACT FROM AUTHOR]