Search

Based on the theory and application, this paper discusses the optimization of art image segmentation algorithm based on FFNN (Feed Forward Neural Network). In this paper, residual units are used in the corresponding stages of encoder and decoder, and feature information of several convolution layers in each convolution stage of encoder is extracted at the same time. And the feature pyramid module is used to extract multiscale features from the feature map of the last convolution stage in the encoder. Finally, pixel by pixel additions combine the previously mentioned feature information into the corresponding layer of the decoder. Additionally, an improved weight adaptive algorithm based on feature preservation is suggested in this paper, which addresses the issue that the conventional image segmentation algorithm is noise-sensitive. The adaptive connection weight mechanism is also introduced. The accuracy and recall rates of this optimization algorithm can both reach 96.574%, according to the results of 50% cross-validation. All the segmentation performance evaluation indexes of this algorithm are higher than the existing main algorithms. Moreover, the algorithm takes a short time, does not need too much manual intervention, and can effectively segment artistic images. The optimization algorithm in this paper has certain reference significance for the related research of artistic image segmentation. [ABSTRACT FROM AUTHOR]

In this paper, the most common pepper noise in grayscale image noise is investigated in depth in the median filtering algorithm, and the improved median filtering algorithm, adaptive switching median filtering algorithm, and adaptive polar median filtering algorithm are applied to the OTSU algorithm. Two improved OTSU algorithms such as the adaptive switched median filter-based OTSU algorithm and the polar adaptive median filter-based OTSU algorithm are obtained. The experimental results show that the algorithm can better cope with grayscale images contaminated by pretzel noise, and the segmented grayscale images are not only clear but also can better retain the detailed features of grayscale images. A genetic algorithm is a kind of search algorithm with high adaptive, fast operation speed, and good global space finding ability, and it will have a good effect when applied to the threshold finding of the OTSU algorithm. However, the traditional genetic algorithm will fall into the local optimal solution in different degrees when finding the optimal threshold. The advantages of the two interpolation methods proposed in this paper are that one is the edge grayscale image interpolation algorithm using OTSU threshold adaptive segmentation and the other is the edge grayscale image interpolation algorithm using local adaptive threshold segmentation, which can accurately divide the grayscale image region according to the characteristics of different grayscale images and effectively improve the loss of grayscale image edge detail information and jagged blur caused by the classical interpolation algorithm. The visual effect of grayscale images is enhanced by selecting grayscale images from the standard grayscale image test set and interpolating them with bilinear interpolation, bucolic interpolation, NEDI interpolation, and FEOI interpolation for interpolation simulation validation. The subjective evaluation and objective evaluation, as well as the running time, are compared, respectively, showing that the method of this paper can effectively improve the quality of grayscale image interpolation. [ABSTRACT FROM AUTHOR]

Aquila optimizer (AO) is an efficient meta-heuristic optimization method, which mimics the hunting style of Aquila in nature. However, the AO algorithm may suffer from immature convergence during the exploitation stage. In this paper, two strategies are elegantly employed into conventional AO, such as random opposition-based learning and nonlinear flexible jumping factor, which can efficiently enhance the performance of conventional AO. Experiments on 1 7 benchmark functions and image segmentation demonstrate the effectiveness of the proposed algorithm. Comparison with several state-of-the-art meta-heuristic optimization techniques indicates the efficacy of the developed method. [ABSTRACT FROM AUTHOR]

In view of the slow convergence speed of traditional particle swarm optimization algorithms, which makes it easy to fall into local optimum, this paper proposes an OTSU multi-threshold image segmentation based on an improved particle swarm optimization algorithm. After the particle swarm completes the iterative update speed and position, the method of calculating particle contribution degree is used to obtain the approximate position and direction, which reduces the scope of particle search. At the same time, the asynchronous monotone increasing social learning factor and the asynchronous monotone decreasing individual learning factor are used to balance global and local search. Finally, chaos optimization is introduced to increase the diversity of the population to achieve OTSU multi-threshold image segmentation based on improved particle swarm optimization (IPSO). Twelve benchmark functions are selected to test the performance of the algorithm and are compared with the traditional meta-heuristic algorithm. The results show the robustness and superiority of the algorithm. The standard dataset images are used for multi-threshold image segmentation experiments, and some traditional meta-heuristic algorithms are selected to compare the calculation efficiency, peak signal to noise ratio (PSNR), structural similarity (SSIM), feature similarity (FSIM), and fitness value (FITNESS). The results show that the running time of this paper is 30% faster than other algorithms in general, and the accuracy is also better than other algorithms. Experiments show that the proposed algorithm can achieve higher segmentation accuracy and efficiency. [ABSTRACT FROM AUTHOR]

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

This paper addresses the problem of semantic segmentation, where the possible class labels are from a predefined set. We exploit top-down guidance, i.e., the coarse localization of the objects and their class labels provided by object detectors. For each detected bounding box, figure–ground segmentation is performed and the final result is achieved by merging the figure–ground segmentations. The main idea of the proposed approach, which is presented in our preliminary work, is to reformulate the figure–ground segmentation problem as sparse reconstruction pursuing the object mask in a nonparametric manner. The latent segmentation mask should be coherent subject to sparse error caused by intra-category diversity; thus, the object mask is inferred by making use of sparse representations over the training set. To handle local spatial deformations, local patch-level masks are also considered and inferred by sparse representations over the spatially nearby patches. The sparse reconstruction coefficients and the latent mask are alternately optimized by applying the Lasso algorithm and the accelerated proximal gradient method. The proposed formulation results in a convex optimization problem; thus, the global optimal solution is achieved. In this paper, we provide theoretical analysis of the convergence and optimality. We also give an extended numerical analysis of the proposed algorithm and a comprehensive comparison with the related semantic segmentation methods on the challenging PASCAL visual object class object segmentation datasets and the Weizmann horse dataset. The experimental results demonstrate that the proposed algorithm achieves a competitive performance when compared with the state of the arts. [ABSTRACT FROM PUBLISHER]

To address the problem of segmenting an image into sizeable homogeneous regions, this paper proposes an efficient agglomerative algorithm on the basis of modularity optimization. Given an oversegmented image that consists of many small regions, our algorithm automatically merges those neighboring regions that produce the largest increase in modularity index. When the modularity of the segmented image is maximized, the algorithm stops merging and produces the final segmented image. To preserve the repetitive patterns in a homogeneous region, we propose a feature on the basis of the histogram of states of image gradients and use it together with the color feature to characterize the similarity of two regions. By constructing the similarity matrix in an adaptive manner, the oversegmentation problem can be effectively avoided. Our algorithm is tested on the publicly available Berkeley Segmentation Data Set as well as the semantic segmentation data set and compared with other popular algorithms. Experimental results have demonstrated that our algorithm produces sizable segmentation, preserves repetitive patterns with appealing time complexity, and achieves object-level segmentation to some extent. [ABSTRACT FROM AUTHOR]

Image segmentation is a very important activity in computer vision, where critical applications are highly dependent on the efficacy of such activity. To enhance the efficiency of such automated activity, meta-heuristic algorithms to optimally elucidate multi-level image segmentation problems have been proposed in the literature. Because of the advantages in terms of efficiency and convergence speed of the bat algorithm, this paper presents a novel improvement of such algorithm for solving the image multi-thresholding problem. The algorithm leads to speed up the convergence and increase diversity through the utilization of an appropriate crossover operator and chaotic sequences, with the use of Kapur's entropy as the optimized objective function. The proposed method produces segmented images with optimal values for the threshold in few iterations. Through the comparative analysis based on standard deviation, peak signal to noise ratio (PSNR) and segmented image quality, it is observed that the effectiveness of the proposed method, validated using different standard test images, outperforms well-known metaheuristic-based optimization techniques. [ABSTRACT FROM AUTHOR]

within constraint satisfaction problems (CSPs), in this paper we introduce a honeybee algorithm that uses new template concept for image segmentation. Our approach uses the guided local search and the graph theory to achieve an improved image segmentation. Compared to previous well known heuristics, our approach is giving better experimental results. [ABSTRACT FROM AUTHOR]

One of the most crucial aspects of image segmentation is multilevel thresholding. However, multilevel thresholding becomes increasingly more computationally complex as the number of thresholds grows. In order to address this defect, this paper proposes a new multilevel thresholding approach based on the Evolutionary Arithmetic Optimization Algorithm (AOA). The arithmetic operators in science were the inspiration for AOA. DAOA is the proposed approach, which employs the Differential Evolution technique to enhance the AOA local research. The proposed algorithm is applied to the multilevel thresholding problem, using Kapur's measure between class variance functions. The suggested DAOA is used to evaluate images, using eight standard test images from two different groups: nature and CT COVID-19 images. Peak signal-to-noise ratio (PSNR) and structural similarity index test (SSIM) are standard evaluation measures used to determine the accuracy of segmented images. The proposed DAOA method's efficiency is evaluated and compared to other multilevel thresholding methods. The findings are presented with a number of different threshold values (i.e., 2, 3, 4, 5, and 6). According to the experimental results, the proposed DAOA process is better and produces higher-quality solutions than other comparative approaches. Moreover, it achieved better-segmented images, PSNR, and SSIM values. In addition, the proposed DAOA is ranked the first method in all test cases. [ABSTRACT FROM AUTHOR]

Despite its simplicity and high accuracy, the real-time efficiency of OTSU segmentation is not high. In order to promote the real-timeliness of image segmentation, this paper introduces the fruitfly optimization algorithm (FOA) to OTSU segmentation, creating an FOA-OTSU segmentation algorithm. In the proposed algorithm, the optimal threshold for segmentation is searched for by the FOA. The classic Lena picture, Flower picture and Cameraman picture were used for simulation experiment, and the results were evaluated by signal-to-noise ratio (SNR) and peak signal-to-noise ratio (PSNR). The results show that the segmentation time is reduced by about 50.0% on the premise of the PSNR and SNR evaluation criteria and the segmentation effect basically unchanged. The simulations indicate that our method converges faster and consumes fewer time than traditional OTSU algorithm, without sacrificing the segmentation accuracy. The research provides a desirable tool with high real-time performance of rapid image segmentation. [ABSTRACT FROM AUTHOR]

Endovascular coiling is a primary treatment for intra-cranial aneurysm, which deploys a thin and detachable metal wire inside the aneurysm so as to prevent its rupture. Emerging evidence from medical research and clinical practice has suggested that the coil configuration inside the aneurysm plays a vital role in properly treating aneurysm and predicting its outcome. In this paper, we propose a novel virtual coiling technique, called Ball Winding , for generating a coil configuration with ensured blocking ability. It can be used as an automatic tool for virtually simulating coiling before its implantation and thus optimizes such treatments. Our approach is based on integer linear programming and computational geometry techniques, and takes into consideration the packing density and coil distribution as the performance measurements. The resulting coiling is deployable (with the help of coil pre-shaping) and with minimized energy. Experimental results on both random and real aneurysm data suggest that our proposed method yields near optimal solution. [ABSTRACT FROM AUTHOR]

This paper presents an enhanced Harris Hawks Optimizer (HHO) to tackle global optimization and determine the optimal threshold values for multi-level image segmentation problems. HHO is a new swarm-based metaheuristic technique that simulates the behaviors of Harris hawks during the process of catching the rabbits. The HHO established its strong performance as a swarm-based optimization technique. However, population-based HHO still may face some limitations in dealing with more multi-modal and composition problems. For example, this optimizer may be stagnated to local optima and turned to immature convergence when performing phases of exploration and exploitation. To mitigate these drawbacks, an improved HHO is proposed that considers the salp swarm algorithm (SSA) as a competitive method to enhance the balance between its exploration and exploitation trends. Firstly, a set of solutions is generated. Then, we divide those solutions into two halves, where the exploratory and exploitative phases of HHO will be applied to the first half, and the searching stages of SSA will be used to update the solutions in the second half. Thereafter, the best solutions from the union sub-populations are selected to continue the iterative process. According to the improved HHO, which is called HHOSSA, an effective multi-level image segmentation approach is also developed in this research. A comprehensive set of experiments are performed using 36 IEEE CEC 2005 benchmark functions and 11 natural gray-scale images. Extensive results and comparisons show the high ability of the SSA to improve the HHO's performance since the proposed HHOSSA achieves a more stable performance compared to HHO, SSA, and many other well-known methods. • This paper presents an enhanced Harris Hawks Optimizer (HHO). • A comprehensive experiment is performed using more than forty five benchmark problems. • Extensive results show the more stable performance of the proposed variant of HHO. [ABSTRACT FROM AUTHOR]

Intelligent optimization algorithms are widely utilized to deal with complex optimization problems in various areas. However, a single intelligent optimization algorithm cannot handle well more and more complex optimization problems. The ensemble strategy can integrate several different operators and algorithms by using some appropriate strategies and maybe obtain better optimization performance. In this paper, a new ensemble multi-swarm method based on teaching–learning-based optimization (EMTLBO) was proposed by integrating three different algorithms including the original teaching–learning-based optimization algorithm, its variant with neighborhood search and the variant with differential evolution. In EMTLBO, a new evaluating mechanism based on the fitness-based and diversity-based metrics (FDEM) for each sub-swarm was proposed to evaluate the optimization performance after a continuous generation interval. Moreover, an algorithm matching mechanism based on ranking for sub-swarms (AMM) is adapted to re-divide the population into three sub-swarms and match a suitable algorithm for each sub-swarm so as to increase the whole optimization performance. Furthermore, the experimental results on CEC2014 and CEC2017 test suits verify the feasibility and optimization performance of EMTLBO. Finally, the proposed algorithm is extended to optimize the segmentation thresholds of images and the segmentation performances on different benchmark images show that EMTLBO has good performance in most cases. • A new evaluating mechanism was proposed to evaluate the optimization performance. • Algorithm matching mechanism is adopted to match a suitable algorithm for each sub-swarm. • The experimental results on CEC2014 and CEC2017 test suits verify EMTLBO. • The proposed EMTLBO algorithm is extended to deal with image segmentation problems. [ABSTRACT FROM AUTHOR]

The fuzzy 2-partition entropy approach has been widely used to select threshold value for image segmenting. This approach used two parameterized fuzzy membership functions to form a fuzzy 2-partition of the image. The optimal threshold is selected by searching an optimal combination of parameters of the membership functions such that the entropy of fuzzy 2-partition is maximized. In this paper, a new fuzzy 2-partition entropy thresholding approach based on the technology of the Big Bang–Big Crunch Optimization (BBBCO) is proposed. The new proposed thresholding approach is called the BBBCO-based fuzzy 2-partition entropy thresholding algorithm. BBBCO is used to search an optimal combination of parameters of the membership functions for maximizing the entropy of fuzzy 2-partition. BBBCO is inspired by the theory of the evolution of the universe; namely the Big Bang and Big Crunch Theory. The proposed algorithm is tested on a number of standard test images. For comparison, three different algorithms included Genetic Algorithm (GA)-based, Biogeography-based Optimization (BBO)-based and recursive approaches are also implemented. From experimental results, it is observed that the performance of the proposed algorithm is more effective than GA-based, BBO-based and recursion-based approaches. [ABSTRACT FROM AUTHOR]

Traditional methods to address color image segmentation work efficiently for bi-level thresholding. However, for multi-level thresholding, traditional methods suffer from time complexity that increases exponentially with the increasing number of threshold levels. To overcome this problem, in this paper, a new approach is proposed to tackle multi-threshold color image segmentation by employing the Otsu method as an objective function. This approach is based on a hybrid of the whale optimization algorithm (WOA) with a novel method called the local minima avoidance method (LMAM), abbreviated as HWOA. LMAM avoids local minima by updating the whale either within the search space of the problem or between two whales selected randomly from the population-based on a certain probability. HWOA is validated on ten color images taken from the Berkeley University Dataset by measuring the objective values, peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), features similarity index (FSIM), and CPU time, and compared with a number of the well-known robust meta-heuristic algorithms: the sine–cosine algorithm (SCA), WOA, modified salp swarm algorithm (MSSA), improved marine predators algorithm (IMPA), modified Cuckoo Search (CS) using McCulloch's algorithm (CSMC), and equilibrium optimizer (EO). The experimental results show that HWOA is superior to all the other algorithms in terms of PSNR, FSIM, and objective values, and is competitive in terms of SSIM. • Developing a novel method, called the local minima elimination method (LMAM). • Proposing a new color image segmentation model based on a hybrid of WOA with LMAM. • The proposed approach is applied to ten color test images. • The proposed approach is compared with a number of robust well-known algorithms. [ABSTRACT FROM AUTHOR]

Grey wolf optimizer (GWO) is a widespread metaphor-based algorithm based on the enhanced variants of velocity-free particle swarm optimizer with proven defects and shortcomings in performance. Regardless of the proven defect and lack of novelty in this algorithm, the GWO has a simple algorithm and it may face considerable unbalanced exploration and exploitation trends. However, GWO is easy to be utilized, and it has a low capacity to deal with multi-modal functions, and it quickly falls into the optima trap or fails to find the global optimal solution. To improve the shortcomings of the basic GWO, this paper proposes an improved GWO called multi-stage grey wolf optimizer (MGWO). By dividing the search process into three stages and using different population updating strategies at each stage, the MGWO's optimization ability is improved while maintaining a certain convergence speed. The MGWO cannot easily fall into premature convergence and has a better ability to get rid of the local optima trap than GWO. Meanwhile, the MGWO achieves a better balance of exploration and exploitation and has a rough balance curve. Hence, the proposed MGWO can obtain a higher-quality solution. Based on verification on the thirty benchmark functions of IEEE CEC2017 as the objective functions, the simulation experiments in which MGWO compared with some swarm-based optimization algorithms and the balance and diversity analysis were conducted. The results verify the effectiveness and superiority of MGWO. Finally, the MGWO was applied to the multi-threshold image segmentation of Leaf Spot Diseases on Maize at four different threshold levels. The segmentation results were analysed by comparing each comparative algorithm's PSNR, SSIM, and FSIM. The results proved that the MGWO has noticeable competitiveness, and it can be used as an effective optimizer for multi-threshold image segmentation. • An improved multi-stage grey wolf optimizer (MGWO) is proposed. • The multi-stage strategy is used to balance exploration and exploitation. • A part of salp swarm algorithm strategy is introduced into GWO. • The greater performance of MGWO is verified over some advanced algorithms. • MGWO is tested on multi-threshold image segmentation of Leaf Spot Diseases on Maize. [ABSTRACT FROM AUTHOR]

With the popularity of cameras and sensors, massive data are captured from various view angles or modalities, which provide abundant complementary information and also bring great challenges for traditional clustering methods. In this article, we propose a novel Adaptive K-Multiple-Means for multi-view clustering method (AKM3C). Unlike traditional multi-view K-means methods by grouping samples into $C$ clusters each with a cluster center in every view, the proposed AKM3C employs $M (M>C)$ sub-cluster centers in each view to reveal the sub-cluster structure in the multi-view data thus enhances the clustering performance. Additionally, to distinguish the importance of different views, instead of using empirical weights, AKM3C exploits the multi-view combination weights strategy to assign a weight to each view automatically and thus fuses the complementary information of different views properly to get an optimally shared bipartite graph, on which the Laplacian rank constraint is executed and the final clusters are obtained by directly partitioning. An efficient optimization algorithm proposed with complexity and convergence analysis is used to solve the proposed AKM3C method. The extensive experimental results on eight public datasets show that the proposed AKM3C performs better than state-of-the-art multi-view clustering methods. The code can be downloaded at https://drive.google.com/file/d/1CQ0royrYxKFJdNLnbBQSbDrohtfH71di/view?usp=sharing. [ABSTRACT FROM AUTHOR]

Recently, a novel virus called COVID-19 has pervasive worldwide, starting from China and moving to all the world to eliminate a lot of persons. Many attempts have been experimented to identify the infection with COVID-19. The X-ray images were one of the attempts to detect the influence of COVID-19 on the infected persons from involving those experiments. According to the X-ray analysis, bilateral pulmonary parenchymal ground-glass and consolidative pulmonary opacities can be caused by COVID-19 — sometimes with a rounded morphology and a peripheral lung distribution. But unfortunately, the specification or if the person infected with COVID-19 or not is so hard under the X-ray images. X-ray images could be classified using the machine learning techniques to specify if the person infected severely, mild, or not infected. To improve the classification accuracy of the machine learning, the region of interest within the image that contains the features of COVID-19 must be extracted. This problem is called the image segmentation problem (ISP). Many techniques have been proposed to overcome ISP. The most commonly used technique due to its simplicity, speed, and accuracy are threshold-based segmentation. This paper proposes a new hybrid approach based on the thresholding technique to overcome ISP for COVID-19 chest X-ray images by integrating a novel meta-heuristic algorithm known as a slime mold algorithm (SMA) with the whale optimization algorithm to maximize the Kapur's entropy. The performance of integrated SMA has been evaluated on 12 chest X-ray images with threshold levels up to 30 and compared with five algorithms: Lshade algorithm, whale optimization algorithm (WOA), FireFly algorithm (FFA), Harris-hawks algorithm (HHA), salp swarm algorithms (SSA), and the standard SMA. The experimental results demonstrate that the proposed algorithm outperforms SMA under Kapur's entropy for all the metrics used and the standard SMA could perform better than the other algorithms in the comparison under all the metrics. • We proposes a new hybrid approach based on the thresholding technique to overcome the image segmentation problem. • We developed an integrated slime mold algorithm (SMA) with the whale optimization algorithm to maximize the Kapur's entropy. • ISMA has been evaluated on 12 chest X-ray images with threshold levels up to 30 and compared with five algorithms. • The experimental results demonstrate that our proposed algorithm outperforms SMA under Kapur's entropy. • Our algorithm could outperform all other algorithms in the fitness values, SSIM, PSNR, UQI, CPU time and (Std). [ABSTRACT FROM AUTHOR]

The fuzzy local information C-means clustering algorithm (FLICM) is an important robust fuzzy clustering segmentation method, which has attracted considerable attention over the years. However, it lacks certain robustness to high noise or severe outliers. To improve the accuracy and robustness of the FLICM algorithm for images corrupted by high noise, a novel fuzzy local information c-means clustering utilizing total Bregman divergence (TFLICM) is proposed in this paper. The total Bregman divergence is modified by the local neighborhood information of sample to further enhance the ability to suppress noise, and then modified total Bregman divergence is introduced into the FLICM to construct a new objective function of robust fuzzy clustering, and the iterative clustering algorithm with high robustness is obtained through optimization theory. The convergence of the TFLICM algorithm is proved by the Zangwill theorem. In addition, the validity of the TFLICM algorithm applied in noise image segmentation is explained by means of sample weighting fuzzy clustering. Meanwhile, the generalized total Bregman divergence unifies the Bregman divergence with the total Bregman divergence and enhances the universality of the TFLICM algorithm applied in segmenting complex medical and remote sensing images. Some experimental results show that the TFLICM algorithm can obtain better segmentation quality and stronger anti-noise robustness than the existing FLICM algorithm. • Total Bregman divergence applied in fuzzy clustering is improved. • The improved total Bregman divergence is introduced in robust FLICM algorithm. • An explanation of TFLICM is given by means of sample weighting clustering. • Generalized total Bregman divergence is proposed to enhance clustering performance. [ABSTRACT FROM AUTHOR]

Selective segmentation methods involve incorporating user input to partition an image into a foreground and background. These methods are often sensitive to some aspect of the user input in a counter intuitive manner, making their use in practice difficult. The most robust methods often involve laborious refinement on the part of the user, and sometimes editing/supervision. The proposed method reduces the burden of the user by simplifying the requirements in the input. Specifically, the fitting term does not depend on a distance function, and so no selection parameter is introduced. Instead, we consider how the user input relates to some general intensity fitting term to ensure the approach is less sensitive to the decisions or intuition of the user. We give comparisons to existing approaches to show the advantages of the new selective segmentation model. [ABSTRACT FROM AUTHOR]

Aiming to address dense small object tracking, we propose an image-to-trajectory framework including tracking and detection, where Track-Oriented Multiple Hypothesis Tracking(TOMHT) is revised for tracking. Unlike common cases of multi-object tracking, merged detections and the greater number of objects make dense small object tracking a more challenging problem. Firstly, we handle frequent merged detections through the aspects of detection and hypothesis selection. To tackle merged detection, we revise Local Contrast Method(LCM) and propose a multi-appearance variant, which exploits tree-like topological information and realizes one threshold for one object. Meanwhile, one-to-many constraint is employed via the proposed extended 0-1 programming, which enables hypothesis selection to handle track exclusions caused by merged detections. Secondly, to alleviate the high complexity caused by dense objects, we consider batch optimization and more rigorous and precise pruning technologies. Specifically, we propose autocorrelation based motion score test and two-stage hypotheses pruning. Experimental results are presented to verify the strength of our methods, which indicates speed and performance advantages of our tracker. [ABSTRACT FROM AUTHOR]

Most multi-object tracking algorithms are developed within the tracking-by-detection framework that consider the pairwise appearance similarities between detection responses or tracklets within a limited temporal window, and thus less effective in handling long-term occlusions or distinguishing spatially close targets with similar appearance in crowded scenes. In this work, we propose an algorithm that formulates the multi-object tracking task as one to exploit hierarchical dense structures on an undirected hypergraph constructed based on tracklet affinity. The dense structures indicate a group of vertices that are inter-connected with a set of hyperedges with high affinity values. The appearance and motion similarities among multiple tracklets across the spatio-temporal domain are considered globally by exploiting high-order similarities rather than pairwise ones, thereby facilitating distinguish spatially close targets with similar appearance. In addition, the hierarchical design of the optimization process helps the proposed tracking algorithm handle long-term occlusions robustly. Extensive experiments on various challenging datasets of both multi-pedestrian and multi-face tracking tasks, demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

We present efficient graph cut algorithms for three problems: (1) finding a region in an image, so that the histogram (or distribution) of an image feature within the region most closely matches a given model; (2) co-segmentation of image pairs and (3) interactive image segmentation with a user-provided bounding box. Each algorithm seeks the optimum of a global cost function based on the Bhattacharyya measure, a convenient alternative to other matching measures such as the Kullback–Leibler divergence. Our functionals are not directly amenable to graph cut optimization as they contain non-linear functions of fractional terms, which make the ensuing optimization problems challenging. We first derive a family of parametric bounds of the Bhattacharyya measure by introducing an auxiliary labeling. Then, we show that these bounds are auxiliary functions of the Bhattacharyya measure, a result which allows us to solve each problem efficiently via graph cuts. We show that the proposed optimization procedures converge within very few graph cut iterations. Comprehensive and various experiments, including quantitative and comparative evaluations over two databases, demonstrate the advantages of the proposed algorithms over related works in regard to optimality, computational load, accuracy and flexibility. [ABSTRACT FROM AUTHOR]

Ultrasound segmentation is a challenging problem due to the inherent speckle and some artifacts like shadows, attenuation and signal dropout. Existing methods need to include strong priors like shape priors or analytical intensity models to succeed in the segmentation. However, such priors tend to limit these methods to a specific target or imaging settings, and they are not always applicable to pathological cases. This work introduces a semi-supervised segmentation framework for ultrasound imaging that alleviates the limitation of fully automatic segmentation, that is, it is applicable to any kind of target and imaging settings. Our methodology uses a graph of image patches to represent the ultrasound image and user-assisted initialization with labels, which acts as soft priors. The segmentation problem is formulated as a continuous minimum cut problem and solved with an efficient optimization algorithm. We validate our segmentation framework on clinical ultrasound imaging (prostate, fetus, and tumors of the liver and eye). We obtain high similarity agreement with the ground truth provided by medical expert delineations in all applications (94% DICE values in average) and the proposed algorithm performs favorably with the literature. [ABSTRACT FROM AUTHOR]