Search

As one of the fatal human diseases, early detection of brain tumors can effectively save patients' lives. Brain tumor image segmentation is of great practical importance for physicians to perform brain tumor diagnoses quickly. Due to the data complexity of 3D brain images, it is impractical to segment out tumor regions manually, so automatic and reliable methods can be utilized instead of manual work to achieve accurate segmentation of tumor regions. In this paper, we propose an end-to-end, more efficient brain tumor MRI segmentation model, REMU-Net, for the problems of multi-scale feature extraction and difficulty in small target feature extraction in 3D brain tumor image segmentation. Firstly, design and use the multi-channel parallel M-RepVGG module as a decoder to achieve multi-scale feature fusion. Secondly, embedding dilated convolution with different dilated rates in the DM-RepVGG module of the encoder to better extract features at different scales. Finally, introduce the expectation-maximizing attention in the network to better extract the features of the internal details of the tumor. The experimental results on the BraTS2018 validation dataset are Dice scores of 80.93%, 90.13%, and 86.15%, respectively. Experimental results on the BraTS2019 validation dataset can be achieved with Dice scores of 78.29%, 90.65%, and 82.77%, respectively. [ABSTRACT FROM AUTHOR]

The classical image segmentation algorithm based on local adaptive threshold can effectively segment images with uneven illumination, but with the increase of the image data, the real-time problem gradually emerges. In this paper, a quantum segmentation algorithm based on local adaptive threshold for NEQR image is proposed, which can use quantum mechanism to simultaneously compute local thresholds for all pixels in a gray-scale image and quickly segment the image into a binary image. In addition, several quantum circuit units, including median calculation, quantum binarization, etc. are designed in detail, and then a complete quantum circuit is designed to segment NEQR images by using fewer qubits and quantum gates. For a 2 n × 2 n image with q gray-scale levels, the complexity of our algorithm can be reduced to O (n 2 + q) , which is an exponential speedup compared to the classic counterparts. Finally, the experiment is conducted on IBM Q to show the feasibility of our algorithm in the noisy intermediate-scale quantum (NISQ) era. [ABSTRACT FROM AUTHOR]

In the past decade, it is proven that satellite image classification using an object-based technique is better than the standard pixel-based technique. With the increasing need for classifying multispectral satellite images for urban planning, the accuracy of the classification becomes a significant performance parameter. Object-based classification (OBC) is a technique in which group of pixels having similar spectral properties, called objects, are generated using image segmentation and then these objects are classified based on their attributes. In this paper, the combination of a multiclass AdaBoost algorithm with extra trees classifier (ETC) is proposed with higher prediction accuracy for the OBC of the urban fringe area. The performance of the AdaBoost algorithm is found to be better in terms of classification accuracy than benchmarked SVM and RF classifiers for OBC. These classification methods were applied to IRS-R2 LISS IV data. The AdaBoosted extra trees classifier (ABETC) has demonstrated the highest accuracy with overall accuracy (OA) of 88.47% and a kappa coefficient of 0.85. The computational time of the ABETC is found to be much smaller than the RF algorithm. In detail, the sensitivity of the classifiers was investigated using stratified random sampling with various sample sizes. [ABSTRACT FROM AUTHOR]

This paper proposes a novel algorithm of segmentation of diseased part in apple leaf images. In agriculture-based image processing, leaf diseases segmentation is the main processing task for region of interest extraction. It is also extremely important to segment the plant leaf from the background in case on live images. Automated segmentation of plant leaves from the background is a common challenge in the processing of plant images. Although numerous methods have been proposed, still it is tough to segment the diseased part of the leaf from the live leaf images accurately by one particular method. In the proposed work, leaves of apple having different background have been segmented. Firstly, the leaves have been enhanced by using Brightness-Preserving Dynamic Fuzzy Histogram Equalization technique and then the extraction of diseased apple leaf part is done using a novel extraction algorithm. Real-time plant leaf database is used to validate the proposed approach. The results of the proposed novel methodology give better results when compared to existing segmentation algorithms. From the segmented apple leaves, color and texture features are extracted which are further classified as marsonina coronaria or apple scab using different machine learning classifiers. Best accuracy of 96.4% is achieved using K nearest neighbor classifier. [ABSTRACT FROM AUTHOR]

Image segmentation is an important processing technology, which is the basis of image recognition and has been widely used in many fields. In this paper, we propose a method, termed coarse-to-fine strategy-based image segmentation (CSIS), for color image segmentation. The basic idea is to segment an image by three phases: (1) the original image is first segmented into several distinct regions by using the mean shift method; (2) the segmented regions are converted to a weighted region adjacency graph (RAG), and a new graph cut method, called multi-cut algorithm, is proposed to partition the RAG into multiple regions; (3) a one-step Chan–Vese algorithm is applied to smooth the boundaries of the segmented objectives. In each of the last two phases, a method is applied to refine the result obtained in the previous phase. By carefully balancing the efforts used in each phase, CSIS could segment color images both efficiently and effectively. These advantages are demonstrated by applying the proposed method to a variety of test instances, and the statistical results also show that it is comparable with some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

As an important identification certificate for citizens, ID card plays a significant role in daily life and its information has found its way into almost every aspect. However, traditional ways tend to adopt manual input, which is not only time-consuming and labor-intensive, but also expensive as well as inaccuracy. In this paper, we proposed a novel algorithm to locate and recognize ID card information, in which several fresh strategies are presented to rectify image, detect boundary, and locate information, respectively. To solve the problem of image rotating, the image is rectified by searching the best rotating angle that can lead to the maximum corner point projection peak. Meanwhile, the boundary of ID card is detected by finding the best lines in the predicted boundary area based on the deviation between the predicted boundary and the detected boundary, and the position of information is located by incorporating the prior information and the location relation between the key information. Experimental results show that the proposed algorithm can achieve a state-of-the-art effect for recognizing ID card's information. [ABSTRACT FROM AUTHOR]

Threshold segmentation has been widely used in recent years due to its simplicity and efficiency. The method of segmenting images by the two-dimensional maximum entropy is a species of the useful technique of threshold segmentation. However, the efficiency and stability of this technique are still not ideal and the traditional search algorithm cannot meet the needs of engineering problems. To mitigate the above problem, swarm intelligent optimization algorithms have been employed in this field for searching the optimal threshold vector. An effective technique of lightning attachment procedure optimization (LAPO) algorithm based on a two-dimensional maximum entropy criterion is offered in this paper, and besides, a chaotic strategy is embedded into LAPO to develop a new algorithm named CLAPO. In order to confirm the benefits of the method proposed in this paper, the other seven kinds of competitive algorithms, such as Ant–lion Optimizer (ALO) and Grasshopper Optimization Algorithm (GOA), are compared. Experiments are conducted on four different kinds of images and the simulation results are presented in several indexes (such as computational time, maximum fitness, average fitness, variance of fitness and other indexes) at different threshold levels for each test image. By scrutinizing the results of the experiment, the superiority of the introduced method is demonstrated, which can meet the needs of image segmentation excellently. [ABSTRACT FROM AUTHOR]

Semi-supervised learning reduces overfitting and facilitates medical image segmentation by regularizing the learning of limited well-annotated data with the knowledge provided by a large amount of unlabeled data. However, there are many misuses and underutilization of data in conventional semi-supervised methods. On the one hand, the model will deviate from the empirical distribution under the training of numerous unlabeled data. On the other hand, the model treats labeled and unlabeled data differently and does not consider inter-data information. In this paper, a semi-supervised method is proposed to exploit unlabeled data to further narrow the gap between the semi-supervised model and its fully-supervised counterpart. Specifically, the architecture of the proposed method is based on the mean-teacher framework, and the uncertainty estimation module is improved to impose constraints of consistency and guide the selection of feature representation vectors. Notably, a voxel-level supervised contrastive learning module is devised to establish a contrastive relationship between feature representation vectors, whether from labeled or unlabeled data. The supervised manner ensures that the network learns the correct knowledge, and the dense contrastive relationship further extracts information from unlabeled data. The above overcomes data misuse and underutilization in semi-supervised frameworks. Moreover, it favors the feature representation with intra-class compactness and inter-class separability and gains extra performance. Extensive experimental results on the left atrium dataset from Atrial Segmentation Challenge demonstrate that the proposed method has superior performance over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper presents a modified flower pollination-based method for performing multilevel segmentation of medical images. The flower pollination-based optimization (FPO) models the pollination process of flowers. Bees serve a major role in the pollination activity of flowers and they memorize and recognize the best flowers producing large pollens of nectar. Such memorizing ability of bees is adapted in the FPO for improving the exploration ability of the algorithm. Besides, the mechanism of avoiding predators by pollinators is also included in the modified FPO (MFPO) for getting away from sub-optimal traps. The medical image segmentation problem is transformed into an optimization problem and solved using the modified FPO (MFPO). The method explores for optimal thresholds in the problem space of the given medical image. The segmented images are presented for showing the superior performance of the proposed method. [ABSTRACT FROM AUTHOR]

Nowadays, image segmentation techniques are being used in many medical applications such as tissue culture monitoring, cell counting, automatic measurement of organs, etc., for assisting doctors. However, high-level segmentation results cannot be obtained without manual annotation or prior knowledge for high variability, noise and other imaging artifacts in medical images. Furthermore, unstable and continuously changing characteristics of all human cells, tissues and organs manipulate training-based segmentation methods. Detecting appropriate contour of a region of interest and single cells from overlapping condition are extremely challenging. In this paper, we aim for a model that can detect biological structure (e.g. cell nuclei and lung contour) with their proper morphology even in overlapping or occluded condition without manual annotation or prior knowledge. We have introduced a new optimal approach for automatic medical image region segmentation. The method first clearly focuses the boundaries of all object regions in a microscopy image. Then it detects the areas by following their contours. Our model is capable of detecting and segmenting object regions from medial image using less computation effort. Our experimental results prove that our model provides better detection on several datasets of different types of medical data and ensures more than 98% segmentation rate in the case of densely connected regions. [ABSTRACT FROM AUTHOR]

In this paper, an expanded multilayer perceptron (EMLP) neural network is proposed to automatically segment angiodysplasia regions in wireless capsule endoscopy (WCE) images The main idea is to minimize the distance between the input image and the corresponding binary ground truth, i.e., the mask image. After the training phase, when a test image is given to the network, the lesion pixels will be close to "one" and the other pixels will be close to "zero" and finally, the lesion area can be segmented using thresholding. Since angiodysplasia lesions appear in images with different spectrums of red color, the classical MLP neural network cannot be trained with a wide range of red color, hence leads to undesirable network accuracy. To solve this problem, we proposed an EMLP neural network for image segmentation. In the EMLP neural network, neurons are divided into several groups, each of which is for learning a spectrum of the lesion. The EMLP is able to learn a wider range of red colors. The proposed method is able to segment WCE images containing angiodysplasia faster than the existing methods. Our investigation shows that our method also outperforms existing methods in terms of segmentation scores. [ABSTRACT FROM AUTHOR]

In this paper, we propose a computationally efficient method for traffic sign detection. Our methodology uses deep learning networks introduced for semantic image segmentation and classification of region of interests generated by image segmentation. The region of interests are detected by segmenting the road scene image dataset and hypothesis tests are applied to accept or reject the probability of being a traffic sign in the detected region of interest. For hypothesis tests, color feature, and the location of the traffic sign with respect to the segmented road information is used. The main contribution of our method is the introduction of hypothesis tests that mutually couple two deep learning networks trained by well-known datasets publicly available for benchmarking purposes. To test and evaluate our traffic sign detection system, we use the German traffic sign detection benchmark dataset with a large set of traffic signs and during its training, The cityscapes dataset offering labeled urban scenes is also leveraged by the traffic sign detection system. Our experimental results illustrate the effectiveness performance metrics are reached at 90.81%, 94.76% and 92.74% in precision, recall and F-measure, respectively. The runtime cost is around 0.4 s for an image on an ordinary laptop computer. [ABSTRACT FROM AUTHOR]

It is well known that neurons communicate through synapses in the nervous system, and the size, morphology, and connectivity of synapses determine the functional properties of the neural network. Therefore, synapses have always been one of the key objects of neuroscience. Due to the technical advance in electron microscope (EM), the physical structure of synapses can be observed at high resolution. Nevertheless, to date, the automatic analysis of the synapse in EM images is still a challenging task. In this paper, we proposed a fractal dimension-based segmentation method for synaptic clef of mouse cortex on EM image stack. Our method does not require a lot of groundtruth to train the model, and shows better adaptive anti-noise performance. That should be ascribed to the stability of segmentation-related key parameters in the data from same tissue. In this way, we only need to give initial values, and then gradually adjust these key parameters. Experiments reveal that our method achieves the desired results, and reduces the time in artificial annotating, so that researchers can focus more on the analysis of segmentation results. [ABSTRACT FROM AUTHOR]

Multilevel thresholding is a basic method in image segmentation. The conventional image multilevel thresholding algorithms are computationally expensive when the number of decomposed segments is high. In this paper, a novel and powerful technique is suggested for Crow Search Algorithm (CSA) devoted to segmentation applications. The main contribution of our work is to adapt Darwinian evolutionary theory with heuristic CSA. First, the population is divided into specified groups and each group tries to find better location in the search space. A policy of encouragement and punishment is set on searching agents to avoid being trapped in the local optimum and premature solutions. Moreover, to increase the convergence rate of the proposed method, a gray-scale map is applied to out-boundary agents. Ten test images are selected to measure the ability of our algorithm, compared with the famous procedure, energy curve method. Two popular entropies i.e. Otsu and Kapur are employed to evaluate the capability of the introduced algorithm. Eight different search algorithms are implemented and compared to the introduced method. The obtained results show that our method, compared with the original CSA, and other heuristic search methods, can extract multi-level thresholding more efficiently. [ABSTRACT FROM AUTHOR]

Breast cancer is dangerous in women. It is generally found after the symptoms appear. Detecting the breast cancer at an early stage and understanding the treatment are the most important strategies to prevent death from cancer. Generally, for detection of breast cancer, breast Magnetic Resonance Image (MRI) takes place. It is one of the best approaches to detect tumor in women. In this research paper, a combination of selection methods for seed region growing image segmentation is suggested to detect breast tumor. The suggested method has been divided into following parts: First, the pre-processing of breast image is performed. Second, the automatic threshold for binarization process is calculated. Third, the number of seed points and its position in the breast image are determined automatically using density of pixels value. Fourth, a method for calculation of threshold value is proposed for the purpose of region creation in seed region growing. For the evaluation purpose, the proposed method was applied and tested on the RIDER MRI breast dataset from National Biomedical Imaging Archive (NBIA). After the test was performed, it was observed that proposed algorithm gives 90% accuracy, 88% True Negative Fraction, 91% True Positive Fraction, 10% Misclassification Rate, 94% Precision and 86% Relative Overlap which is better than other existing methods. It not only gives better evaluation measure but also provides segmentation method for multiple tumor detection. [ABSTRACT FROM AUTHOR]

Remote sensing techniques have been developed over the past decades to acquire data without being in contact of the target object or data source. Their application on land-cover image segmentation has attracted significant attention during recent years. With the help of satellites, scientists and researchers can collect and store high-resolution image data that can be further be processed, segmented, and classified. However, these research results have not yet been synthesized to provide coherent guidance on the effect of variant land-cover segmentation processes. In this paper, we present a novel model that augments segmentation using smaller networks to segment individual classes. The combined network is trained on the same data but with the masks, combined and trained using categorical cross entropy. Experimental results show that the proposed method produces the highest mean IoU (Intersection of Union) as compared against several existing state-of-the-art models on the DeepGlobe dataset. [ABSTRACT FROM AUTHOR]

Image scene analysis is to analyze image scene content through image semantic segmentation, which can identify the categories and positions of different objects in an image. However, due to the loss of spatial detail information, the accuracy of image scene analysis is often affected, resulting in rough edges of FCN, inconsistent class labels of target regions and missing small targets. To address these problems, this paper increases the receptive field, conducts multi-scale fusion and changes the weight of different sensitive channels, so as to improve the feature discrimination and maintain or restore spatial detail information. Furthermore, the deep neural network FCN is used to build the base model of semantic segmentation. The ASPP, data augmentation, SENet, decoder and global pooling are added to the baseline to optimize the model structure and improve the effect of semantic segmentation. Finally, the more accurate results of scene analysis are obtained. [ABSTRACT FROM AUTHOR]

The implication of firefly and fuzzy firefly optimization algorithms has been greatly witnessed in clustering techniques and extensively used in applications such as Image segmentation. Parameters such as step factor and attractiveness have been kept constant in these algorithms, which affect the convergence rate and accuracy of the clustering process. Though fuzzy adaptive firefly algorithm tackled this problem by making those parameters an adaptive one, issues such as low convergence rate, and provision of non-optimal solutions are still there. To tackle these issues, this paper proposed a novel fuzzy adaptive fuzzy firefly algorithm that significantly improves the accuracy and convergence rate while comparing with the existing optimization algorithms. Further, the proposed algorithm fused with existing hybrid clustering algorithms involving fuzzy set, intuitionistic fuzzy set, and rough set resulted in eight novel hybrid clustering algorithms which lead to better performance in optimizing the selection of initial centroids. To validate the proposal, experimental studies have been conducted on datasets found in bench-marking data repositories such as UCI, and Kaggle. The performance and accuracy evaluation of proposed algorithms have been carried out with the aid of seven accuracy measures. Results clearly indicate the improved accuracy and convergence rate of the proposed algorithms. [ABSTRACT FROM AUTHOR]

This paper discusses how to efficiently recognize flowers based on a convolutional neural network (CNN) using multiple features. Our proposed work consists of three phases including segmentation by Otsu thresholding with particle swarm optimization algorithms, feature extraction of color, shape, texture and recognition with the LeNet-5 neural network. In the feature extraction, an improved H component with the definition of WGB value is applied to extract the color feature, and a new algorithm based on local binary pattern (LBP) is proposed to enhance the accuracy of texture extraction. Besides this, we replace ReLU with Mish as activation function in the network design, and therefore increase the accuracy by 8% accuracy according to our comparison. The Oxford-102 and Oxford-17 datasets are adopted for benchmarking. The experimental results show that the combination of color features and texture features generates the highest recognition accuracy as 92.56% on Oxford-102 and 93% on Oxford-17. [ABSTRACT FROM AUTHOR]

In this paper, we give a systematic review of the theory of Gibbs measures of Potts model on Cayley trees (developed since 2013) and discuss many applications of the Potts model to real world situations: mainly biology, physics, and some examples of alloy behavior, cell sorting, financial engineering, flocking birds, flowing foams, image segmentation, medicine, sociology, etc. [ABSTRACT FROM AUTHOR]

Image segmentation is a prime operation to understand the content of images. Multilevel thresholding is applied in image segmentation because of its speed and accuracy. In this paper, a novel multilevel thresholding algorithm based on Cuckoo search (CS) is introduced. One of the major drawbacks of metaheuristic algorithms is the stagnation phenomenon which leads to a fall into local optimums and premature convergence. To overcome this shortcoming, the idea of Darwinian theory is incorporated with CS algorithm to increase the diversity and quality of the individuals without decreasing the convergence speed of CS algorithm. A policy of encouragement and punishment is considered to lead searching agents in the search space and reduce the computational time. The algorithm is implemented based on dividing the population into specified groups and each group tries to find a better location. Ten test images are selected to verify the ability of our algorithm using the famous energy curve method. Two popular entropies criteria, Otsu and Kapur, are employed to evaluate the capability of the introduced algorithm. Eight different search algorithms are also implemented and compared with our method. Experimental results manifest that DCS is a powerful tool for multilevel thresholding and the obtained results outperform the CS algorithm and other heuristic search methods. [ABSTRACT FROM AUTHOR]

In recent times, there has been a tremendous progress in image dehazing for computer vision applications, while the sky region processed by these algorithms tends to degrade by noise and color distortion. In this paper, an improved dark channel prior algorithm is proposed which detects the sky region first and divides the image into sky region and non-sky region and then estimates the transmission of two parts separately, followed by combining with refining step. The proposed algorithm also accurately corrects the transmission of the sky region to avoid noise and color distortion. Experimental results show a greater quality improvement in the output images than the existing strategies. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNNs) trained on the pixel-level annotated images have achieved improvements in semantic segmentation. Due to the high cost of labeling training data, their applications may have great limitation. However, weakly supervised segmentation approaches can significantly reduce human labeling efforts. In this paper, we introduce a new framework to generate high-quality initial pixel-level annotations. By using a hierarchical image segmentation algorithm to predict the boundary map, we select the optimal scale of high-quality hierarchies. In the initialization step, scribble annotations and the saliency map are combined to construct a graphic model over the optimal scale segmentation. By solving the minimal cut problem, it can spread information from scribbles to unmarked regions. In the training process, the segmentation network is trained by using the initial pixel-level annotations. To iteratively optimize the segmentation, we use a graphical model to refine segmentation masks and retrain the segmentation network to get more precise pixel-level annotations. The experimental results on Pascal VOC 2012 dataset demonstrate that the proposed framework outperforms most of weakly supervised semantic segmentation methods and achieves the state-of-the-art performance, which is 6 9. 3 % mIoU. [ABSTRACT FROM AUTHOR]

This paper proposes an advanced and precise technique for the segmentation of Magnetic Resonance Image (MRI) of the brain. Brain MRI segmentation is to be familiar with the anatomical structure, to recognize the deformities, and to distinguish different tissues which help in treatment planning and diagnosis. Nature's inspired population-based evolutionary algorithms are extremely popular for a wide range of applications due to their best solutions. Teaching Learning Based Optimization (TLBO) is an advanced population-based evolutionary algorithm designed based on Teaching and Learning process of a classroom. TLBO uses common controlling parameters and it won't require algorithm-specific parameters. TLBO is more appropriate to optimize the real variables which are fuzzy valued, computationally efficient, and does not require parameter tuning. In this work, the pixels of the brain image are automatically grouped into three distinct homogeneous tissues such as White Matter (WM), Gray Matter (GM), and Cerebro Spinal Fluid (CSF) using the TLBO algorithm. The methodology includes skull stripping and filtering in the pre-processing stage. The outcomes for 10 MR brain images acquired by utilizing the proposed strategy proved that the three brain tissues are segmented accurately. The segmentation outputs are compared with the ground truth images and high values are obtained for the measure's sensitivity, specificity, and segmentation accuracy. Four different approaches, namely Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Bacterial Foraging Algorithm (BFA), and Electromagnetic Optimization (EMO) are likewise implemented to compare with the results of the proposed methodology. From the results, it can be proved that the proposed method performed effectively than the other. [ABSTRACT FROM AUTHOR]

Numerous evolutionary algorithms have been proposed which are inspired by the amazing lives of creatures, such as animals, insects, and birds. Each inspired algorithm has its own advantages and disadvantages, and has its own way to accomplish exploration and exploitation. In this paper, a new evolutionary algorithm with novel concepts, called Wildebeests Herd Optimization (WHO), is proposed. This algorithm is inspired by the splendid life of wildebeests in Africa. Moving and migration are inseparable from wildebeests' lives. When a wildebeest wants to choose its path during migration, it considers the best path known to itself, the location of the more mature wildebeests in the crowd, and the direction of wildebeests with high mobility. The WHO algorithm imitates these traits, and can concurrently explore and exploit the search space. For validating WHO, it is applied to optimization problems and data mining tasks. It is demonstrated that WHO outperforms other evolutionary algorithms, such as genetic algorithm (GA) and particle swarm optimization, in the assessed problems. Then, WHO is applied to the customer segmentation problem. Customer segmentation is one of the most important tasks of data mining, especially in the banking sector. In this paper, the customers of a bank with current accounts are segmented using WHO based on four aspects: profitability, cost, loyalty and credit; some of these aspects are calculated in a novel way. The results were welcome by the bank authorities. [ABSTRACT FROM AUTHOR]

Solar image consists of obvious regions of solar activities and peaceful regions of no activity. Identifying effective solar active areas from solar image is a typical application of image-processing technology in astronomical research. Benefiting from real-time solar observation data provided by Heliophysics Event Knowledgebase (HEK) of Solar Dynamics Observatory (SDO), this paper presents a method of solar activity identification based on HEK. In this method, we gather data of six kinds of solar activities (time, location, and area) and establish a multiscale transformation model for the full-disk solar image of the corresponding time. Combining both location data and area data, we design different gradient thresholds to segment different solar activities’ regions. Two kinds of boundary-identification methods are used to locate and recognize solar activities’ regions, respectively. Furthermore, we study the correlation of the characteristic parameters (six kinds of solar activities’ data) of solar image and get the best combination of the characteristic parameters of each solar activity. The method in the paper provides precise positioning and efficient identification of solar activities, which lays the foundation for further work. In addition to that, extracting specific combination of features from different solar activities’ regions can provide a feasible way to build a streamlined image feature set for content-based image retrieval (CBIR) systems. [ABSTRACT FROM AUTHOR]

Subspace clustering analysis algorithms are often employed when dealing with high-dimensional data. As a representative approach, Low-Rank Representation (LRR) of data has achieved great success for subspace segmentation tasks in applications such as image processing. The traditional LRR-related methods consist of two separate tasks: first, the affinity graph construction by using lowrank minimization techniques, and then the spectral clustering, which is done on the affinity graph to get the final segmentation. Since these two steps are independent of each other, this method does not guarantee that the results obtained by the algorithm are globally optimal. In this paper, a method called Robust Structured Low-Rank Representation (RSLRR) is proposed, by integrating the two above mentioned tasks and solve a joint optimization problem. This paper also puts forward a method to solve the joint optimization problem, which can efficiently get both the segmentation and the structured low-rank representation. Experiments on several standard datasets show that, compared with other algorithms, the algorithm proposed in this paper can achieve better clustering results. [ABSTRACT FROM AUTHOR]

Deep learning artificial intelligence (AI) is a booming area in the research field. It allows the development of end-to-end models to predict outcomes based on input data without the need for manual extraction of features. This paper aims for evaluating the automatic crack detection process that is used in identifying the cracks in building structures such as bridges, foundations or other large structures using images. A hybrid approach involving image processing and deep learning algorithms is proposed to detect automatic cracks in structures. As cracks are detected in the images they are segmented using a segmentation process. The proposed deep learning models include a hybrid architecture combining Mask R-CNN with single layer CNN, 3-layer CNN, and8-layer CNN. These models utilizes depth wise convolution with varying dilation rates for efficiently extracting diversified features from the crack images. Further, performance evaluation shows that Mask R-CNN with a single layer CNN achieves an accuracy of 97.5% on a normal dataset and 97.8% on a segmented dataset. The Mask R-CNN with 2-layer convolution resulted in an accuracy of 98.32% on a normal dataset and 98.39% on a segmented dataset. The Mask R-CNN with 8-layers convolution achieves an accuracy of 98.4% on a normal dataset and 98.75% on a segmented dataset. The proposed Mask R-CNN have proved its feasibility in detecting cracks in huge building and structures. [ABSTRACT FROM AUTHOR]

Chest X-ray images are notoriously difficult to analyze due to the noisy nature. Automatic identification of pneumonia on medical images has attracted intensive study recently. In this paper, a novel joint-task architecture that can learn pneumonia classification and segmentation simultaneously is presented. Two modules, including an image preprocessing module and an attention module, are developed to improve both the classification and segmentation accuracies. Results from the experiments performed on the massive dataset of the Radiology Society of North America have confirmed its superiority over the other existing methods. The classification test accuracy is improved from 0.89 to 0.95, and the segmentation model achieves an improved mean precision result of 0.58–0.78. Finally, two weakly supervised learning methods, class-saliency map and Grad-CAM, are used to highlight the corresponding pixels or areas which have significant influence on the classification model, such that the refined segmentation can focus on the correct areas with high confidence. [ABSTRACT FROM AUTHOR]

Segmentation of the left ventricle in ultrasound images for viewing through different axes is a critical aspect. This paper proposes the development of novel active contour models with shape constraint to segment the left ventricle in three different axis views of the ultrasound images. The shapes observed in all the axis views of the left ventricle were not similar. According to the cardiac cycle, the valve opening in the end-diastolic phase influenced the left ventricle segmentation; hence, a shape constraint was embedded in the active contour model to keep ventricle's shape, especially in the Apical long-axis view and Apical four-chamber view. Furthermore, for different axes views, diverse active contour models were proposed to fit each situation. The shape constraint in each function for different views exhibited a specific shape during the function iteration. In order to speed up the algorithm evolution, previous results were used for the initialization of the present active contour. We evaluated the proposed method on 57 patients with three different views: Apical long-axis view, Apical four-chamber view and Short-axis view at the papillary muscle level and obtained the Dice similarity coefficients of 0. 8 6 ± 0. 0 5 , 0. 9 0 ± 0. 0 6 and 0. 9 0 ± 0. 0 6 and the Hausdorff distance metrics of 1 0. 1 1 ± 4. 6 6 , 7. 4 1 ± 4. 4 6 and 9. 9 8 ± 6. 5 8 , respectively. The qualitative and quantitative evaluations showed an advantage of our method in terms of segmentation accuracy. [ABSTRACT FROM AUTHOR]

The annotation-free word spotting method that is proposed in this paper makes document images searchable without requiring any labeled training data. Thus, our method supports the exploration of a document collection directly without demanding any manual efforts from the users for the preparation of a training dataset. Our method works in the query-by-example scenario where the user selects an exemplary occurrence of the query word. Afterwards, the entire collection of document images is searched according to visual similarity to the query. The proposed method requires only minimal assumptions about the visual appearance of text. This is achieved by processing document images as a whole without requiring a given segmentation of the images on word level or on line level. Therefore, the method is also segmentation-free. Word size variabilities can be handled by representing the sequential structure of text with a statistical sequence model. In order to make the computationally costly application of the sequence model feasible in practice, regions are retrieved according to approximate similarity with an efficient model decoding algorithm. Re-ranking these regions according to the visual similarity obtained with the sequence model leads to highly accurate word spotting results. The method is evaluated on five benchmark datasets. In the segmentation-free query-by-example scenario where no annotated training data is available, the method outperforms all other methods that have been evaluated on any of these five benchmarks. [ABSTRACT FROM AUTHOR]

In this paper, we propose an automatic binary data classification method using a modified Allen–Cahn (AC) equation. The modified AC equation was originally developed for image segmentation. The equation consists of the AC equation with a fidelity term which enforces the solution to be the given data. In the proposed method, we start from a coarse grid and refine the grid until the accuracy of the data classification reaches a given tolerance. Therefore, we can avoid a laborious trial and error procedure. For a numerical method for the modified AC equation, we use a recently developed explicit hybrid scheme. We perform several 2D and 3D computational tests to demonstrate the performance of the proposed method. The computational results confirm that the proposed algorithm is automatic. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a new phase field approximation of the Mumford–Shah functional similar to the well-known one from Ambrosio and Tortorelli. However, in our setting the phase field is allowed to be a function of bounded variation, instead of an H 1 -function. In the context of image segmentation, we also show how this new approximation can be used for numerical computations, which contains a total variation minimization of the phase field variable, as it appears in many problems of image processing. A comparison to the classical Ambrosio–Tortorelli approximation, where the phase field is an H 1 -function, shows that the new model leads to sharper phase fields. [ABSTRACT FROM AUTHOR]

Nowadays, lung disease is a major global problem in the world. Many of the lung diseases are untreatable and reduce the life span of the individual. Initial diagnosis of these diseases can help to completely cure the illness and reduce disease progression. Diagnosis of lung disease is often made based on CT scan images of the lungs. But the diagnosis of lung disease in CT images is a complicated and challenging task. Such a challenge is due to the noise of imaging, the lack of transparency of the image, the intensity of the lighting of some components, and so on. Eliminating these issues makes it easy to diagnose the disease for specialized physicians as well as existing automated diagnostic systems. In this paper, we propose a novel approach for lung CT image segmentation that solves some of these challenges. Also, correct accurate segmentation of these images can help to automatically detect lung diseases. The correct segmentation means a precise determination of the intensity of each area's brightness, the exact location of the pixels in each area and the preservation of the original image. We employed a reinforcement-based approach for our image segmentation. The proposed method produces the image without noise, and the image components are split with the best accuracy. To evaluate our approach, we manually generated 200 labelled lung CT images. After that, the proposed method, along with two recently published approaches is evaluated against our generated dataset. This comparative evaluation is conducted in two qualitative and quantitative ways. For the qualitative comparison, we employed the consultation of two ultrasound radiologists for evaluating the results of our approach. We also used a similarity measurement to quantitatively evaluate the performance of our proposed segmentation method. In both evaluation approaches, the proposed algorithm provides better performance compared to the other methods. The proposed method provides an accuracy of more than 90% for lung image segmentation, which shows around 5% increase in the accuracy comparing to the state of the art. The high accuracy of this method is due to its fitness to the application. [ABSTRACT FROM AUTHOR]

Image pixel clustering or segmentation intends to identify pixel groups on an image without any preliminary labels. It remains a challenging task in computer vision since the size and shape of object segments are varied. Moreover, determining the segment number in an image without prior knowledge of the image content is an NP-hard problem. In this paper, we present an automatic image pixel clustering scheme based on mussels wandering optimization. An activation variable is applied to determine the number of clusters automatically with the cluster centers optimization. We revise the within- and between-class sum of squares ratio for random natural image content and develop a novel fitness function for the image pixel clustering task. Our proposed scheme is compared against existing state-of-the-art techniques using both synthetic data and real ASD dataset. Experimental results show the superiority performance of the proposed scheme. [ABSTRACT FROM AUTHOR]

This paper proposes an incoming Deep Convolutional Neural Network (CNN) architecture for segmenting retinal blood vessels automatically from fundus images. Automatic segmentation performs a substantial role in computer-aided diagnosis of retinal diseases; it is of considerable significance as eye diseases as well as some other systemic diseases give rise to perceivable pathologic changes. Retinal blood vessel segmentation is challenging because of the excessive changes in the morphology of the vessels on a noisy background. Previous deep learning-based supervised methods suffer from the insufficient use of low-level features which is advantageous in semantic segmentation tasks. The proposed architecture makes use of both high-level features and low-level features to segment retinal blood vessels. The major contribution of the proposed architecture concentrates on two important factors; the first in its supplying of extremely modularized network architecture of aggregated residual connections which enable us to copy the learned layers from the shallower model and developing additional layers to identity mapping. The second is to improve the utilization of computing resources within the network. This is achieved through a skillfully crafted design that allows for increased depth and width of the network while maintaining the stability of its computational budget. Experimental results show the effectiveness of using aggregated residual connections in segmenting retinal vessels more accurately and clearly. Compared to the best existing methods, the proposed method outperformed other existing methods in different measures, comprised less false positives at fine vessels, and caressed more clear lines with sufficient details like the human annotator. [ABSTRACT FROM AUTHOR]

The normalized intensity factor based on statistical first-order moment of gray-scale image is defined in this paper. The intensity factor can be used to distinguish the brightness level of a gray-scale image and to determine a threshold value for image segmentation. According to the intensity factor and the characteristic of human body in the gray-scale infrared image, a new algorithm of calculating the intensity-level threshold is designed which can be used for segmenting human body area in an infrared image. In the algorithm, based on the concept of intensity factor, a histogram of low brightness gray-scale image (LGIRI) is divided into three parts: a low-intensity region (0.25 L), a medium-intensity region (0.25–0.75 L), and a high-intensity region (0.75–1 L), and then the intensity i which satisfies the L a M (i) = 0. 5 k L L a is selected as an intensity-level value k h , and the intensity i which satisfies L M (i) = 0. 5 k L L is selected as an intensity-level value t h , at last 0. 5 (t h + k h) is the pixel classification threshold (the intensity-level threshold). It is noted that there is no preprocessing for image noise filtering and/or processing, and all images come from OTCBVS. Compared with the method of selecting trough points of the histogram as the intensity-level threshold, this algorithm avoids the problem of nonexistence of evident trough point at the high-intensity level of a histogram. Also, the experimental results show that the segmenting results of LGIRI processed by the algorithm are better than those of Otsu method. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have achieved prominent performance in a series of image processing problems. CNNs become the first choice for dense classification problems such as semantic segmentation. However, CNNs predict the class of each pixel independently in semantic segmentation tasks, spatial regularity of the segmented objects is still a problem for these methods. Especially when given few training data, CNN could not perform well in the details, isolated and scattered small regions often appear in all kinds of CNN segmentation results. In this paper, we propose a method to add spatial regularization to the segmented objects. In our method, the spatial regularization such as total variation (TV) can be easily integrated into CNN network and it produces smooth edges and eliminate isolated points. We apply our proposed method to Unet and Segnet, which are well-established CNNs for image segmentation, and test them on WBC and CamVid datasets, respectively. The results show that the details of predictions are well improved by regularized networks. [ABSTRACT FROM AUTHOR]

In this paper, an automatic RGBD object segmentation method is described. The method integrates depth feature with the cues from RGB images and then uses maximal similarity based region merging (MSRM) method to obtain the segmentation results. Firstly, the depth information is fused to the simple linear iterative clustering (SLIC) method so as to produce superpixels whose boundaries are well adhered to the edges of the natural image. Meanwhile, the depth prior is also incorporated into the saliency estimation, which helps a more accurate localization of representative object and background seeds. By introducing the depth cue into the region merging rule, the maximal geometry weighted similarity (MGWS) is considered, and the resulting segmentation framework has the ability to handle the complex image with similar colour appearance between object and background. Extensive experiments on public RGBD image datasets show that our proposed approach can reliably and automatically provide very promising segmentation results. [ABSTRACT FROM AUTHOR]

The one-dimensional Otsu method is an adaptive threshold method. It obtains the optimal threshold for image segmentation by the maximum between-class variance, without considering the minimum within-class variance. As the background of water surface image is mostly uniform, using this feature, the threshold selection tactics adopt the combination of the one-dimensional Otsu method and the uniformity measurement, proposes the threshold segmentation method based on uniformity measurement, and adopts the performance evaluation method based on GT image to compare the segmentation result. Experimental results demonstrate that effectiveness of the improved Otsu method is generally better than the traditional Otsu method, and the other four commonly used threshold segmentation methods for the water surface image, which improves the segmentation accuracy of such images and reduces the segmentation error rate. At the same time, as the water surface image is usually affected by light intensity, water ripple and other factors, this paper also adopts the relevant correction algorithm to further improve the segmentation accuracy. [ABSTRACT FROM AUTHOR]

To design an efficient fusion scheme for the generation of a highly informative fused image by combining multiple images is still a challenging task in computer vision. A fast and effective image fusion scheme based on multi-resolution singular value decomposition (MR-SVD) with guided filter (GF) has been introduced in this paper. The proposed scheme decomposes an image of two-scale by MR-SVD into a lower approximate layer and a detailed layer containing the lower and higher variations of pixel intensity. It generates lower and details of left focused (LF) and right focused (RF) layers by applying the MR-SVD on each series of multi-focus images. GF is utilized to create a refined and smooth-textured weight fusion map by the weighted average approach on spatial features of the lower and detail layers of each image. A fused image of LF and RF has been achieved by the inverse MR-SVD. Finally, a deep convolutional autoencoder (CAE) has been applied to segment the fused results by generating the trained-patches mechanism. Comparing the results by state-of-the-art fusion and segmentation methods, we have illustrated that the proposed schemes provide superior fused and its segment results in terms of both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

In the actual cotton planting environment, rapid change of light within a day, reflection from different backgrounds and different weather conditions can affect the imaging of cotton. Therefore, the crop object segmentation is difficult. Images which were captured in 12 natural scenes during cotton planting, including three weather conditions, such as sunny, cloudy and rainy and four soil cover conditions, such as white mulch film, black mulch film, straw and bare soil were regarded as the research objects. This paper presents the cotton leaf segmentation method based on Immune algorithm and pulse coupled neural networks (PCNN). First, 17 color components of white mulch film, black mulch film, straw, bare soil and cotton under the conditions of sunny, cloudy and rainy days were analyzed by using statistical method. Three high feasible and anti-light color components were selected by histogram statistical with mean gray value. Second, the optimal parameters of PCNN model and the optimal number of iterations were determined by using immune algorithm optimization theory, and the method in this paper was tested by using 1200 cotton images which were captured under 12 natural scenes. Finally, the test results showed that this method can distinguish cotton target region from soil and other background regions. Meanwhile, for reflection of mulch film, crop shadow, dark light, complex background, noise, etc. which are often appeared in natural scene, four image segmentation methods of Otsu algorithm, -Means algorithm, FCM algorithm and PCNN were compared with the proposed method in this paper. The segmentation result showed that the proposed method has good resistance to change of light and complex background. The average of the proposed method is 6.5%, significantly lower than that of other four methods and the performance is better than other four methods. This method can segment cotton images in different weather conditions and different backgrounds accurately under complex natural conditions. It will contribute to the subsequent growth status determination and pest diagnosis of cotton. [ABSTRACT FROM AUTHOR]

LSS-Target (the Low altitude, Slow speed and Small Target) is likely to be a threat to the observation platform, thus infrared LSS-Target detection is an urgent task. LSS-Target is a challenging issue due to the low Signal-to-Noise Ratio (SNR) and sophisticated background. Motivated by the analysis of infrared imaging characteristics, this paper proposes a novel fusion method for IR LSS-Target detection with complex urban background, which is suitable for precise guidance and self defense. First, an adaptive threshold segmentation based on accumulative histogram and maximum likelihood estimation are utilized to eliminate the clutter and improve SNR of the initial image. Second, a template is set up to identify the seed points in the image. Third, a constrained four criteria region growth algorithm is performed to separate the entire regions. Finally, the confidence measure is constructed, which can eliminate false targets and the background edges. Experimental results show that the method in this paper can screen out the real LSS-Target in real time with high accuracy under sophisticated background. [ABSTRACT FROM AUTHOR]

Virtual simulation and 3D interaction have shown great potentials in a variety of domains for our future life. For a virtual fish swarm simulation system, the simulation of cohesion behaviors of fish swarm and the interaction between human and fish swarm are two key components to create immersive interactive experiences. However, it is a huge challenge to create a realistic fish swarm simulation system while providing a natural and comfortable interaction. In this paper, we propose a method for immersive virtual fish swarm simulation based on infrared sensors. Based on dynamic weight constraints, we propose a particle swarm optimization method for fish swarm cohesion simulation, which separates a particle swarm by the state of each particle and dynamically controls the particle swarm, making the movement behavior of virtual fish more realistic. In addition, an interactive fast skinning method is proposed for cartoon fishes, which leverages image segmentation, Optical Character Recognition (OCR) and bone skinning are used to generate cartoon fishes based on user-created colors. With infrared sensors, we propose a method for virtual fish swarm interaction, where the positions of human skeleton are processed by an action analyzer, achieving real-time user interactions with fish swarms. With all the proposed techniques integrated in a system, the experimental results show that our method is feasible and effective. [ABSTRACT FROM AUTHOR]

In this paper, we propose a robust variational segmentation model capable of overcoming the problem of the negative effects of outliers. The proposed method is based on the combination of the characteristics of the generalized mean with the concept of the active contours. The optimization problem raising in this combination employs a power method technique. We demonstrate the performance of the proposed model on a series of sample images from diverse modalities and show an outperforming proposed model in comparison with the state-of-the-art methods. The proposed method shows better or equivalent performance in terms of accuracy and robustness than the conventional state-of-the-art models. The validation of the efficiency of the proposed two-phase algorithm is further extended to vector-valued images and multi-phase formulation. [ABSTRACT FROM AUTHOR]

Kernel methods are a class of algorithms for pattern analysis to robust them to noise, overlaps, outliers and also unequal sized clusters. In this paper, kernel-based fuzzy c-means (KFCM) method is extended to apply KFCM on any crisp and non-crisp input numbers only in a single structure. The proposed vectorized KFCM (VKFM) algorithm maps the input (crisp or non-crisp) features to crisp ones and applies the KFCM (with prototypes in feature space) on them. Finally the resulted crisp prototypes in the mapped space are influenced by an inverse mapping to obtain the prototypes' (centers') parameters in the input features space. The performance of the proposed method has been compared with the conventional FCM and KFCM and other new methods, to show its effectiveness in clustering of gene expression data and segmentation of land-cover using satellite images. Simulation results show good accuracy of proposed method in compare to other methods. [ABSTRACT FROM AUTHOR]

Brain tumor segmentation from magnetic resonance (MR) image is vital for both the diagnosis and treatment of brain cancers. To alleviate noise sensitivity and improve stability of segmentation, an effective hybrid clustering algorithm combined with fast guided filter is proposed for brain tumor segmentation in this paper. Preprocessing is performed using adaptive Wiener filtering combined with a fast guided filter. Then simple linear iterative clustering (SLIC) is utilized for pre-segmentation to effectively remove scatter. During the clustering, K-means + + and Gaussian kernel-based fuzzy C-means (K + + GKFCM) clustering algorithm are combined to segment, and the fast-guided filter is introduced into the clustering. The proposed algorithm not only improves the robustness of the algorithm to noise, but also improves the stability of the segmentation. In addition, the proposed algorithm is compared with other current segmentation algorithms. The results show that the proposed algorithm performs better in terms of accuracy, sensitivity, specificity and recall. [ABSTRACT FROM AUTHOR]

With the development of the world economy and the accelerating process of urbanization, cars have brought great convenience to people's lives and activities, and have become an indispensable means of transportation. Intelligent vehicles have the important significance of reducing traffic accidents, improving transportation capacity and broad market prospects, and can lead the future development of the automotive industry, so they have received extensive attention. In the existing intelligent vehicle system, the laser radar is a well-deserved protagonist because of its excellent speed and precision. It is an indispensable part of achieving high-precision positioning, but to some extent, the price hindering its marketization is a major factor. Compared with lidar sensors, vision sensors have the advantages of fast sampling rate, light weight, low energy consumption and low price. Therefore, many domestic and foreign research institutions have listed them as the focus of research. However, the current vision-based intelligent vehicle environment sensing technology is also susceptible to factors such as illumination, climate and road type, resulting in insufficient accuracy and real-time performance of the algorithm. This paper takes the environment perception of intelligent vehicles as the research object, and conducts in-depth research on the existing problems in road recognition and obstacle detection algorithms, including road image vanishing point detection, road image segmentation problem, road scene based on binocular vision. Three-dimensional reconstruction and obstacle detection technology. [ABSTRACT FROM AUTHOR]

In the domain of computer technology, image processing strategies have become a part of various applications. A few broadly used image segmentation methods have been characterized as seeded region growing (SRG), edge-based image segmentation, fuzzy k -means image segmentation, etc. SRG is a quick, strongly formed and impressive image segmentation algorithm. In this paper, we delve into different applications of SRG and their analysis. SRG delivers better results in analysis of magnetic resonance images, brain image, breast images, etc. On the other hand, it has some limitations as well. For example, the seed points have to be selected manually and this manual selection of seed points at the time of segmentation brings about wrong selection of regions. So, a review of some automatic seed selection methods with their advantages, disadvantages and applications in different fields has been presented. [ABSTRACT FROM AUTHOR]

Image segmentation is one of the fundamental problems in the image processing, which identifies the objects and other structures in the image. One of the widely used methods for image segmentation is image thresholding that can separate pixels based on the specified thresholds. Otsu method calculates the thresholds to divide two or multiple classes based on between-class variance maximization and within-class variance minimization. However, increasing the number of thresholds, surging the computational time of the segmentation. To combat this drawback, the combination of Otsu and the evolutionary algorithm is usually beneficial. Crow Search Algorithm (CSA) is a novel, and efficient swarm-based metaheuristic algorithm that inspired from the way crows storing and retrieving food. In this paper, we proposed a hybrid method based on employing CSA and Otsu for multilevel thresholding. The obtained results compared with the combination of the Otsu method with three other evolutionary algorithms consisting of improved Particle Swarm Optimization (PSO), Firefly Algorithm (FA), and also the fuzzy version of FA. Our evaluation on the five benchmark images shows competitive/improved results both in time and uniformity. [ABSTRACT FROM AUTHOR]