Search

Foundation models (FMs) have rapidly evolved and have achieved significant accomplishments in computer vision tasks. Specifically, the prompt mechanism conveniently allows users to integrate image prior information into the model, making it possible to apply models without any training. Therefore, we proposed a workflow based on foundation models and zero training to solve the tasks of photoacoustic (PA) image processing. We employed the Segment Anything Model (SAM) by setting simple prompts and integrating the model’s outputs with prior knowledge of the imaged objects to accomplish various tasks, including: (1) removing the skin signal in three-dimensional PA image rendering; (2) dual speed-of-sound reconstruction, and (3) segmentation of finger blood vessels. Through these demonstrations, we have concluded that FMs can be directly applied in PA imaging without the requirement for network design and training. This potentially allows for a hands-on, convenient approach to achieving efficient and accurate segmentation of PA images. This paper serves as a comprehensive tutorial, facilitating the mastery of the technique through the provision of code and sample datasets. [ABSTRACT FROM AUTHOR]

Edge detection is an essential image processing act that is crucial for many computer vision applications such as object detection, image segmentation, face recognition, text recognition, medical imaging, and autonomous vehicles. Deep learning is the most advanced and widely used tool of them all. In this paper, we present a novel deep learning model and use image datasets to test it. Our model uses a fractional calculus tool, which could enhance gradient approaches' performances. Specifically, we approximate the fractional-order derivative-order neural network (GLFNet) using a Grünwald–Letnikov fractional definition. First, the original dataset is subjected to a Grünwald–Letnikov fractional order. After that, the CNN model is updated with the new dataset, concluding the standard CNN procedure. The training rate, the improvement in the F-measure for identifying the effective edge while maintaining the CNN model's memory consumption, and the values of the loss errors between the prediction and training processes were all tested using the MNIST dataset. Our experiments show that GLFNet considerably enhances edge detection. GLFNet outperformed CNN with an average loss error ratio of 15.40, suggesting fewer loss mistakes. The F1-measure ratio of 0.81 indicates that GLFNet can compete with CNN in terms of precision and recall. The training time for GLFNet was lowered by an average ratio of 1.14 when compared to CNN, while inference time was faster with a ratio of 1.14, indicating increased efficiency. These findings demonstrate the efficacy of introducing Grünwald–Letnikov fractional convolution into deep learning models, resulting in more precise and reliable edge detection while preserving comparable memory utilization. [ABSTRACT FROM AUTHOR]

Abstract In order to balance accuracy and real‐time performance in semantic segmentation, this paper proposes a real‐time semantic segmentation algorithm model based on attention mechanism and multi‐branch feature fusion using Fast convolutional neural network model (Fast‐SCNN). In this method, the spatial detail feature enhancement branch is introduced to enhance spatial detail features firstly. Then, through rational design of fusion module, the feature information of each branch is optimized to achieve better fusion of deep and shallow features. At the end of the feature fusion module, an adaptive feature enhancement focus module is introduced to capture the interdependence between remote pixels. The experimental results show that the proposed algorithm achieves 71.55% segmentation accuracy on Cityscapes dataset, the reasoning speed FPS is 97.6 frames/s, and the number of parameters is 1.39 M, which verifies the effectiveness of the network model constructed by the algorithm. Code is available at https://github.com/ccchhheeennn/model.

The characterization of beached and marine microplastic debris is critical to understanding how plastic litter accumulates across the world's oceans and identifying hotspots that should be targeted for early cleanup efforts. Currently, the most common monitoring method to quantify microplastics at sea requires physical sampling using surface trawling and sifting for beached microplastics, which are then followed by manual counting and laboratory analysis. The need for manual counting is time-consuming, operatordependent, and incurs high costs, thereby preventing scalable deployment of consistent marine plastic monitoring worldwide. Here, we describe a workflow combining a simple experimental setup with advanced image processing techniques to conduct both quantitative and qualitative assessments of microplastic (0.05 cm < particle size <0.5 cm). The image processing relies on deep learning models designed for image segmentation and classification. The results demonstrated comparable or superior performance in comparison to manual identification for microplastic particles with a 96% accuracy. Thus, the use of the model offers an efficient, more robust, standardized, highly replicable, and less labor-intensive alternative to particle counting. In addition to the relative simplicity of the network architecture used that made it easy to train, the model presents promising prospects for better-standardized reporting of plastic particles surveyed in the environment. We also made the models and datasets open-source and created a user-friendly web interface for directly annotating new images. [ABSTRACT FROM AUTHOR]

The article presents research on the application of image processing techniques and convolutional neural networks (CNN) for the detection and measurement of seed sizes, specifically focusing on coffee and white bean seeds. The primary objective of the study is to evaluate the potential of using CNNs to develop tools that automate seed recognition and measurement in images. A database was created, containing photographs of coffee and white bean seeds with precise annotations of their location and type. Image processing techniques and You Only Look Once v8 (YOLO) models were employed to analyze the seeds' position, size, and type. A detailed comparison of the effectiveness and performance of the applied methods was conducted. The experiments demonstrated that the best-trained CNN model achieved a segmentation accuracy of 90.1% IoU, with an average seed size error of 0.58 mm. The conclusions indicate a significant potential for using image processing techniques and CNN models in automating seed analysis processes, which could lead to increased efficiency and accuracy in these processes. [ABSTRACT FROM AUTHOR]

Lesion segmentation is a fundamental task in medical image processing, often facing the challenge of subtle lesions. It is important to detect these lesions, even though they can be difficult to identify. Convolutional neural networks, an effective method in medical image processing, often ignore the relationship between lesions, leading to topological errors during training. To tackle topological errors, move is made from pixel‐level to hypergraph representations. Hypergraphs can model lesions as vertices connected by hyperedges, capturing the topology between lesions. This paper introduces a novel dynamic hypergraph learning strategy called DHLS. DHLS allows for the dynamic construction of hypergraphs contingent upon input vertex variations. A hypergraph global‐aware segmentation network, termed HGSNet, is further proposed. HGSNet can capture the key high‐order structure information, which is able to enhance global topology expression. Additionally, a composite loss function is introduced. The function emphasizes the global aspect and the boundary of segmentation regions. The experimental setup compared HGSNet with other advanced models on medical image datasets from various organs. The results demonstrate that HGSNet outperforms other models and achieves state‐of‐the‐art performance on three public datasets. [ABSTRACT FROM AUTHOR]

In order to balance accuracy and real‐time performance in semantic segmentation, this paper proposes a real‐time semantic segmentation algorithm model based on attention mechanism and multi‐branch feature fusion using Fast convolutional neural network model (Fast‐SCNN). In this method, the spatial detail feature enhancement branch is introduced to enhance spatial detail features firstly. Then, through rational design of fusion module, the feature information of each branch is optimized to achieve better fusion of deep and shallow features. At the end of the feature fusion module, an adaptive feature enhancement focus module is introduced to capture the interdependence between remote pixels. The experimental results show that the proposed algorithm achieves 71.55% segmentation accuracy on Cityscapes dataset, the reasoning speed FPS is 97.6 frames/s, and the number of parameters is 1.39 M, which verifies the effectiveness of the network model constructed by the algorithm. Code is available at https://github.com/ccchhheeennn/model. [ABSTRACT FROM AUTHOR]

Abstract The integration of Augmented Reality (AR) into daily surgical practice is withheld by the correct registration of pre‐operative data. This includes intelligent 3D model superposition whilst simultaneously handling real and virtual occlusions caused by the AR overlay. Occlusions can negatively impact surgical safety and as such deteriorate rather than improve surgical care. Robotic surgery is particularly suited to tackle these integration challenges in a stepwise approach as the robotic console allows for different inputs to be displayed in parallel to the surgeon. Nevertheless, real‐time de‐occlusion requires extensive computational resources which further complicates clinical integration. This work tackles the problem of instrument occlusion and presents, to the authors’ best knowledge, the first‐in‐human on edge deployment of a real‐time binary segmentation pipeline during three robot‐assisted surgeries: partial nephrectomy, migrated endovascular stent removal, and liver metastasectomy. To this end, a state‐of‐the‐art real‐time segmentation and 3D model pipeline was implemented and presented to the surgeon during live surgery. The pipeline allows real‐time binary segmentation of 37 non‐organic surgical items, which are never occluded during AR. The application features real‐time manual 3D model manipulation for correct soft tissue alignment. The proposed pipeline can contribute towards surgical safety, ergonomics, and acceptance of AR in minimally invasive surgery.

Abstract Firstly, the Canny operator combined with circle fitting is used to position the working surface. Secondly, the median filter and the Laplacian operator are selected for preprocessing. Due to uneven illumination, surface texture, or environmental dust, the extracted scratches exhibit fragmentation, and traditional morphological operations cannot handle scratches well, so an improved Canny operator combined with probabilistic Hough transform is proposed for scratch connection. A bidirectional connection is introduced to optimize the edge detection process of the Canny operator, and a parallel algorithm is introduced to shorten the detection time. Finally, the standard Hough transform needs to traverse the entire parameter space, and the calculation is complicated, and the probability Hough transform is selected. The experimental results show that compared with the traditional Canny algorithm, the precision, recall, and F1‐score of the improved Canny algorithm are increased by 3.2%, 13.2%, and 6.0%, respectively. After adding parallel processing, the average detection time was reduced by 45 ms. Finally, the accuracy of scratches extracted using this algorithm reached 97.96%, the leak rate, and mistake rate of this study are only 3.33% and 2.00%, which provides a more accurate and efficient theoretical support for the research on brake disc scratch detection.

Abstract Human parsing is very important in a diverse range of industrial applications. Despite the considerable progress that has been achieved, the performance of existing methods is still less than satisfactory, since these methods learn the shared features of various parsing labels at the image level. This limits the representativeness of the learnt features, especially when the distribution of parsing labels is imbalanced or the scale of different labels is substantially different. To address this limitation, a Region‐level Parsing Refiner (RPR) is proposed to enhance parsing performance by the introduction of region‐level parsing learning. Region‐level parsing focuses specifically on small regions of the body, for example, the head. The proposed RPR is an adaptive module that can be integrated with different existing human parsing models to improve their performance. Extensive experiments are conducted on two benchmark datasets, and the results demonstrated the effectiveness of our RPR model in terms of improving the overall parsing performance as well as parsing rare labels. This method was successfully applied to a commercial application for the extraction of human body measurements and has been used in various online shopping platforms for clothing size recommendations. The code and dataset are released at this link https://github.com/applezhouyp/PRP.

Image segmentation is a core research in the image processing and computer vision. In this paper, we suggest a Bi-cubic spline phase transition potential and elaborate a Bi-Cubic spline phase transition potential development. In the image segmentation, we develop the new approach to apply the novel computational fluid dynamics in the boundary with subgrid. The numerical subgrid Bi-cubic method with Bi-Cubic spline for minimizing the piecewise constant energy functional is very efficient, robust and fast in the image segmentation with a multispecies multiphase segmentation models. The subgrid Bi-cubic spline is applied on the boundary with subgrid and the regular grid is applied on the non-boundary. The model generates a multispecies multiphase distribution with Bi-Cubic spline and we can extract the image segments with multispecies multiphase. Finally, we analyze the models and show the numerical results. Numerical results are presented with OCR (Optical Character Recognition) and the medical image. [ABSTRACT FROM AUTHOR]

Firstly, the Canny operator combined with circle fitting is used to position the working surface. Secondly, the median filter and the Laplacian operator are selected for preprocessing. Due to uneven illumination, surface texture, or environmental dust, the extracted scratches exhibit fragmentation, and traditional morphological operations cannot handle scratches well, so an improved Canny operator combined with probabilistic Hough transform is proposed for scratch connection. A bidirectional connection is introduced to optimize the edge detection process of the Canny operator, and a parallel algorithm is introduced to shorten the detection time. Finally, the standard Hough transform needs to traverse the entire parameter space, and the calculation is complicated, and the probability Hough transform is selected. The experimental results show that compared with the traditional Canny algorithm, the precision, recall, and F1‐score of the improved Canny algorithm are increased by 3.2%, 13.2%, and 6.0%, respectively. After adding parallel processing, the average detection time was reduced by 45 ms. Finally, the accuracy of scratches extracted using this algorithm reached 97.96%, the leak rate, and mistake rate of this study are only 3.33% and 2.00%, which provides a more accurate and efficient theoretical support for the research on brake disc scratch detection. [ABSTRACT FROM AUTHOR]

Image segmentation, the process of partitioning an image into meaningful regions, is a fundamental step in image processing, crucial for applications like computer vision, medical imaging, and object recognition. Image segmentation is an essential step of image processing that directly affects its success. Among the methods used for image segmentation, histogram-based thresholding is prevalent. Two well-known approaches to histogram-based thresholding are Otsu's and Kapur's methods in gray images that maximize the between-class variance and the entropy measure, respectively. Both techniques were introduced for bi-level thresholding. However, these techniques can be expanded to multilevel image thresholding. For this to occur, a large number of iterations are required to account for exact threshold values. To this end, various optimization techniques have been used to overcome this drawback. Recently, a new optimization algorithm called Battle Royal Optimizer (BRO) has been published, which is shown to solve various optimization tasks effectively. In this study, BRO has been applied to yield optimum threshold values in multilevel image thresholding. Here is also demonstrated the effectiveness of BRO for image segmentation on various images from the standard publicly accessible Berkeley segmentation dataset. We compare the performance of BRO to other state-of-the-art optimization-based methods and show that it outperforms them in terms of fitness value, Peak Signal-to-Noise Ratio, Structural Similarity Index Method, Feature Similarity Index Method (FSIM), Color FSIM (FSIMc), and Standard Deviation. These results underscore the potential of BRO as a promising solution for image segmentation tasks, particularly through its effective implementation of multilevel thresholding. [ABSTRACT FROM AUTHOR]

Detecting parcels accurately and efficiently has always been a challenging task when unloading from trucks onto conveyor belts because of the diverse and complex ways in which parcels are stacked. Conventional methods struggle to quickly and accurately classify the various shapes and surface patterns of unordered parcels. In this paper, we propose a parcel-picking surface detection method based on deep learning and image processing for the efficient unloading of diverse and unordered parcels. Our goal is to develop a systematic image processing algorithm that emphasises the boundaries of parcels regardless of their shape, pattern, or layout. The core of the algorithm is the utilisation of RGB-D technology for detecting the primary boundary lines regardless of obstacles such as adhesive labels, tapes, or parcel surface patterns. For cases where detecting the boundary lines is difficult owing to narrow gaps between parcels, we propose using deep learning-based boundary line detection through the You Only Look at Coefficients (YOLACT) model. Using image segmentation techniques, the algorithm efficiently predicts boundary lines, enabling the accurate detection of irregularly sized parcels with complex surface patterns. Furthermore, even for rotated parcels, we can extract their edges through complex mathematical operations using the depth values of the specified position, enabling the detection of the wider surfaces of the rotated parcels. Finally, we validate the accuracy and real-time performance of our proposed method through various case studies, achieving mAP (50) values of 93.8% and 90.8% for randomly sized and rotationally covered boxes with diverse colours and patterns, respectively. [ABSTRACT FROM AUTHOR]

3D instance segmentation is crucial for applications demanding comprehensive 3D scene understanding. Here, a novel method is introduced that simultaneously learns coefficients and prototypes. Employing an overcomplete sampling strategy, the method produces an overcomplete set of instance predictions, from which the optimal ones are selected through a Non‐Maximum Suppression (NMS) algorithm during inference. The obtained prototypes are visualizable and interpretable. The method demonstrates superior performance on S3DIS‐blocks, consistently outperforming existing methods in mRec and mPrec. Moreover, it operates 32.9% faster than the state‐of‐the‐art. Notably, with only 0.8% of the total inference time, the method exhibits an over 20‐fold reduction in the variance of inference time compared to existing methods. These attributes render the method well‐suited for practical applications requiring both rapid inference and high reliability. [ABSTRACT FROM AUTHOR]

The expansion of scientific image data holds great promise to quantify individuals, size distributions and traits. Computer vision tools are especially powerful to automate data mining of images and thus have been applied widely across studies in aquatic and terrestrial ecology. Yet marine benthic communities, especially infauna, remain understudied despite their dominance of marine biomass, biodiversity and playing critical roles in ecosystem functioning.Here, we disaggregated infauna from sediment cores taken throughout the spring transition (April–June) from a near‐natural mesocosm setup under experimental warming (Ambient, +1.5°C, +3.0°C). Numerically abundant mudsnails were imaged in batches under stereomicroscopy, from which we automatically counted and sized individuals using a superpixel‐based segmentation algorithm. Our segmentation approach was based on clustering superpixels, which naturally partition images by low‐level properties (e.g., colour, shape and edges) and allow instance‐based segmentation to extract all individuals from each image.We demonstrate high accuracy and precision for counting and sizing individuals, through a procedure that is robust to the number of individuals per image (5–65) and to size ranges spanning an order of magnitude (<750 μm to 7.4 mm). The segmentation routine provided at least a fivefold increase in efficiency compared with manual measurements. Scaling this approach to a larger dataset tallied >40k individuals and revealed overall growth in response to springtime warming.We illustrate that image processing and segmentation workflows can be built upon existing open‐access R packages, underlining the potential for wider adoption of computer vision tools among ecologists. The image‐based approach also generated reproducible data products that, alongside our scripts, we have made freely available. This work reinforces the need for next‐generation monitoring of benthic communities, especially infauna, which can display differential responses to average warming. [ABSTRACT FROM AUTHOR]

Wire electrical discharge machining (WEDM) is a process that removes material from conductive workpieces by using sequential electrical discharges. The morphology of the craters formed by these discharges is influenced by various process parameters and affects the quality and efficiency of the machining. To understand and optimize the WEDM process, it is essential to identify and characterize single craters from microscopy images. However, manual labeling of craters is tedious and prone to errors. This paper presents a novel approach to detect and segment single craters using state-of-the-art computer vision techniques. The YOLOv8 model, a convolutional neural network-based object detection technique, is fine-tuned on a custom dataset of WEDM craters to locate and enclose them with tight bounding boxes. The segment anything model, a vision transformer-based instance segmentation technique, is applied to the cropped images of individual craters to delineate their shape and size. Geometric analysis of the segmented craters reveals significant variations in their contour and area depending on the energy setting, while the wire diameter has minimal influence. [ABSTRACT FROM AUTHOR]

Biomedical image segmentation is a vital task in the analysis of medical imaging, including the detection and delineation of pathological regions or anatomical structures within medical images. It has played a pivotal role in a variety of medical applications, involving diagnoses, monitoring of diseases, and treatment planning. Conventionally, clinicians or expert radiologists have manually conducted biomedical image segmentation, which is prone to human error, subjective, and time-consuming. With the advancement in computer vision and deep learning (DL) algorithms, automated and semi-automated segmentation techniques have attracted much research interest. DL approaches, particularly convolutional neural networks (CNN), have revolutionized biomedical image segmentation. With this motivation, we developed a novel equilibrium optimization algorithm with a deep learning-based biomedical image segmentation (EOADL-BIS) technique. The purpose of the EOADL-BIS technique is to integrate EOA with the Faster RCNN model for an accurate and efficient biomedical image segmentation process. To accomplish this, the EOADL-BIS technique involves Faster R-CNN architecture with ResNeXt as a backbone network for image segmentation. The region proposal network (RPN) proficiently creates a collection of a set of region proposals, which are then fed into the ResNeXt for classification and precise localization. During the training process of the Faster RCNN algorithm, the EOA was utilized to optimize the hyperparameter of the ResNeXt model which increased the segmentation results and reduced the loss function. The experimental outcome of the EOADL-BIS algorithm was tested on distinct benchmark medical image databases. The experimental results stated the greater efficiency of the EOADL-BIS algorithm compared to other DL-based segmentation approaches. [ABSTRACT FROM AUTHOR]

Human parsing is very important in a diverse range of industrial applications. Despite the considerable progress that has been achieved, the performance of existing methods is still less than satisfactory, since these methods learn the shared features of various parsing labels at the image level. This limits the representativeness of the learnt features, especially when the distribution of parsing labels is imbalanced or the scale of different labels is substantially different. To address this limitation, a Region‐level Parsing Refiner (RPR) is proposed to enhance parsing performance by the introduction of region‐level parsing learning. Region‐level parsing focuses specifically on small regions of the body, for example, the head. The proposed RPR is an adaptive module that can be integrated with different existing human parsing models to improve their performance. Extensive experiments are conducted on two benchmark datasets, and the results demonstrated the effectiveness of our RPR model in terms of improving the overall parsing performance as well as parsing rare labels. This method was successfully applied to a commercial application for the extraction of human body measurements and has been used in various online shopping platforms for clothing size recommendations. The code and dataset are released at this link https://github.com/applezhouyp/PRP. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Education & Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

An unresolved issue in contemporary biomedicine is the overwhelming number and diversity of complex images that require annotation, analysis and interpretation. Recent advances in Deep Learning have revolutionized the field of computer vision, creating algorithms that compete with human experts in image segmentation tasks. However, these frameworks require large human-annotated datasets for training and the resulting "black box" models are difficult to interpret. In this study, we introduce Kartezio, a modular Cartesian Genetic Programming-based computational strategy that generates fully transparent and easily interpretable image processing pipelines by iteratively assembling and parameterizing computer vision functions. The pipelines thus generated exhibit comparable precision to state-of-the-art Deep Learning approaches on instance segmentation tasks, while requiring drastically smaller training datasets. This Few-Shot Learning method confers tremendous flexibility, speed, and functionality to this approach. We then deploy Kartezio to solve a series of semantic and instance segmentation problems, and demonstrate its utility across diverse images ranging from multiplexed tissue histopathology images to high resolution microscopy images. While the flexibility, robustness and practical utility of Kartezio make this fully explicable evolutionary designer a potential game-changer in the field of biomedical image processing, Kartezio remains complementary and potentially auxiliary to mainstream Deep Learning approaches. Deep learning frameworks require large human-annotated datasets for training and the resulting 'black box' models are difficult to interpret. Here, the authors present Kartezio; a modular Cartesian Genetic Programming-based computational strategy that generates fully transparent and easily interpretable image processing pipelines. [ABSTRACT FROM AUTHOR]

Abnormalities of navigation buoys include tilting, rusting, breaking, etc. Realizing automatic extraction and evaluation of rust on buoys is of great significance for maritime supervision. Severe rust may cause damage to the buoy itself. Therefore, a lightweight method based on machine vision is proposed for extracting and evaluating the rust of the buoy. The method integrates image segmentation and processing. Firstly, image segmentation technology is used to extract the metal part of the buoy based on an improved U-Net. Secondly, the RGB image is converted into an HSV image by preprocessing, and the transformation law of HSV channel color value is analyzed to obtain the best segmentation threshold and then the pixels of the rusted and the metal parts can be extracted. Finally, the rust ratio of the buoy is calculated to evaluate the rust level of the buoy. Results show that both the segmentation precision and recall are above 0.95, and the accuracy is nearly 1.00. Compared with the rust evaluation algorithm directly using the image processing method, the accuracy and processing speed of rust grade evaluation are greatly improved. [ABSTRACT FROM AUTHOR]

Segmentation is one of the image processing techniques, widely used in computer vision, to extract various types of information represented as objects or areas of interest. The development of neural networks has influenced image processing techniques, including creation of new ways of image segmentation. The aim of this study is to compare classical algorithms and deep learning methods in RGB image segmentation tasks. Two hypotheses were put forward: (1) The quality of segmentation applying deep learning methods is higher than using classical methods for RGB images, and (2) The increase of the RGB image resolution has positive impact on the segmentation quality. Two traditional segmentation algorithms (Thresholding and K-means) were compared with deep learning approach (U-Net, SegNet and FCN 8) to verify RGB segmentation quality. Two resolutions of images were taken into consideration: 160x240 and 320x480 pixels. Segmentation quality for each algorithm was estimated based on four parameters: Accuracy, Precision, Recall and Sorensen-Dice ratio (Dice score). In the study the Carvana dataset, containing 5,088 high-resolution images of cars, was applied. The initial set was divided into training, validation and test subsets as 60%, 20%, 20%, respectively. As a result, the best Accuracy, Dice score and Recall for images with resolution 160x240 were obtained for U-Net, achieving 99.37%, 98.56%, and 98.93%, respectively. For the same resolution the highest Precision 98.19% was obtained for FCN-8 architecture. For higher resolution, 320x480, the best mean Accuracy, Dice score, and Precision were obtained for FCN-8 network, reaching 99.55%, 99.95% and 98.85%, respectively. The highest results for classical methods were obtained for Threshold algorithm reaching 80.41% Accuracy, 58.49% Dice score, 67.32% Recall and 52.62% Precision. The results confirm both hypotheses. [ABSTRACT FROM AUTHOR]

Abstract 3D instance segmentation is crucial for applications demanding comprehensive 3D scene understanding. Here, a novel method is introduced that simultaneously learns coefficients and prototypes. Employing an overcomplete sampling strategy, the method produces an overcomplete set of instance predictions, from which the optimal ones are selected through a Non‐Maximum Suppression (NMS) algorithm during inference. The obtained prototypes are visualizable and interpretable. The method demonstrates superior performance on S3DIS‐blocks, consistently outperforming existing methods in mRec and mPrec. Moreover, it operates 32.9% faster than the state‐of‐the‐art. Notably, with only 0.8% of the total inference time, the method exhibits an over 20‐fold reduction in the variance of inference time compared to existing methods. These attributes render the method well‐suited for practical applications requiring both rapid inference and high reliability.

Abstract In this paper, a new approach to visual geo‐localization for natural environments is proposed. The digital elevation model (DEM) data in virtual space is rendered and construct a panoramic skyline database is constructed. By combining the skyline database with real‐world image data (used as the “queries” to be localized), visual geo‐localization is treated as a cross‐modal image retrieval problem for panoramic skyline images, creating a unique new visual geo‐localization benchmark for the natural environment. Specifically, the semantic segmentation model named LineNet is proposed, for skyline extractions from query images, which has proven to be robust to a variety of complex natural environments. On the aforementioned benchmarks, the fully automatic method is elaborated for large‐scale cross‐modal localization using panoramic skyline images. Finally, the compound index is delicately designed to reduce the storage space of the positioning global descriptors and improve the retrieval efficiency. Moreover, the proposed method is proven to outperform most state‐of‐the‐art methods.

Abstract Real‐time semantic segmentation is a crucial technology in automatic driving scenarios, which needs to meet both high precision and real‐time. The authors observe that learning complex correlations between object categories is vital in the real‐time semantic segmentation task. Moreover, image spatial detail information plays an important role in small object segmentation and preserving edges and textures. A Semantics Recalibration and Detail Enhancement Network for real‐time semantic segmentation based on BiSeNet V2 is proposed. On the one hand, a lightweight Semantics Recalibration module is designed to effectively extract global semantic contextual information, which combines pyramid segmentation and adaptive recalibration operations to learn the correlations between object categories. On the other hand, a Detail Enhancement module takes the feature maps of the shallow layers in the semantics branch as input and refines the feature maps to highlight the detail information. Finally, quantitative and qualitative analyses on Cityscapes and CamVid datasets demonstrate the effectiveness and generalisation of the proposed method.

In this paper, a new approach to visual geo‐localization for natural environments is proposed. The digital elevation model (DEM) data in virtual space is rendered and construct a panoramic skyline database is constructed. By combining the skyline database with real‐world image data (used as the "queries" to be localized), visual geo‐localization is treated as a cross‐modal image retrieval problem for panoramic skyline images, creating a unique new visual geo‐localization benchmark for the natural environment. Specifically, the semantic segmentation model named LineNet is proposed, for skyline extractions from query images, which has proven to be robust to a variety of complex natural environments. On the aforementioned benchmarks, the fully automatic method is elaborated for large‐scale cross‐modal localization using panoramic skyline images. Finally, the compound index is delicately designed to reduce the storage space of the positioning global descriptors and improve the retrieval efficiency. Moreover, the proposed method is proven to outperform most state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

• A computational binary characterization method for convex object(s). • A unified model for convex object(s) segmentation and convex hull computation. • Linearization technique employed to reduce the difficulty of the model solving. • A convergent proximal alternating direction method of multipliers for the linearization problem. • An interactive procedure to improve the segmentation accurac y in terms of shape distance and D ice coefficient. Convexity prior is one of the main cues for human vision and shape completion with important applications in image processing and computer vision. This paper provides a computable characterization method for shape convexity, and illustrates its applications in image segmentation and convex hull computation. We prove that the convexity of a region is equivalent to a series of quadratic inequality constraints on its indicator function. By incorporating this result, models are proposed for image segmentation with convexity prior and convex hull computation of clean and noisy data sets, respectively. Then, these models are summarized into a unified optimization problem on binary function(s) with the quadratic inequality constraints. Numerical method is proposed by linearizing the quadratic constraints. The linearization problem is solved by a proximal alternating direction method of multipliers, the convergence of which is guaranteed under some proper conditions. Numerical experiments demonstrate the efficiency and effectiveness of the proposed methods for image segmentation and convex hull computation. [ABSTRACT FROM AUTHOR]

Superpixel segmentation has been widely used in computer vision as a preprocessing to reduce the number of image primitives for subsequent image processing tasks. Simple Linear Iterative Clustering (SLIC) is the most popular superpixel segmentation algorithm in the literature, which is an iterative algorithm. The basic SLIC technique includes two main steps named Assignment and Update steps, and their data dependency is the main problem to speed up execution of the basic SLIC algorithm. It is also well known that this algorithm is not memory efficient, which is the main bottleneck in applying basic SLIC in low-power applications. In this paper, we have proposed a new structure for SLIC implementation. This new structure replaces the cluster-based search operation with pixel-based process in the Assignment step that gains considerable speed improvement. This new technique simply removes the data dependency in the SLIC structure. In the proposed method, the distance index, the main parameter computed in the Assignment step, no longer is needed to be stored in memory. This leads to a significant improvement in the memory efficiency of the proposed structure. The proposed structure is implemented on the Virtex-5 FPGA family, and the results show about 26 % in memory improvement compared to basic SLIC. According to the implementation results, the proposed technique process 143 frames per second for an input image of 300 × 400 pixel resolution which is far faster than real-time process requirements. [ABSTRACT FROM AUTHOR]

Abstract Video summarization offers a summary version that conveys the primary information of a longer video. The main challenges of video summarization are related to keyframe extraction and saliency mapping. Thus, this work proposes a sparse coding model for keyframe extraction and saliency mapping applications. Specifically, the minimax concave penalty (MCP) is utilized as a sparse regularization scheme and the regularized non‐convex MCP problem is solved by decomposing MCP into two convex functions and the convex function's algorithm difference is relied on to solve the resulting sub‐problems. The experimental results demonstrate higher compressed keyframes and saliency maps than current state‐of‐the‐art algorithms. In particular, the model attains a lower summary length of 34% and 19% compared to sparse modeling representation selection (SMRS) and sparse modeling using the determinant sparsity measure (SC‐det), respectively. In addition, the developed scheme has a shorter computation time, requiring 82% and 33% less time than the ITTI and the dense and sparse reconstruction (DSR) methods.

• A new model was proposed to segment the intensity inhomogeneity image. • A prior constraint was added in the proposed for improving the robustness. • Based on an operator method, the proposed model can be efficiently solved. • Numerical implementations showed the robustness of the proposed model. Image segmentation is a fundamental task in computer vision and image processing. How to efficiently decrease the effect such as high noise, low resolution and intensity inhomogeneity is the key to improve the accuracy of segmentation. To this end, we propose a novel segmentation model by assuming the image to be the product of a piecewise-constant function and a smooth function and then the model can be proposed based on the suitable gradient spaces. To improve the robustness of the proposed model, we add a prior constraint for the smooth function and then analyse the existence of the solution based on the functional theory. Since the proposed model includes two nonsmooth terms, we use a heat kernel convolution to approximately replace the length regularization term and then the alternating direction method of multipliers can be employed to solve it. Numerical experiments on several testing images demonstrate that the effectiveness and the robustness of the proposed model compared to some state-of-the-art segmentation models. [ABSTRACT FROM AUTHOR]

Real‐time semantic segmentation is a crucial technology in automatic driving scenarios, which needs to meet both high precision and real‐time. The authors observe that learning complex correlations between object categories is vital in the real‐time semantic segmentation task. Moreover, image spatial detail information plays an important role in small object segmentation and preserving edges and textures. A Semantics Recalibration and Detail Enhancement Network for real‐time semantic segmentation based on BiSeNet V2 is proposed. On the one hand, a lightweight Semantics Recalibration module is designed to effectively extract global semantic contextual information, which combines pyramid segmentation and adaptive recalibration operations to learn the correlations between object categories. On the other hand, a Detail Enhancement module takes the feature maps of the shallow layers in the semantics branch as input and refines the feature maps to highlight the detail information. Finally, quantitative and qualitative analyses on Cityscapes and CamVid datasets demonstrate the effectiveness and generalisation of the proposed method. [ABSTRACT FROM AUTHOR]

The deep learning-based image segmentation approach has evolved into the mainstream of target detection and shape characterization in microscopic image analysis. However, the accuracy and generalizability of deep learning approaches are still hindered by the insufficient data problem that results from the high expense of human and material resources for microscopic image acquisition and annotation. Generally, image augmentation can increase the amount of data in a short time by means of mathematical simulation, and has become a necessary module for deep learning-based material microscopic image analysis. In this work, we first review the commonly used image augmentation methods and divide more than 60 basic image augmentation methods into eleven categories based on different implementation strategies. Secondly, we conduct experiments to verify the effectiveness of various basic image augmentation methods for the image segmentation task of two classical material microscopic images using evaluation metrics with different applicabilities. The U-Net model was selected as a representative benchmark model for image segmentation tasks, as it is the classic and most widely used model in this field. We utilize this model to verify the improvement of segmentation performance by various augmentation methods. Then, we discuss the advantages and applicability of various image augmentation methods in the material microscopic image segmentation task. The evaluation experiments and conclusions in this work can serve as a guide for the creation of intelligent modeling frameworks in the materials industry. [ABSTRACT FROM AUTHOR]

Root phenotypic parameters are the important basis for studying the growth state of plants, and root researchers obtain root phenotypic parameters mainly by analyzing root images. With the development of image processing technology, automatic analysis of root phenotypic parameters has become possible. And the automatic segmentation of roots in images is the basis for the automatic analysis of root phenotypic parameters. We collected highresolution images of cotton roots in a real soil environment using minirhizotrons. The background noise of the minirhizotron images is extremely complex and affects the accuracy of the automatic segmentation of the roots. In order to reduce the influence of the background noise, we improved OCRNet by adding a Global Attention Mechanism (GAM) module to OCRNet to enhance the focus of the model on the root targets. The improved OCRNet model in this paper achieved automatic segmentation of roots in the soil and performed well in the root segmentation of the high-resolution minirhizotron images, achieving an accuracy of 0.9866, a recall of 0.9419, a precision of 0.8887, an F1 score of 0.9146 and an Intersection over Union (IoU) of 0.8426. The method provided a new approach to automatic and accurate root segmentation of high-resolution minirhizotron images. [ABSTRACT FROM AUTHOR]

With the development of computer vision technology, its applications in forestry are steadily becoming wider. To address the problems of inconvenience in transporting unmanned aerial vehicles (UAVs), as well as the complex operation of large instruments for measurement, a new method based on multi-vision image segmentation and coordinate fusion (MISF) is proposed in this paper for measuring the size of standing trees. In MISF, after images of a standing tree are captured using a camera from multiple angles, a semantic segmentation method based on deep learning is used to segment the main body of the standing tree and automatically detect the edge feature points. Next, the effects of visual field splicing and fusion are analyzed collaboratively using the correlations among images, so as to restore the three-dimensional spatial information of the feature points of the tree to be measured. Lastly, the size attributes of the standing tree, such as height, diameter at breast height (DBH), and crown width, are automatically measured. The urban environment measurement experiment showed that the relative errors of tree height, DBH, and crown width measured using the proposed method, i.e., MISF, were 1.89%, 2.42%, and 3.15%, respectively, representing a significant enhancement compared with binocular measurement. On the one hand, the experimental results exhibited a high degree of measurement accuracy; therefore, MISF can be used for the management inventory of typical forests. On the other hand, MISF cannot be used if a tree's images cannot be acquired due to environmental or other reasons. [ABSTRACT FROM AUTHOR]

As a severe thermal damage, grinding burns reduce the surface quality and service life of high-performance gears. In this study, to realize accurate localization, classification, and grading of burn defects on gear grinding surfaces, a machine vision–based intelligent detection method was proposed. Different from image processing methods based on hand-designed features, the proposed method can minimize inspection conditions. To recognize individual gear functional surfaces and burn regions from random backgrounds, an image segmentation model was developed by using deep convolutional neural networks. For the scarcity of defect samples in industrial surface testing, a data-augmentation method combining deep learning methods with geometric and color-space transformations was proposed. The experimental results of the gear surface image dataset demonstrated that the proposed burn segmentation model has a precision and recall rate of 84.44% and 82.79%, respectively. This work provides fresh insights for realizing efficient and accurate detection of gear grinding burn defects. [ABSTRACT FROM AUTHOR]

Video summarization offers a summary version that conveys the primary information of a longer video. The main challenges of video summarization are related to keyframe extraction and saliency mapping. Thus, this work proposes a sparse coding model for keyframe extraction and saliency mapping applications. Specifically, the minimax concave penalty (MCP) is utilized as a sparse regularization scheme and the regularized non‐convex MCP problem is solved by decomposing MCP into two convex functions and the convex function's algorithm difference is relied on to solve the resulting sub‐problems. The experimental results demonstrate higher compressed keyframes and saliency maps than current state‐of‐the‐art algorithms. In particular, the model attains a lower summary length of 34% and 19% compared to sparse modeling representation selection (SMRS) and sparse modeling using the determinant sparsity measure (SC‐det), respectively. In addition, the developed scheme has a shorter computation time, requiring 82% and 33% less time than the ITTI and the dense and sparse reconstruction (DSR) methods. [ABSTRACT FROM AUTHOR]

As a fundamental but difficult topic in computer vision, 3D object segmentation has various applications in medical image analysis, autonomous vehicles, robotics, virtual reality, lithium battery image analysis, etc. In the past, 3D segmentation was performed using hand-made features and design techniques, but these techniques could not generalize to vast amounts of data or reach acceptable accuracy. Deep learning techniques have lately emerged as the preferred method for 3D segmentation jobs as a result of their extraordinary performance in 2D computer vision. Our proposed method used a CNN-based architecture called 3D UNET, which is inspired by the famous 2D UNET that has been used to segment volumetric image data. To see the internal changes of composite materials, for instance, in a lithium battery image, it is necessary to see the flow of different materials and follow the directions analyzing the inside properties. In this paper, a combination of 3D UNET and VGG19 has been used to conduct a multiclass segmentation of publicly available sandstone datasets to analyze their microstructures using image data based on four different objects in the samples of volumetric data. In our image sample, there are a total of 448 2D images, which are then aggregated as one 3D volume to examine the 3D volumetric data. The solution involves the segmentation of each object in the volume data and further analysis of each object to find its average size, area percentage, total area, etc. The open-source image processing package IMAGEJ is used for further analysis of individual particles. In this study, it was demonstrated that convolutional neural networks can be trained to recognize sandstone microstructure traits with an accuracy of 96.78% and an IOU of 91.12%. According to our knowledge, many prior works have applied 3D UNET for segmentation, but very few papers extend it further to show the details of particles in the sample. The proposed solution offers a computational insight for real-time implementation and is discovered to be superior to the current state-of-the-art methods. The result has importance for the creation of an approximately similar model for the microstructural analysis of volumetric data. [ABSTRACT FROM AUTHOR]

Generation of random fields (GRF) for image segmentation represents partitioning an image into different regions that are homogeneous or have similar facets of the image. It is one of the most challenging tasks in image processing and a very important pre-processing step in the fields of computer vision, image analysis, medical image processing, pattern recognition, remote sensing, and geographical information system. Many researchers have presented numerous image segmentation approaches, but still, there are challenges like segmentation of low contrast images, removal of shadow in the images, reduction of high dimensional images, and computational complexity of segmentation techniques. In this review paper, the authors address these issues. The experiments are conducted and tested on the Berkely dataset (BSD500), Semantic dataset, and our own dataset, and the results are shown in the form of tables and graphs. [ABSTRACT FROM AUTHOR]

Premedical diagnostics is the process of examining survey results. Correct premedical diagnostics can improve the process of patient management and reduce the burden on the medical sector. Diagnostics of medical images such as computed tomography and X-ray are an obligatory step for further treatment. However, the shortage of clinicians causes delays in this step. We observed two state-of-the-art algorithms proposed for medical image segmentation: TransUnet and Swin-Unet. We conducted a theoretical comparison of algorithms in terms of the applicability of pre-hospital diagnostics according to quality and speed of training. The comparison is based on the original source of code provided by the authors of the original articles. We chose these two algorithms because they have similar U-form architecture, a high level of citation, and show competitive DICE scores on pictures of various human organs. Some architectural features were also important. Both models inherit key elements of U-net. TransUnet is a hybrid Transformer and CNN model. It consists of Transformer encoder and a convolutional decoder. Some additional computations are required in the bottleneck. Swin-Unet is a fully Transformer-based model. These architectural differences give rise to a difference in the number of trainable parameters. Generally, deeper architectures with bigger number of parameters usually show better performance, however, according to our review, Swin-Unet has smaller number of parameters and shows better DICE and Hausdorff Distance. It should be noted that the distribution between false positive and false negative predictions is important in medical image processing. It is crucial to avoid overloading the medical sector while also not missing any sick patients. Precision and recall can be used to evaluate the ratio of incorrect predictions. Therefore, we also observed the results of caries segmentation where precision and DICE were provided. In this specific case, TransUnet shows better DICE and recall values but worse precision. [ABSTRACT FROM AUTHOR]

Image segmentation, which has become a research hotspot in the field of image processing and computer vision, refers to the process of dividing an image into meaningful and non-overlapping regions, and it is an essential step in natural scene understanding. Despite decades of effort and many achievements, there are still challenges in feature extraction and model design. In this paper, we review the advancement in image segmentation methods systematically. According to the segmentation principles and image data characteristics, three important stages of image segmentation are mainly reviewed, which are classic segmentation, collaborative segmentation, and semantic segmentation based on deep learning. We elaborate on the main algorithms and key techniques in each stage, compare, and summarize the advantages and defects of different segmentation models, and discuss their applicability. Finally, we analyze the main challenges and development trends of image segmentation techniques. [ABSTRACT FROM AUTHOR]

Image semantic segmentation is one of the core tasks for computer vision. It is widely used in fields such as unmanned driving, medical image processing, geographic information systems, and intelligent robots. Aiming at the problem that the existing semantic segmentation algorithm ignores the different channel and location features of the feature map and the simple method when the feature map is fused, this paper designs a semantic segmentation algorithm that combines the attention mechanism. First, dilated convolution is used, and a smaller downsampling factor is used to maintain the resolution of the image and to obtain its detailed information. Secondly, the attention mechanism module is introduced to assign weights to different parts of the feature map, which reduces the accuracy loss. The design feature fusion module assigns weights to the feature maps of different receptive fields obtained by the two paths and merges them together to obtain the final segmentation result. Finally, through experiments, it was verified on the Camvid, Cityscapes, and PASCAL VOC2012 data sets. Mean intersection over union (MIoU) and mean pixel accuracy (MPA) are used as metrics. The method in this paper can make up for the loss of accuracy caused by downsampling while ensuring the receptive field and improving the resolution, which can better guide the model learning. And the proposed feature fusion module can better integrate the features of different receptive fields. Therefore, the proposed method can significantly improve the segmentation performance compared to the traditional method. [ABSTRACT FROM AUTHOR]

Deep learning methods have achieved outstanding results in many image processing and computer vision tasks, such as image segmentation. However, they usually do not consider spatial dependencies among pixels/voxels in the image. To obtain better results, some methods have been proposed to apply classic spatial regularization, such as total variation, into deep learning models. However, for some challenging images, especially those with fine structures and low contrast, classical regularizations are not suitable. We derived a new regularization to improve the connectivity of segmentation results and make it applicable to deep learning. Our experimental results show that for both deep learning methods and unsupervised methods, the proposed method can improve performance by increasing connectivity and dealing with low contrast and, therefore, enhance segmentation results. [ABSTRACT FROM AUTHOR]

Steel plays an important role in industry, and the surface defect detection for steel products based on machine vision has been widely used during the last two decades. This paper attempts to review state‐of‐art of vision‐based surface defect inspection technology of steel products by investigating about 170 publications. This review covers the overall aspects of vision‐based surface defect inspection for steel products including hardware system, automated vision‐based inspection method, existing problems and latest development. The types of steel product surface defects composition of visual inspection system are briefly described, and image acquisition system is introduced as well. The image processing algorithms for surface defect detection of steel products are reviewed, including image pre‐processing, region of interest (ROI) detection, image segmentation for ROI, feature extraction and selection and defect classification. The important problems such as small sample and real time of steel surface defect detection are discussed. Finally, the challenge and development trend of steel surface defect detection are prospected. [ABSTRACT FROM AUTHOR]

Automatic brain tumor detection in MR Images is one of the basic applications of machine vision in medical image processing, which, despite much research, still needs further development. Using multiple machine learning techniques as an ensemble system is one of the solutions that can be effective in achieving this goal. In this paper, a novel method for diagnosing brain tumors by combining data mining and machine learning techniques has been proposed. In the proposed method, each image is initially pre-processed to eliminate its background region and identify brain tissue. The Social Spider Optimization (SSO) algorithm is then utilized to segment the MRI Images. The MRI Images segmentation allows for a more precise identification of the tumor region in the image. In the next step, the distinctive features of the image are extracted using the SVD technique. In addition to removing redundant information, this strategy boosts the speed of the processing at the classification stage. Finally, a combination of the algorithms Naïve Bayes, Support vector machine and K-nearest neighbor is used to classify the extracted features and detect brain tumors. Each of the three algorithms performs feature classification individually, and the final output of the proposed model is created by integrating the three independent outputs and voting the results. The results indicate that the proposed method can diagnose brain tumors in the BRATS 2014 dataset with an average accuracy of 98.61%, sensitivity of 95.79% and specificity of 99.71%. Additionally, the proposed method could diagnose brain tumors in the BTD20 database with an average accuracy of 99.13%, sensitivity of 99% and specificity of 99.26%. These results show a significant improvement compared to previous efforts. The findings confirm that using the image segmentation technique, as well as the ensemble learning, is effective in improving the efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

This research study compares the performance of different digital image processing algorithms based on computer vision segmentation methods to process satellite multispectral images of Normalized Difference Vegetation Index (NDVI) to estimate agricultural cropland yield as a proposal for supporting spatial planning decisions. NDVI multispectral images were collected from Sentinel-2 L2-A satellite with distinctive features to be processed through these algorithms implemented in an owned and friendly software interface developed in MATLAB App Designer. These are based on image color detection, using three techniques: rectangular thresholding method, simple thresholding method, and segmentation through Mahalanobis discriminant classifier. The segmented images were used to estimate cropland yields as a function of NDVI variations and the characteristics of each analyzed image, employing a linear model that assigned a yield to each segmented area as a function of a specific NDVI range. Algorithm accuracy was determined as a function of expected cropland yield. Results show that the rectangular thresholding method tends to average cropland yield value in slightly non-uniform images. In contrast, thresholding by pixel and Mahalanobis methods performed better on highly non-uniform NDVI images, with deviations less than 8% compared with the expected cropland yield. The rectangular thresholding method could be a more straightforward tool regarding computational cost since, e.g., the demarcation of rectangular areas is easier in any cultivated area, facilitating the implementation of spatial support plans for farmers. The proposal is to use the rectangular thresholding method as a planning tool, as the other methods may be used for more accurate estimations. [ABSTRACT FROM AUTHOR]

Medical image segmentation is a crucial stage in computer vision and image processing to help the later-stage diagnosis process become more accurate. Because medical image segmentation, such as X-ray, can extract tissue, organs, and pathological structures. However, medical image processing, primarily in the segmentation process, has significant challenges regarding feature representation. Because medical images have different characteristics than other images related to contrast, blur, and noise. This study proposes the use of lung segmentation on chest X-ray images based on deep learning with the FCA-Net (Fully Convolutional Attention Network) architecture. In addition, attention modules, namely spatial attention and channel attention, are added to the Res2Net encoder so that it is expected to be able to represent features better. This research was conducted on chest X-ray images from Qatar University contained in the Kaggle repository. A chest x-ray image measuring 256 × 256 pixels and as many as 1500 images were then divided into 10% testing data and 90% training data. The training data will then be processed in K-Fold Cross validation from K = 2 until K = 10. The experiment was conducted with scenarios that used spatial attention, channel attention, and a combination of spatial and channel attention. The best test results in this study were using a variety of spatial attention and channel attention in the division of K-Fold with a value of K = 5 with a DSC (Dice Similarity Coefficient) value in the testing data of 97.24% and IoU (Intersection over Union) in the testing data of 94.66%. This accuracy result is better than the UNet++, DeepLabV3+, and SegNet architectures. [ABSTRACT FROM AUTHOR]

Deep neural networks have been tremendously successful at segmenting objects in images. However, it has been shown they still have limitations on challenging problems such as the segmentation of medical images. The main reason behind this lower success resides in the reduced size of the object in the image. In this paper we overcome this limitation through a cyclic collaborative framework, CyCoSeg. The proposed framework is based on a deep active shape model (D-ASM), which provides prior information about the shape of the object, and a semantic segmentation network (SSN). These two models collaborate to reach the desired segmentation by influencing each other: SSN helps D-ASM identify relevant keypoints in the image through an Expectation Maximization formulation, while D-ASM provides a segmentation proposal that guides the SSN. This cycle is repeated until both models converge. Extensive experimental evaluation shows CyCoSeg boosts the performance of the baseline models, including several popular SSNs, while avoiding major architectural modifications. The effectiveness of our method is demonstrated on the left ventricle segmentation on two benchmark datasets, where our approach achieves one of the most competitive results in segmentation accuracy. Furthermore, its generalization is demonstrated for lungs and kidneys segmentation in CT scans. [ABSTRACT FROM AUTHOR]

Monitoring food processing is mandatory for controlling and ensuring product quality. Most of the used techniques are destructive, arduous, and time-consuming. Non-destructive analyses are convenient for rapid and conservative food quality assessment. Color images of apple slices during the manufacturing of healthy snacks were used for monitoring the drying processing. The implementation of the image-based analysis was straightforward, feasible, and low-cost. The parameters analyzed during imagen acquisition for normalizing were: contrast enhancement, binarization, and morphologic processing, varying the illumination and reference between the positions of the camera and object under analysis. Several apple features related to color, texture, and shape were extracted with computer vision techniques and also analyzed. During image analysis, the entropy was one of the most relevant computed features according to principal component analysis, and it was also relevant in terms of physical interpretation. The average percentage of entropy increase was 19.81% in the green and blue channels, while it was 16.82% in the red channel. Other relevant visual features were the skewness and kurtosis in the RGB channels; and textural information such as contrast, correlation, and variance. [ABSTRACT FROM AUTHOR]