Natural Image Segmentation Research Articles

Inhomogeneity-embedded active contour for natural image segmentation

Active contour model (ACM) is one of the popular methodologies for image segmentation. However, the ACMs developed so far have not shown powerful performance on natural images. The reason is that natural images are rich in color, intensity or texture. The object pixels are often not artifact inhomogeneous, but inherently inhomogeneous. In this paper, we propose an inhomogeneity-embedded active contour (InH_ACM) for natural image segmentation. InH_ACM describes the inhomogeneity in natural images by a pixel inhomogeneity factor and utilizes it for segmentation, unlike most of existing methods that use some averaging convolution to reduce or remove the inhomogeneity in images. Moreover, we build a saliency-inspired framework that can automatically locate the initial contour for InH_ACM to start the evolution. Experimental results on Alpert׳s 100 gray images, MSRA׳s 1000 color images and our collected 300 images where the contained objects are mostly intrinsic inhomogeneous indicate that our proposed InH_ACM can produce reliably satisfactory segmentation in many situations, outperforming most of current popular ACMs.

An Improved Mean Shift Segmentation Method of High-Resolution Remote Sensing Image Based on LBP and Canny Features

Mean shift algorithm is a robust approach toward feature space analysis, which has been wildly used for natural scene image and medical image segmentation. Due to fuzzy boundary and low accuracy of Mean shift segmentation method, this paper puts forward to an improved Mean shift segmentation method of high-resolution remote sensing image based on LBP and Canny features. The results show that this improved Mean shift segmentation access can enhance segmentation accuracy compared to the traditional Mean shift.

A Novel Level Set Model Based on Multi-scale Local Structure Operation for Texture Image Segmentation

Regional level set method is a popular approach for image segmentation that uses inside and outside information of contour to extract object boundary. Unfortunately, in many cases, such method is not adequate to model complex textured objects. In this paper, we propose a natural texture image segmentation method which incorporates the pixel-level feature into region-level feature. The multiscale local structure operation is proposed as pixel-level feature to describe the texture structure of image. So the problems of multi-scale and rotation invariance of inhomogeneous texture are addressed by introducing multi-scale local structure operation into level set energy functional. Then, the global intensity information is extracted as the region-level feature and integrated with multi-scale local structure operation. Further, we propose a so-called vector level set method to obtain the segmentation results. Here, we extend the traditional regional level set model into the vector formulation so that the multi-scale local structure operation can be suitably combined with the global intensity information to achieve the more superior image segmentation performance than that of the traditional segmentation methods for texture images. Experiments on some synthesis texture images and real natural scene images demonstrate the excellent performance of the proposed method which successfully combines local structure information and global intensity information to extract the object boundary.

Automatic Segmentation of Nature Object Using Salient Edge Points Based Active Contour

Natural image segmentation is often a crucial first step for high-level image understanding, significantly reducing the complexity of content analysis of images. LRAC may have some disadvantages. (1) Segmentation results heavily depend on the initial contour selection which is a very skillful task. (2) In some situations, manual interactions are infeasible. To overcome these shortcomings, we propose a novel model for unsupervised segmentation of viewer’s attention object from natural images based on localizing region-based active model (LRAC). With aid of the color boosting Harris detector and the core saliency map, we get the salient object edge points. Then, these points are employed as the seeds of initial convex hull. Finally, this convex hull is improved by the edge-preserving filter to generate the initial contour for our automatic object segmentation system. In contrast with localizing region-based active contours that require considerable user interaction, the proposed method does not require it; that is, the segmentation task is fulfilled in a fully automatic manner. Extensive experiments results on a large variety of natural images demonstrate that our algorithm consistently outperforms the popular existing salient object segmentation methods, yielding higher precision and better recall rates. Our framework can reliably and automatically extract the object contour from the complex background.

Active contours with a joint and region‐scalable distribution metric for interactive natural image segmentation

In this study, we present an efficient active contour with a joint and region-scalable distribution metric for interactive natural image segmentation. First, the authors project a red–green–blue image into the CIELab colour space and employ independent component analysis to select two subspace channels. Then, by initialising the evolving curve interactively in terms of a polygonal curve or multiple polygonal curves, they compute a joint probability distribution associated with a region-scalable mask to model the regional statistics and propose a simple but effective distribution metric to regularise the active contours. Subsequently, they convert the resultant level set function into binary pattern and find the larger 8-connected regions as the desired objects. Finally, the selected regions are smoothed with a circular averaging filter such that the final segmentation results can be obtained. The proposed approach not only can deal with the complex appearance and intensity in homogeneity, but also has the advantages of fast convergence and easy implementation. The experiments have shown the precise and reliable segmentation results in comparison with the state-of-the-art competing approaches.

Wavelet-based fuzzy multiphase image segmentation method

We present a novel wavelet-based fuzzy multiphase image segmentation model.By introducing PCA features data, the proposed model can segment texture images.We formulate a fast iterative shrinkage algorithm for multiphase image segmentation.Experimental results show the effectiveness of the proposed method. This letter proposes a novel fuzzy multiphase image segmentation model. In the model, we introduce wavelet based regularization on the membership functions which are used as indicators of different regions. By using principal component analysis (PCA) features data as descriptors, the proposed model can segment texture and natural images. To efficiently solve the model, we formulate a fast iterative shrinkage algorithm for multiphase image segmentation. Experimental results show that the proposed method achieves better segmentation results compared with some other classical variational segmentation methods.

Automatic marker generation for watershed segmentation of natural images

Automatic marker selection for watershed segmentation is a difficult problem. Most of the existing procedures are intended for specific application fields and usually require some prior knowledge about the problem at hand. A simple and general method for generating markers is proposed. The markers are obtained from the splitting of the three-dimensional (3D) colour histogram of the image and imposed as minima for watershed segmentation. The method has been tested on natural images from the Berkeley segmentation dataset (BSDS500), showing results comparable with the state-of-the-art segmentation algorithms.

Gaussian Markov random field based improved texture descriptor for image segmentation

This paper proposes a novel robust texture descriptor based on Gaussian Markov random fields (GMRFs). A spatially localized parameter estimation technique using local linear regression is performed and the distributions of local parameter estimates are constructed to formulate the texture features. The inconsistencies arising in localized parameter estimation are addressed by applying generalized inverse, regularization and an estimation window size selection criterion. The texture descriptors are named as local parameter histograms (LPHs) and are used in texture segmentation with the k-means clustering algorithm. The segmentation results on general texture datasets demonstrate that LPH descriptors significantly improve the performance of classical GMRF features and achieve better results compared to the state-of-the-art texture descriptors based on local feature distributions. Impressive natural image segmentation results are also achieved and comparisons to the other standard natural image segmentation algorithms are also presented. LPH descriptors produce promising texture features that integrate both statistical and structural information about a texture. The region boundary localization can be further improved by integrating colour information and using advanced segmentation algorithms.

Image Segmentation Using Higher-Order Correlation Clustering.

In this paper, a hypergraph-based image segmentation framework is formulated in a supervised manner for many high-level computer vision tasks. To consider short- and long-range dependency among various regions of an image and also to incorporate wider selection of features, a higher-order correlation clustering (HO-CC) is incorporated in the framework. Correlation clustering (CC), which is a graph-partitioning algorithm, was recently shown to be effective in a number of applications such as natural language processing, document clustering, and image segmentation. It derives its partitioning result from a pairwise graph by optimizing a global objective function such that it simultaneously maximizes both intra-cluster similarity and inter-cluster dissimilarity. In the HO-CC, the pairwise graph which is used in the CC is generalized to a hypergraph which can alleviate local boundary ambiguities that can occur in the CC. Fast inference is possible by linear programming relaxation, and effective parameter learning by structured support vector machine is also possible by incorporating a decomposable structured loss function. Experimental results on various data sets show that the proposed HO-CC outperforms other state-of-the-art image segmentation algorithms. The HO-CC framework is therefore an efficient and flexible image segmentation framework.

Multi-class learning for vessel characterisation in intravascular ultrasound

In this thesis we tackle the problem of automatic characterization of human coronary vessel in IntravascularUltrasound (IVUS) image modality. The basis for the whole characterization process is machinelearning applied to multi-class problems. In all the presented approaches, the Error-Correcting Output Codes(ECOC) framework is used as central element for the design of multi-class classifiers. Two main contributionsare presented in this thesis. First, a novel method for the design of potential function for DiscriminativeRandom Fields, namely ECOC-DRF, is presented. The method is successfully applied to problems of objectclassification and segmentation in synthetic and natural images. Furthermore, ECOC-DRF is applied toobtain a robust vessel characterization in IVUS image sequences. Based on ECOC-DRF, the main regionsof the coronary artery are robustly segmented by means of a novel holistic approach, namely HoliMAb, representingthe second contribution of this thesis. The HoliMAb framework is applied to problems of lumenborder and media-adventitia border detection, achieving an error comparable with inter-observer variabilityand with state of the art methods.

Rival Penalized Image Segmentation

Image segmentation plays an important role in computer vision and image analysis. In this paper, we cast natural image segmentation into a problem of feature clustering. We extract local homogeneity, textures and color features from images and describe them with Gaussian Mixture Models. Unlike most existing clustering based segmentation methods, our method is capable of model selection automatically by de-learning redundant segments (clusters) during the clustering process. Thus, our method does not need to specify the exact number of segments in advance. Comprehensive experiments are conducted to measure the performance of the proposed algorithm in terms of visual evaluation and a variety of quantitative indices for image segmentation. The proposed algorithm compares favorably against other well-known image segmentation methods on the BSDS500 image database.

Phase synchrony facilitates binding and segmentation of natural images in a coupled neural oscillator network

Synchronization has been suggested as a mechanism of binding distributed feature representations facilitating segmentation of visual stimuli. Here we investigate this concept based on unsupervised learning using natural visual stimuli. We simulate dual-variable neural oscillators with separate activation and phase variables. The binding of a set of neurons is coded by synchronized phase variables. The network of tangential synchronizing connections learned from the induced activations exhibits small-world properties and allows binding even over larger distances. We evaluate the resulting dynamic phase maps using segmentation masks labeled by human experts. Our simulation results show a continuously increasing phase synchrony between neurons within the labeled segmentation masks. The evaluation of the network dynamics shows that the synchrony between network nodes establishes a relational coding of the natural image inputs. This demonstrates that the concept of binding by synchrony is applicable in the context of unsupervised learning using natural visual stimuli.

A SURVEY ON COLOR IMAGE SEGMENTATION THROUGH LEAKY INTEGRATE AND FIRE MODEL OF SPIKING NEURAL NETWORKS

Neurological research shows that the biological neurons store information in the timing of spikes. Spiking neural networks are the third generation of neural networks which take into account the precise firing time of neurons for information encoding. In SNNs, computation is performed in the temporal (time related) domain and relies on the timings between spikes. The leaky integrate-and-fire neuron is probably the best-known example of a formal spiking neuron model. In this paper, we have simulated LIF model of SNN for performing the image segmentation using K-Means clustering. Clustering can be termed here as a grouping of similar images in the database. Clustering is done based on different attributes of an image such as size, color, texture etc. The purpose of clustering is to get meaningful result, effective storage and fast retrieval in various areas. Image segmentation is the first step and also one of the most critical tasks of image analysis .Because of its simplicity and efficiency, clustering approach is used for the segmentation of (textured) natural images. After the extraction of the image features using wavelet; the feature samples, handled as vectors, are grouped together in compact but well-separated clusters corresponding to each class of the image. Simulation results therefore demonstrate how SNN can be applied with efficacy in Image Segmentation.

An Efficient Weakly Supervised Approach for Texture Segmentation via Graph Cuts

AbstractWe propose an approach for texture segmentation based on weak supervised learning. The weak supervision implies that the user marks only a single small patch for each class in the input image. These patches are used for training. We employ the method of graph cuts for the segmentation task. Our work demonstrates that even under such weak training, texture segmentation can be achieved efficiently and with good accuracy via graph cuts. Moreover, our approach uses a simpler feature representation than that in similar contemporary segmentation approaches. We also provide a brief discussion indicating the good performance of our approach. We validate our method on various standard texture mosaics and also on segmentation of natural images with large texture variations.

A Hybrid Morphological Active Contour for Natural Images

Morphological active contours for image segmentation have become popular due to their low computational complexity coupled with their accurate approximation of the partial differential equations involved in the energy minimization of the segmentation process. In this paper, a morphological active contour which mimics the energy minimization of the popular Chan-Vese Active Contour without Edges is coupled with a morphological edge-driven segmentation term to accurately segment natural images. By using morphological approximations of the energy minimization steps, the algorithm has a low computational complexity. Additionally, the coupling of the edge-based and region-based segmentation techniques allows the proposed method to be robust and accurate. We will demonstrate the accuracy and robustness of the algorithm using images from the Weizmann Segmentation Evaluation Database and report on the segmentation results using the Sorensen-Dice similarity coefficient.

Unsupervised Natural Image Segmentation via Bayesian Ying–Yang Harmony Learning Theory

An unsupervised image segmentation method for natural images is proposed in this paper. We assume that texture features in natural images are distributed as a mixture of Gaussians. In order to cluster the extracted feature vectors, we modify a clustering algorithm based on Bayesian Ying–Yang (BYY) harmony learning theory with Dirichlet-Normal-Wishart prior. This algorithm can determine the number of components automatically during the clustering procedure, as long as we give a large enough initial component number. Our works in this paper have presented a complete pipeline of clustering-based image segmentation including feature extraction, robust feature clustering and methodological effective post processing. The experiments reported in this paper demonstrate that the proposed method is efficient (in terms of visual evaluation and quantitative performance measures) and performs competitively compared to the existing state-of-the-art segmentation methods.

Semantic image segmentation using low-level features and contextual cues

Semantic image segmentation aims to partition an image into non-overlapping regions and assign a pre-defined object class label to each region. In this paper, a semantic method combining low-level features and high-level contextual cues is proposed to segment natural scene images. The proposed method first takes the gist representation of an image as its global feature. The image is then over-segmented into many super-pixels and histogram representations of these super-pixels are used as local features. In addition, co-occurrence and spatial layout relations among object classes are exploited as contextual cues. Finally the features and cues are integrated into the inference framework based on conditional random field by defining specific potential terms and introducing weighting functions. The proposed method has been compared with state-of-the-art methods on the MSRC database, and the experimental results show its effectiveness.

New one-versus-all [formula omitted] solving intra–inter class imbalance with extended manifold regularization and localized relative maximum margin

The optimal separating hyperplane with maximum margin plays a central role in the support vector machine (SVM) classifiers, but is exclusively determined by the support vectors that does not take any structure information into account, especially in the one-versus-all (OVA) SVM for the multi-class classification application where the positive samples and negative ones are usually unbalanced. To address this intra–inter class imbalance problem, a new OVA SVM method is proposed by extending manifold regularization and enhancing the relative maximum margin. It aims to minimize the scatter of nearby intra-class point pairs while penalize that of nearby inter-class point pairs not being arbitrarily large through the constraints of marginal separation and manifold regularization. This objective is transformed into a constrained optimization problem that overcomes both the classical SVM's weakness of ignoring the data underlying structure, and the Laplacian SVM's weakness of abandoning class label information and class separation of manifolds. It also takes the positive and negative samples into different consideration according to their unbalanced distribution. Additionally, risk bounds are derived for the proposed formulation based on the theory of Rademacher complexity and the improvement on the bounds of standard SVM is proven. The comparative experiments for multi-class classification, face recognition, and natural image segmentation on several synthetic and benchmark data sets validate the effectiveness of the proposed method and indicate the consideration of both preserving intrinsic within-class manifold structure and bounding the local relative margin between class is helpful to improve the OVA SVM classification performance.

AN OVERVIEW OF IMAGE SEGMENTATION ALGORITHMS

Image segmentation is a puzzled problem even after four decades of research. Research on image segmentation is currently conducted in three levels. Development of image segmentation methods, evaluation of segmentation algorithms and performance and study of these evaluation methods. Hundreds of techniques have been proposed for segmentation of natural images, noisy images, medical images etc. Currently most of the researchers are evaluating the segmentation algorithms using ground truth evaluation of (Berkeley segmentation database) BSD images. In this paper an overview of various segmentation algorithms is discussed. The discussion is mainly based on the soft computing approaches used for segmentation of images without noise and noisy images and the parameters used for evaluating these algorithms. Some of these techniques used are Markov Random Field (MRF) model, Neural Network, Clustering, Particle Swarm optimization, Fuzzy Logic approach and different combinations of these soft techniques.

Variational and PCA based natural image segmentation

This paper introduces a novel variational segmentation method within the fuzzy framework, which solves the problem of segmenting multi-region color-scale images of natural scenes. We call this kind of images as natural images. The advantages of our segmentation method are: (1) by introducing the PCA descriptors, our segmentation model can partition color-texture images better than classical variational-based segmentation models, (2) to preserve geometrical structure of each fuzzy membership function, we propose a nonconvex regularization term in our model, (3) to solve our segmentation model more efficiently, we design a fast iteration algorithm in which we integrate the augmented Lagrange multiplier method and the iterative reweighting. We conduct comprehensive experiments to measure the segmentation performance of our model in terms of visual evaluation, and we also demonstrate the efficiency of the corresponding algorithm in terms of a variety of quantitative indices. The proposed model achieves better segmentation results compared with some other well-known models, such as the level-set model and the fuzzy region competition model, while the proposed algorithm is much more efficient than the algorithm of the state-of-the-art natural image segmentation model.