Interactive image segmentation via kernel propagation

In this paper, we propose a new approach to interactive image segmentation via kernel propagation (KP), called KP Cut. The key to success in interactive image segmentation is to preserve characteristics of the user?s interactive input and maintain data-coherence effectively. To achieve this, we employ KP which is very effective in propagating the given supervised information into the entire data set. KP first learns a small-size seed-kernel matrix, and then propagates it into a large-size full-kernel matrix. It is based on a learned kernel, and thus can fit the given data better than a predefined kernel. Based on KP, we first generate a small-size seed-kernel matrix from the user?s interactive input. Then, the seed-kernel matrix is propagated into the full-kernel matrix of the entire image. During the propagation, foreground objects are effectively segmented from background. Experimental results demonstrate that KP Cut effectively extracts foreground objects from background, and outperforms the state-of-the-art methods for interactive image segmentation.     

Interactive image segmentation using probabilistic hypergraphs

This paper introduces a novel interactive framework for segmenting images using probabilistic hypergraphs which model the spatial and appearance relations among image pixels. The probabilistic hypergraph provides us a means to pose image segmentation as a machine learning problem. In particular, we assume that a small set of pixels, which are referred to as seed pixels, are labeled as the object and background. The seed pixels are used to estimate the labels of the unlabeled pixels by learning on a hypergraph via minimizing a quadratic smoothness term formed by a hypergraph Laplacian matrix subject to the known label constraints. We derive a natural probabilistic interpretation of this smoothness term, and provide a detailed discussion on the relation of our method to other hypergraph and graph based learning methods. We also present a front-to-end image segmentation system based on the proposed method, which is shown to achieve promising quantitative and qualitative results on the commonly used GrabCut dataset.     

Two-stage nonparametric kernel leaning: From label propagation to kernel propagation

We introduce a kernel learning algorithm, called kernel propagation (KP), to learn a nonparametric kernel from a mixture of a few pairwise constraints and plentiful unlabeled samples. Specifically, KP consists of two stages: the first is to learn a small-sized sub-kernel matrix just restricted to the samples with constrains, and the second is to propagate this learned sub-kernel matrix into a large-sized full-kernel matrix over all samples. As an interesting fact, our approach exposes a natural connection between KP and label propagation (LP), that is, one LP can naturally induce its KP counterpart. Thus, we develop three KPs from the three typical LPs correspondingly. Following the idea in KP, we also naturally develop an out-of-sample extension to directly capture a kernel matrix for outside-training data without the need of relearning. The final experiments verify that our developments are more efficient, more error-tolerant and also comparably effective in comparison with the state-of-the-art algorithm.     

Automating image segmentation verification and validation by learning test oracles

An image segmentation algorithm delineates (an) object(s) of interest in an image. Its output is referred to as a segmentation. Developing these algorithms is a manual, iterative process involving repetitive verification and validation tasks. This process is time-consuming and depends on the availability of experts, who may be a scarce resource (e.g., medical experts). We propose a framework referred to as Image Segmentation Automated Oracle (ISAO) that uses machine learning to construct an oracle, which can then be used to automatically verify the correctness of image segmentations, thus saving substantial resources and making the image segmentation verification and validation task significantly more efficient. The framework also gives informative feedback to the developer as the segmentation algorithm evolves and provides a systematic means of testing different parametric configurations of the algorithm. During the initial learning phase, segmentations from the first few (optimally two) versions of the segmentation algorithm are manually verified by experts. The similarity of successive segmentations of the same images is also measured in various ways. This information is then fed to a machine learning algorithm to construct a classifier that distinguishes between consistent and inconsistent segmentation pairs (as determined by an expert) based on the values of the similarity measures associated with each segmentation pair. Once the accuracy of the classifier is deemed satisfactory to support a consistency determination, the classifier is then used to determine whether the segmentations that are produced by subsequent versions of the algorithm under test, are (in)consistent with already verified segmentations from previous versions. This information is then used to automatically draw conclusions about the correctness of the segmentations. We have successfully applied this approach to 3D segmentations of the cardiac left ventricle obtained from CT scans and have obtained promising results (accuracies of 95%). Even though more experiments are needed to quantify the effectiveness of the approach in real-world applications, ISAO shows promise in increasing the quality and testing efficiency of image segmentation algorithms.     

Image segmentation based on multi-scan constraint satisfaction neural network

A novel image segmentation method based on a constraint satisfaction neural network (CSNN) is presented. The new method uses CSNN-based relaxation but with a modified scanning scheme of the image. The pixels are visited with more distant intervals and wider neighborhoods in the first level of the algorithm. The intervals between pixels and their neighborhoods are reduced in the following stages of the algorithm. This method contributes to the formation of more regular segments rapidly and consistently. A cluster validity index to determine the number of segments is also added to complete the proposed method into a fully automatic unsupervised segmentation scheme. The results are compared quantitatively by means of a novel segmentation evaluation criterion. The results are promising.     

Automatic data clustering using continuous action-set learning automata and its application in segmentation of images

Most of the proposed algorithms to solve the dynamic clustering problem are based on nature inspired meta-heuristic algorithms. In this paper a different reinforcement based optimization approach called continuous action-set learning automata (CALA) is used and a novel dynamic clustering approach called ACCALA is proposed. CALA is an optimization tool interacting with a random environment and learn the optimal action from the environment feedbacks. In this paper the dynamic clustering problem considered as a noisy optimization problem and the team of CALAs is used to solve this noisy optimization problem. To build such a team of CALAs this paper proposed a new representation of CALAs. Each automaton in this team uses its continuous action-set and defining a suitable action-set for each automaton has a great impact on the CALAs search behavior. In this paper we used the statistical property of data-sets and proposed a new method to automatically find an action-set for each automaton. The performance of ACCALA is evaluated and the results are compared with seven well-known automatic clustering techniques. Also ACCALA is used to perform automatic segmentation. The experimental results are promising and show that the proposed algorithm produced compact and well-separated clusters.     

Column subset selection for active learning in image classification

Image classification is an important task in computer vision and machine learning. However, it is known that manually labeling images is time-consuming and expensive, but the unlabeled images are easily available. Active learning is a mechanism which tries to determine which unlabeled data points would be the most informative (i.e., improve the classifier the most) if they are labeled and used as training samples. In this paper, we introduce the idea of column subset selection, which aims to select the most representation columns from a data matrix, into active learning and propose a novel active learning algorithm, column subset selection for active learning (CSS_active). CSS_active selects the most representative images to label, then the other images are reconstructed by these labeled images. The goal of CSS_active is to minimize the reconstruction error. Besides, most of the previous active learning approaches are based on linear model, and hence they only consider linear functions. Therefore, they fail to discover the intrinsic geometry in images when the image space is highly nonlinear. Therefore, we provide a kernel-based column subset selection for active learning (KCSS_active) algorithm which performs the active learning in Reproducing Kernel Hilbert Space (RKHS) instead of the original image space to address this problem. Experimental results on Yale, AT&T and COIL20 data sets demonstrate the effectiveness of our proposed approaches.     

Leukocyte image segmentation using simulated visual attention

Computer-aided automatic analysis of microscopic leukocyte is a powerful diagnostic tool in biomedical fields which could reduce the effects of human error, improve the diagnosis accuracy, save manpower and time. However, it is a challenging to segment entire leukocyte populations due to the changing features extracted in the leukocyte image, and this task remains an unsolved issue in blood cell image segmentation. This paper presents an efficient strategy to construct a segmentation model for any leukocyte image using simulated visual attention via learning by on-line sampling. In the sampling stage, two types of visual attention, “bottom-up” and “top-down” together with the movement of the human eye are simulated. We focus on a few regions of interesting and sample high gradient pixels to group training sets. While in the learning stage, the SVM (support vector machine) model is trained in real-time to simulate the visual neuronal system and then classifies pixels and extracts leukocytes from the image. Experimental results show that the proposed method has better performance compared to the marker controlled watershed algorithms with manual intervention and thresholding-based methods.     

A fast segmentation method based on constraint optimization and its applications: Intensity inhomogeneity and texture segmentation

We propose a new constraint optimization energy and an iteration scheme for image segmentation which is connected to edge-weighted centroidal Voronoi tessellation (EWCVT). We show that the characteristic functions of the edge-weighted Voronoi regions are the minimizers (may not unique) of the proposed energy at each iteration. We propose a narrow banding algorithm to accelerate the implementation, which makes the proposed method very fast. We generalize the CVT segmentation to hand intensity inhomogeneous and texture segmentation by incorporating the global and local image information into the energy functional. Compared with other approaches such as level set method, the experimental results in this paper have shown that our approach greatly improves the calculation efficiency without losing segmentation accuracy.     

Scale selection for supervised image segmentation

Finding the right scales for feature extraction is crucial for supervised image segmentation based on pixel classification. There are many scale selection methods in the literature; among them the one proposed by Lindeberg is widely used for image structures such as blobs, edges and ridges. Those schemes are usually unsupervised, as they do not take into account the actual segmentation problem at hand. In this paper, we consider the problem of selecting scales, which aims at an optimal discrimination between user-defined classes in the segmentation. We show the deficiency of the classical unsupervised scale selection paradigms and present a supervised alternative. In particular, the so-called max rule is proposed, which selects a scale for each pixel to have the largest confidence in the classification across the scales. In interpreting the classifier as a complex image filter, we can relate our approach back to Lindeberg's original proposal. In the experiments, the max rule is applied to artificial and real-world image segmentation tasks, which is shown to choose the right scales for different problems and lead to better segmentation results.     

一种基于信任传播的混凝土CT图像分割方法*

提出一种信任传播(belief propagation)算法,对混凝土CT图像进行分割处理。从分割结果看,该方法能够完整地反映出混凝土材料的内部结构和缺陷,并且与模拟退火算法ICM、Metropolis和Gibbs采样法分割结果图进行了比较,结果表明,信任传播算法在图像分割效率和分割精度上都有明显的提高。该分析方法为混凝土应力分析提供了一种重要的辅助手段,具有重要的应用意义。     

Efficient surface defect detection using self-supervised learning strategy and segmentation network

Surface defect detection plays a crucial role in the production process to ensure product quality. With the development of Industry 4.0 and smart manufacturing, traditional manual defect detection becomes no longer satisfactory, and deep learning-based technologies are gradually applied to surface defect detection tasks. However, the application of deep learning-based defect detection methods in actual production lines is often constrained by insufficient data, expensive annotations, and limited computing resources. Detection methods are expected to require fewer annotations as well as smaller computational consumption. In this paper, we propose the Self-Supervised Efficient Defect Detector (SEDD), a high-efficiency defect defector based on self-supervised learning strategy and image segmentation. The self-supervised learning strategy with homographic enhancement is employed to ensure that defective samples with annotations are no longer needed in our pipeline, while competitive performance can still be achieved. Based on this strategy, a new surface defect simulation dataset generation method is proposed to solve the problem of insufficient training data. Also, a lightweight structure with the attention module is designed to reduce the computation cost without incurring accuracy. Furthermore, a multi-task auxiliary strategy is employed to reduce segmentation errors of edges. The proposed model has been evaluated with three typical datasets and achieves competitive performance compared with other tested methods, with 98.40% AUC and 74.84% AP on average. Experimental results show that our network has the smallest computational consumption and the highest running speed among the networks tested.     

Bagging Constraint Score for feature selection with pairwise constraints

Constraint Score is a recently proposed method for feature selection by using pairwise constraints which specify whether a pair of instances belongs to the same class or not. It has been shown that the Constraint Score, with only a small amount of pairwise constraints, achieves comparable performance to those fully supervised feature selection methods such as Fisher Score. However, one major disadvantage of the Constraint Score is that its performance is dependent on a good selection on the composition and cardinality of constraint set, which is very challenging in practice. In this work, we address the problem by importing Bagging into Constraint Score and a new method called Bagging Constraint Score (BCS) is proposed. Instead of seeking one appropriate constraint set for single Constraint Score, in BCS we perform multiple Constraint Score, each of which uses a bootstrapped subset of original given constraint set. Diversity analysis on individuals of ensemble shows that resampling pairwise constraints is helpful for simultaneously improving accuracy and diversity of individuals. We conduct extensive experiments on a series of high-dimensional datasets from UCI repository and gene databases, and the experimental results validate the effectiveness of the proposed method.     

Multiphase image segmentation using a phase-field model

In this paper, we propose a new, fast, and stable hybrid numerical method for multiphase image segmentation using a phase-field model. The proposed model is based on the Allen-Cahn equation with a multiple well potential and a data-fitting term. The model is computationally superior to the previous multiphase image segmentation via Modica-Mortola phase transition and a fitting term. We split its numerical solution algorithm into linear and a nonlinear equations. The linear equation is discretized using an implicit scheme and the resulting discrete system of equations is solved by a fast numerical method such as a multigrid method. The nonlinear equation is solved analytically due to the availability of a closed-form solution. We also propose an initialization algorithm based on the target objects for the fast image segmentation. Finally, various numerical experiments on real and synthetic images with noises are presented to demonstrate the efficiency and robustness of the proposed model and the numerical method.     

Novel fuzzy active contour model with kernel metric for image segmentation

In this paper, a novel region-based fuzzy active contour model with kernel metric is proposed for a robust and stable image segmentation. This model can detect the boundaries precisely and work well with images in the presence of noise, outliers and low contrast. It segments an image into two regions – the object and the background by the minimization of a predefined energy function. Due to the kernel metric incorporated in the energy and the fuzziness of the energy, the active contour evolves very stably without the reinitialization for the level set function during the evolution. Here the fuzziness provides the model with a strong ability to reject local minima and the kernel metric is employed to construct a nonlinear version of energy function based on a level set framework. This new fuzzy and nonlinear version of energy function makes the updating of region centers more robust against the noise and outliers in an image. Theoretical analysis and experimental results show that the proposed model achieves a much better balance between accuracy and efficiency compared with other active contour models.     

Multispectral image compression using eigenregion-based segmentation

In the study, a novel segmentation technique is proposed for multispectral satellite image compression. A segmentation decision rule composed of the principal eigenvectors of the image correlation matrix is derived to determine the similarity of image characteristics of two image blocks. Based on the decision rule, we develop an eigenregion-based segmentation technique. The proposed segmentation technique can divide the original image into some proper eigenregions according to their local terrain characteristics. To achieve better compression efficiency, each eigenregion image is then compressed by an efficient compression algorithm eigenregion-based eigensubspace transform (ER-EST). The ER-EST contains 1D eigensubspace transform (EST) and 2D-DCT to decorrelate the data in spectral and spatial domains. Before performing EST, the dimension of transformation matrix of EST is estimated by an information criterion. In this way, the eigenregion image may be approximated by a lower-dimensional components in the eigensubspace. Simulation tests performed on SPOT and Landsat TM images have demonstrated that the proposed compression scheme is suitable for multispectral satellite image.     

Feature extraction and image segmentation using self-organizing networks

Feature extraction and image segmentation (FEIS) are two primary goals of almost all image-understanding systems. They are also the issues at which we look in this paper. We think of FEIS as a multilevel process of grouping and describing at each level. We emphasize the importance of grouping during this process because we believe that many features and events in real images are only perceived by combining weak evidence of several organized pixels or other low-level features. To realize FEIS based on this formulation, we must deal with such problems as how to discover grouping rules, how to develop grouping systems to integrate grouping rules, how to embed grouping processes into FEIS systems, and how to evaluate the quality of extracted features at various levels. We use self-organizing networks to develop grouping systems that take the organization of human visual perception into consideration. We demonstrate our approach by solving two concrete problems: extracting linear features in digital images and partitioning color images into regions. We present the results of experiments on real images.     

基于深度学习的多模态医学影像分割研究综述

多模态医学影像分割是医学影像分析领域的研究热点之一。有效利用不同模态影像的互补信息,从多种层面提供病灶区域及其周围区域的更多信息,可提高临床诊断的准确性。为了分析深度学习在多模态医学影像分割领域的研究现状及发展方向,对该领域近些年的分割方法进行了整理和研究。在分析它们的特点及存在的问题的基础上,对未来研究方向进行了展望,可帮助相关研究者全面、快速地了解该领域的研究现状、存在的问题和未来研究方向。     

Water body segmentation of Synthetic Aperture Radar image using Deep Convolutional Neural Networks

Deep Convolutional Neural Networks are finding their way into modern machine learning tasks and proved themselves to become one of the best contenders for future development in the field. Several proposed methods in image segmentation and classification problems are giving us satisfactory results and could even perform better than humans in image recognition tasks. But also at the cost of their performance, they also require a huge amount of images for training and huge amount of computing power and time that makes them unrealistic in some situations where obtaining a large dataset is not feasible. In this work, an attempt is made for segmentation of Synthetic Aperture Radar (SAR) images which are not usually abundant enough for training, and are heavily affected by a kind of multiplicative noise called speckle noise. For the segmentation task, pre-defined filters are first applied to the images and are fed to hybrid CNN that is resulted from the concept of Inception and U-Net. The outcome of our proposed method has been examined for their effectiveness of application in a complete set of SAR images that are not used for training. The accuracy has also been compared with the manually annotated SAR images.