Region-based Methods Research Articles

Deep Coattention-Based Comparator for Relative Representation Learning in Person Re-Identification.

Person re-identification (re-ID) favors discriminative representations over unseen shots to recognize identities in disjoint camera views. Effective methods are developed via pair-wise similarity learning to detect a fixed set of region features, which can be mapped to compute the similarity value. However, relevant parts of each image are detected independently without referring to the correlation on the other image. Also, region-based methods spatially position local features for their aligned similarities. In this article, we introduce the deep coattention-based comparator (DCC) to fuse codependent representations of paired images so as to correlate the best relevant parts and produce their relative representations accordingly. The proposed approach mimics the human foveation to detect the distinct regions concurrently across images and alternatively attends to fuse them into the similarity learning. Our comparator is capable of learning representations relative to a test shot and well-suited to reidentifying pedestrians in surveillance. We perform extensive experiments to provide the insights and demonstrate the state of the arts achieved by our method in benchmark data sets: 1.2 and 2.5 points gain in mean average precision (mAP) on DukeMTMC-reID and Market-1501, respectively.

Mammogram Segmentation Techniques: A Review

There is a significant development in computer-aided detection (CADe) and computer-aided diagnostic (CADx) systems in recent years. This development coincides with the evolution of computing power and the growth of data. The CAD systems support detections and diagnosis of significant diseases, including cancer. Breast cancer is one of the most prevalent cancers influencing women and causing death around the world. Early detection of breast cancer has a significant effect on treatment. The typical CAD system goes through various steps, including image segmentation, feature extraction, and image classification. Image segmentation plays an important role in CAD systems and simplifies further processing. This review explores popular mammogram segmentation techniques. A mammogram is medical imaging which uses a low-dose x-ray system to see inner tissues of the breast. There are many segmentation techniques used to segment medical images. These techniques can be categorized into five main categories: region-based methods, boundary-based methods, atlas-based methods, model-based methods, and deep learning. A ground truth image is needed to measure the performance of the segmentation algorithm. Different performance measurements were used to evaluate the segmentation process, including accuracy, precision, recall, F1 score, Hausdorff Distance, Jaccard, and Dice Index. The research in mammogram segmentation has yielded promising results, but there is room for improvements.

Exploring Spatial Diversity for Region-Based Active Learning.

State-of-the-art methods for semantic segmentation are based on deep neural networks trained on large-scale labeled datasets. Acquiring such datasets would incur large annotation costs, especially for dense pixel-level prediction tasks like semantic segmentation. We consider region-based active learning as a strategy to reduce annotation costs while maintaining high performance. In this setting, batches of informative image regions instead of entire images are selected for labeling. Importantly, we propose that enforcing local spatial diversity is beneficial for active learning in this case, and to incorporate spatial diversity along with the traditional active selection criterion, e.g., data sample uncertainty, in a unified optimization framework for region-based active learning. We apply this framework to the Cityscapes and PASCAL VOC datasets and demonstrate that the inclusion of spatial diversity effectively improves the performance of uncertainty-based and feature diversity-based active learning methods. Our framework achieves 95% performance of fully supervised methods with only 5 - 9% of the labeled pixels, outperforming all state-of-the-art region-based active learning methods for semantic segmentation.

Thyroid nodules segmentation methods in clinical ultrasound images: A review

Thyroid is an extremely essential butterfly shaped organ which is positioned in front of neck. For finding thyroid disease, ultrasound imaging is considered a best for identification of thyroid nodules because of its inexpensive and trouble-free nature. For diagnosis of thyroid disorder, it is very important to separate thyroid nodules from thyroid gland. For the same in biomedical image processing, image segmentation and classification followed by image preprocessing is very imperative steps. The key goal of this work is to categorized of thyroid nodules, thyroid gland segmentation methods. This paper explained different segmentation methods like counter and shaped based, region based and machine learning and deep learning strategies for thyroid gland and thyroid nodules. In addition, grouping of thyroid knobs is classified by traditional and convolution neural network for different feature extraction methods. All these methods are evaluated and compared by different quality metrics. After careful assessment of plenty of paper we did comparative and comprehensive analysis of segmentation methods with deep learning. Segmentation by deep learning approach gives better performance but it required more marked data base. In thyroid nodules segmentation region-based methods and contour and shape-based methods gives better performance. This paper concludes segmentation methods and their performance which is based on image attributes applications etc. The performance is assets by accuracy, selectivity and specificity and mean overlap parameters. Moreover, we concentrate on several advantages and disadvantages of current thyroid nodules ultrasound image segmentation of thyroid nodules and thyroid gland methods for 2Dimentionsl Ultrasound image, which would be useful for future studies such as identification of specific thyroid disease.

Simultaneous Detection of Signal Regions Using Quadratic Scan Statistics With Applications to Whole Genome Association Studies

We consider in this article detection of signal regions associated with disease outcomes in whole genome association studies. Gene- or region-based methods have become increasingly popular in whole genome association analysis as a complementary approach to traditional individual variant analysis. However, these methods test for the association between an outcome and the genetic variants in a prespecified region, for example, a gene. In view of massive intergenic regions in whole genome sequencing (WGS) studies, we propose a computationally efficient quadratic scan (Q-SCAN) statistic based method to detect the existence and the locations of signal regions by scanning the genome continuously. The proposed method accounts for the correlation (linkage disequilibrium) among genetic variants, and allows for signal regions to have both causal and neutral variants, and the effects of signal variants to be in different directions. We study the asymptotic properties of the proposed Q-SCAN statistics. We derive an empirical threshold that controls for the family-wise error rate, and show that under regularity conditions the proposed method consistently selects the true signal regions. We perform simulation studies to evaluate the finite sample performance of the proposed method. Our simulation results show that the proposed procedure outperforms the existing methods, especially when signal regions have causal variants whose effects are in different directions, or are contaminated with neutral variants. We illustrate Q-SCAN by analyzing the WGS data from the Atherosclerosis Risk in Communities study. Supplementary materials for this article are available online.

T-Spline Surface Toolpath Generation Using Watershed-Based Feature Recognition

The freeform surface is treated as a single machining region for most traditional toolpath generation algorithms. However, due to the complexity of a freeform surface, it is impossible to produce a high-quality surface using one unique machining process. Hence, region-based methods are widely investigated for freeform surface machining to achieve an optimized toolpath. The Non-Uniform Rational B-spline Surface (NURBS) represented freeform surface is not suitable for region-based toolpath generation because of the surface gaps caused by NURBS trimming and merging operations. To solve the limitation of the NURBS, T-spline is proposed with the advantages of being gap-free, having less control points, and local refinement, which is an ideal tool for region-based toolpath generation. Thus, T-spline is introduced to represent a freeform surface for its toolpath generation in the paper. A region-based toolpath generation method for the T-spline surface is proposed based on watershed technology. Firstly, watershed-based feature recognition is presented to divide the T-spline surface into a set of sub-regions. Secondly, the concept of a PolyBoundingBox that consists of a set of minimum bounding boxes is proposed to describe the sub-regions, and Manufacturing-Suitable Regions are constructed with the help of T-spline local refinement and the PolyBoundingBox. In the end, an optimized multi-rectangles toolpath generation algorithm is applied for sub-regions. The proposed method is tested using three synthetic T-spline surfaces, and the comparison results show the advantage in toolpath length and toolpath reversing number.

An Integrated System for Detection Exudates and Severity Quantification for Diabetic Macular Edema

The prevalence of vision loss because of Diabetic macular edema (DME), which is a complication caused by diabetes mellitus, is increasing. Seven per cent of Indian diabetic population suffer from DME or damage to macula. The study proposes an integrated model to contribute to the prevention of loss of visual acuity. For detection of exudates and visualization of severity of DME image processing, machine learning and data analysis strategies are used. Experimentation on Indian population is done using Indian Diabetic Eye Diseases Dataset (IDEDD), acquired from metropolitan region of Mumbai and publicly available Indian Diabetic Retinopathy Image Dataset (IDRiD, Nanded) and a standard public database DIARETDB1- Standard Diabetic Retinopathy Database. To negate the effect of increase in the dimensionality and overfitting of the dataset parameters, a tree-based forward search algorithm for optimal feature subset identification is proposed. This provides global insight of effect of the statistical and spatial features on model behaviour. Machine learning algorithms of random forest and support vector machine are used for classification. The sensitivity and specificity of 97.1% and 100% is achieved for IDEDD data. Severity grading is done using image processing for segmenting the vessel mesh, optic disk, and macula from the abnormal retinal scans for detecting clinically significant macular edema by visualizing exudates. The distance between optic disc—fovea (OF) and the ratio of distance (OF) to that of disc diameter is formulated for localization of macula. Region-based and distance-based grading methods for quantification of the severity and visualization are implemented. The proposed algorithm enables the building of a predictive model for primordial and secondary prevention of DME with high classification accuracy and visualization of severity grading.

A survey of level set method for image segmentation with intensity inhomogeneity

Image segmentation is a fundamental task in computer vision and image processing. Due to the presence of high noise, low resolution and intensity inhomogeneity, it is still a difficult problem in the practical applications. Level set methods have been widely used in image processing and computer vision. During the past decades, many models based on level set methods have been proposed to solve image segmentation with intensity inhomogeneity. It is necessary to conduct a comprehensive review and comparison of these models. Specifically, level set methods can be categorized into two groups, including edge-based level set methods (EBLSMs) and region-based level set methods (RBLSMs). This paper reviews some of the recent advances in EBLSMs and RBLSMs for segmenting image with intensity inhomogeneity. Their advantages and disadvantages are discussed in an objective point of view, and their performance is compared on image segmentation with intensity inhomogeneity. Finally, this paper further explores and discusses some open questions in segmenting images with intensity inhomogeneity.

Analysis of Breathing Patterns from Thermal Images Using an Automated Segmentation Method

Breathing is one of the important vital signs in diagnosing and monitoring for patients’ treatment and disease. Few modalities have been used to evaluate breathing activity such as respiratory belt, thermistor and capacitive sensor. However, these requires external attachments such as electrode or sensor which might be inconvenience over long period of time. Hence, we proposed the use of thermography as a contactless monitoring device. In this study, inspiration time and expiration time of three different breathing patterns such as normal, prolonged and rapid breathing patterns were measured by using the thermography. Thermal images obtained from the subjects were processed and analysed by using an automated segmentation method which integrate the knowledge of edge-based and region-based segmentation methods into the algorithm developed. The algorithm developed in this study has shown that the tracker was able to segment the region of interest of the thermal images automatically and it provides a more accurate and stable results than manual calculation method. Thus, three different types of breathing patterns could be identified based on the inspiration time to expiration time ratio. Results shows that there was less than 5% of relative error which suggest the benefit of this algorithm.

Defocus map estimation from a single image using improved likelihood feature and edge-based basis

Defocus map estimation (DME) is very useful in many computer vision applications and has drawn much attention in recent years. Edge-based DME methods can generate sharp defocus discontinuities but usually suffer from textures of the input image. Region-based methods are free of textures but cannot catch the defocus discontinuities very well. In this paper, we propose a DME method combining edge-based and region-based methods together to keep their respective advantages while eliminating the shortcomings. The combination is achieved via regression tree fields (RTF). In an RTF, the input feature and the linear basis are of vital importance. For our RTF, they are obtained as follows. (i) Two orthogonal gradient operators with the corresponding subsets of Gabor filters are employed in localized 2D frequency analysis to generate accurate likelihood, and the first K highest local maximums of likelihood are sent to an RTF as input feature. (ii) At the same time, the input image is processed by three edge-based methods and the results serve as the linear basis of RTF. The experiments demonstrate that the proposed method outperforms state-of-the-art DME methods. Moreover, the proposed method can be readily applied to defocused image deblurring and defocus blur detection.

Efficient three-dimensional super-diffusive model for benign brain tumor segmentation

Brain is most complex and central part of the human body. Millions of cells are present in the brain. Brain tumor is extra unwanted cell in the human brain. It is mainly categorized into benign and malignant. Benign tumor cells have very similar characteristics with its surrounding cells. Its accurate detection and segmentation is very challenging task. Image segmentation methods have major contribution in detection and segmentation of these tumor cells. Segmentation methods are either boundary based or region based. These methods use traditional integral-order calculus. It has been observed that these approaches are unable to detect low variational region such as benign tumor. In the present manuscript, fractional diffusion-based benign brain tumor detection and segmentation method is being proposed. It has been observed that the proposed method is able to detect and segment benign brain tumor region more accurately. Higher accuracy has been obtained due to fractional-order derivative. Frequency domain derivative definition has been used in the proposed method due to simplicity and low computational cost. A hardware model of the proposed work has been also presented in the current manuscript. The results obtained have been compared with existing boundary-based and region-based tumor detection and segmentation methods. It has been found that the proposed method is having higher accuracy in benign brain tumor detection and segmentation with low computational cost.

Multiscale Image Matting Based Multi-Focus Image Fusion Technique

Multi-focus image fusion is a very essential method of obtaining an all focus image from multiple source images. The fused image eliminates the out of focus regions, and the resultant image contains sharp and focused regions. A novel multiscale image fusion system based on contrast enhancement, spatial gradient information and multiscale image matting is proposed to extract the focused region information from multiple source images. In the proposed image fusion approach, the multi-focus source images are firstly refined over an image enhancement algorithm so that the intensity distribution is enhanced for superior visualization. The edge detection method based on a spatial gradient is employed for obtaining the edge information from the contrast stretched images. This improved edge information is further utilized by a multiscale window technique to produce local and global activity maps. Furthermore, a trimap and decision maps are obtained based upon the information provided by these near and far focus activity maps. Finally, the fused image is achieved by using an enhanced decision maps and fusion rule. The proposed multiscale image matting (MSIM) makes full use of the spatial consistency and the correlation among source images and, therefore, obtains superior performance at object boundaries compared to region-based methods. The achievement of the proposed method is compared with some of the latest techniques by performing qualitative and quantitative evaluation.

Learning a robust CNN-based rotation insensitive model for ship detection in VHR remote sensing images

ABSTRACT Deep convolutional neural networks (CNN) have been widely applied in various fields, especially in the field of object detection. Deep CNN-based models showed great advantages over many traditional methods, even so, there are still many specific problems in the application of certain scenarios. In very high resolution (VHR) remote-sensing image datasets, the uncertainty of the object direction angle causes big trouble to the learning of the detector. Although the pooling operation can slightly alleviate the deviation caused by small angle, the feature learning of the objects with larger angle rotation still relies mainly on the sufficiency of sample data or effective data augmentation, which means the insufficiency of the training instances may cause serious performance degradation of the detector. In this paper, we propose a multi-angle box-based rotation insensitive object detection structure (MRI-CNN), which is an extended exploration for typical region-based CNN methods. On the one hand, we defined a set of directionally rotated bounding boxes before learning, and restricted the classification scene in a small angular range by rotated RoI (Region of Interest) pooling. On the other hand, we proposed a more effective screening method of bounding boxes, enabling the detector to adapt to diverse ground truth annotation methods and learn more accurate object localization. We trained our detector with different datasets containing different amount of training data, and the test results showed that the method proposed in this paper performs better than some mainstream detection methods when limited training data are provided in VHR remote-sensing datasets.

Occlusion-aware Region-based 3D Pose Tracking of Objects with Temporally Consistent Polar-based Local Partitioning.

Region-based methods have become the state-of-art solution for monocular 6-DOF object pose tracking in recent years. However, two main challenges still remain: the robustness to heterogeneous configurations (both foreground and background), and the robustness to partial occlusions. In this paper, we propose a novel region-based monocular 3D object pose tracking method to tackle these problems. Firstly, we design a new strategy to define local regions, which is simple yet efficient in constructing discriminative local color histograms. Contrary to previous methods which define multiple circular regions around the object contour, we propose to define multiple overlapped, fan-shaped regions according to polar coordinates. This local region partitioning strategy produces much less number of local regions that need to be maintained and updated, while still being temporally consistent. Secondly, we propose to detect occluded pixels using edge distance and color cues. The proposed occlusion detection strategy is seamlessly integrated into the region-based pose optimization pipeline via a pixel-wise weight function, which significantly alleviates the interferences caused by partial occlusions. We demonstrate the effectiveness of the proposed two new strategies with a careful ablation study. Furthermore, we compare the performance of our method with the most recent state-of-art region-based methods in a recently released large dataset, in which the proposed method achieves competitive results with a higher average tracking success rate. Evaluations on two real-world datasets also show that our method is capable of handling realistic tracking scenarios.

Review of 3D Point Cloud Data Segmentation Methods

Abstract 3D point cloud segmentation is one of the key steps in point cloud processing, which is the technology and process of dividing the point cloud data set into several specific regions with unique properties and proposing interesting targets. It has important applications in medical image processing, industrial inspection, cultural relic’s identification and 3D visualization. Despite widespread use, point cloud segmentation still faces many challenges because of uneven sampling density, high redundancy, and lack explicit structure of point cloud data. The main goal of this paper is to analyse the most popular algorithms and methodologies to segment point clouds. To facilitate analysis and summary, according to the principle of segmentation we divide the 3D point cloud segmentation methods into edge-based methods, region-based methods, graph-based methods, model-based methods, and machine learning-based methods. Then analyze and discuss the advantages, disadvantages and application scenarios of these segmentation methods. For some algorithms the results of the segmentation and classification is shown. Finally, we outline the issues that need to be addressed and important future research directions.

Trans-ethnic meta-analysis of rare variants in sequencing association studies.

Trans-ethnic meta-analysis is a powerful tool for detecting novel loci in genetic association studies. However, in the presence of heterogeneity among different populations, existing gene-/region-based rare variants meta-analysis methods may be unsatisfactory because they do not consider genetic similarity or dissimilarity among different populations. In response, we propose a score test under the modified random effects model for gene-/region-based rare variants associations. We adapt the kernel regression framework to construct the model and incorporate genetic similarities across populations into modeling the heterogeneity structure of the genetic effect coefficients. We use a resampling-based copula method to approximate asymptotic distribution of the test statistic, enabling efficient estimation of p-values. Simulation studies show that our proposed method controls type I error rates and increases power over existing approaches in the presence of heterogeneity. We illustrate our method by analyzing T2D-GENES consortium exome sequence data to explore rare variant associations with several traits.

DETECTOR QUASI-PERIODIC TEXTURE SEGMENTATION METHOD FOR DERMATOLOGICAL IMAGES PROCESSING

Currently,digital diagnosis systems that process medical images are widely used in the diagnosis processin the field of healthcare. The purpose of such systems is to assist the doctorin establishing the diagnosis, or in monitoring changes in the patient's condition during treatment. Dermatology is one of the areas of medicine where the number of visits to a doctoris high. At the same time, the tasks of establishing a diagnosis and monitoring changes in the patient's condition during treatment are time-consuming and subjective and they depend on knowledge and experience of a dermatologist. However, today, digital systems for the diagnosis of dermatological diseases are not in every locality, expensive and are stationary systems. With the development ofmobile information technologies, it became possible to develop mobile image processing systems for the analysis of dermatological diseases, which allow you to: receiving, analyze, and compareimages before and after treatment at anytime, anywhere.One of the basic procedures in image processing systems is segmentation, the purpose of which is to reduce the amount of processed data. Segmentation methods can be classified asboundary-based methods and region-based methods. Dermatological disease images consistof regions which have difference by texture, that is, the segmentation problem is considered as the task of selection homogeneous regions by texture. The result of image processing depends on the quality of segmentation. To improve the qualityof segmentation, in this work, we developed a detector quasi-periodic texture segmentation method for dermatological images processing,which contain quasi-periodic textures on a complex background in noisy conditions. This method is developed on the basis of the methodology of texture segmentation using detector, the stages of which are localization of spatial frequencies, detection, and contoursegmentation. To localize of spatial frequencies, a wavelet-function improved by transform of graph of power function was used, which increases the accuracy of determining the boundaries of quasi-periodic textures contained in dermatological disease images.On the detection step,the comb filters, which are wavelets with a periodic or quasi-periodic transfer function that are applied to each image line, wereused. The Canny method was use, as a contour preparation. Detectorsegmentation methods are focused on the image model. Therefore, a mathematical model of medical dermatological disease images was proposed, which contain quasi-periodic textures on a complex background in noisy conditions, as a model of a texture image with amplitude-modulated fluctuations in the intensity values by a random change in the amplitude and frequency of the oscillation. The developed method was applied to test medical images of psoriasis disease, which are available on the Internet. The accuracy of the segmentation of medical images of psoriasis disease containing a quasi-periodic texture was evaluated using the proposed method and the method using Gabor filters.It is shown that the proposed method is characterized by high speed and high segmentation quality, that is, it can be used in the development of express-diagnostic systems for monitoring changes in the patient's condition during treatment andto determine a parameter such as lesionsarea.

BMF-CNN: an object detection method based on multi-scale feature fusion in VHR remote sensing images

ABSTRACTObject detection in very-high-resolution (VHR) remote sensing images is one of the important technical means in many fields. In recent years, conventional object detection methods have been completely replaced by Convolutional Neural Network (CNN)-based methods, which are more accurate and efficient. However, most current CNN-based methods applied in VHR image sets have certain defects: (1) Scale preference is common in the framework designs, and the representation ability of feature maps for large and small objects is quite different, so accuracy promotion can hardly be made comprehensively in the detection of different objects. (2) The scale difference of the objects leads to training difficulties. (3) Some high-precision methods require high hardware costs, and the overall frameworks lack practicality. To address such problems, we propose a new object detection method in this paper, namely Balanced Multi-Scale Fusion-based CNN (BMF-CNN). It is a redesigned two-stage detection framework according to the region-based object detection methods, which enabled the detection accuracy of both large and small objects to reach a high level. Through the evaluation in the open VHR remote sensing image sets, we found that BMF-CNN showed a better integrative performance than the current mainstream detection methods.

PolSAR Image Classification via Learned Superpixels and QCNN Integrating Color Features

Polarimetric synthetic aperture radar (PolSAR) image classification plays an important role in various PolSAR image application. And many pixel-wise, region-based classification methods have been proposed for PolSAR images. However, most of the pixel-wise methods can not model local spatial relationship of pixels due to negative effects of speckle noise, and most of the region-based methods fail to figure out the regions with the similar polarimetric features. Considering that color features can provide good visual expression and perform well for image interpretation, in this work, based on the PolSAR pseudo-color image over Pauli decomposition, we propose a supervised PolSAR image classification approach combining learned superpixels and quaternion convolutional neural network (QCNN). First, the PolSAR RGB pseudo-color image is formed under Pauli decomposition. Second, we train QCNN with quaternion PolSAR data converted by RGB channels to extract deep color features and obtain pixel-wise classification map. QCNN treats color channels as a quaternion matrix excavating the relationship among the color channels effectively and avoiding information loss. Third, pixel affinity network (PAN) is utilized to generate the learned superpixels of PolSAR pseudo-color image. The learned superpixels allow the local information exploitation available in the presence of speckle noise. Finally, we fuse the pixel-wise classification result and superpixels to acquire the ultimate pixel-wise PolSAR image classification map. Experiments on three real PolSAR data sets show that the proposed approach can obtain 96.56%, 95.59%, and 92.55% accuracy for Flevoland, San Francisco and Oberpfaffenhofen data set, respectively. And compared with state-of-the-art PolSAR image classification methods, the proposed algorithm can obtained competitive classification results.

A novel local region-based active contour model for image segmentation using Bayes theorem

Local region-based active contour methods have been widely used to segment images with intensity inhomogeneity. However, this process can hardly segment images well when influenced by different noise. To simultaneously strengthen the anti-noise ability and preserve the distinction in segmenting images with intensity inhomogeneity, we propose characterizing image regions using local prior region descriptors under the Bayesian criterion for image segmentation. Based on the framework of Bayes theorem, a spatial regularization of connectivity maps based on a Markov random field (MRF) is introduced as the prior probability in our model. The connectivity maps enhance noise robustness by building a relationship between a pixel and its adjacent pixels. Additionally, the conditional probability of the image intensity in each local region is assumed to satisfy a Gaussian distribution with different means and deviations. Furthermore, to decrease time costs, we use the sparse field method (SFM) and compute the means and variances of the intensities in each local region before the evolution of the contour. Extensive experiments have demonstrated that the proposed method is superior to state-of-the-art active contour methods in terms of time efficiency and noise robustness.