Natural Image Segmentation Research Articles

Unsupervised Natural Image Segmentation Using Mean Histogram Features

A new histogram feature based natural image segmentation algorithm has been proposed. The proposed scheme uses histogram based new color texture extraction method which inherently combines color texture features rather then explicitly extracting it. A non parametric Bayesean clustering is employed to make the segmentation framework fully unsupervised where no a priori knowledge about the number and types of regions are required. The performance of the proposed method have been demonstrated by various experiments using images of natural scenes. The experimental results indicates that superior segmentation results can be obtained through the proposed unsupervised natural image segmentation algorithm.

Multi-nature hierarchical approach for natural image segmentation with pattern refinement feedback

A hierarchical learning method for segmenting natural images is proposed in this paper. This approach combines the perceptual information of three natures – colour, texture, and homogeneity – in order to segment natural colour images. These low-level features are extracted using a multiple scale neural architecture we previously proven in [1,20]. Present approach incorporates the human knowledge to a hierarchical categorisation process, where the features of the three natures are independently categorised. The final segmentation is achieved through pattern refinement cycles. The approach is compared to other two significant natural scene segmentation methods, achieving better results in a global evaluation. These comparisons are performed using the Berkeley Segmentation Dataset.

Texture Segmentation of Natural Images Based on Active Contour Model

To segment complex texture natural environment images; the first, the texture features of natural images should be analysed and the texture features should be extracted; The second, texture images segmengtation can be achieved by using Mumford-Shah active contour model, this segmentation model can better process fuzzy, default boundary, and this model can be solved by level set method. This method can express well complex texture signal features of natural images. Through making texture segmentation experiment for standard texture synthesis image and natural environmental image, its results show that the texture segmentation based on Mumford-Shah active contour model can segment natural images.

Gene transposon based clone selection algorithm for automatic clustering

Inspired by the principle of gene transposon proposed by Barbara McClintock, a new immune computing algorithm for automatic clustering named as Gene Transposon based Clone Selection Algorithm (GTCSA) is proposed in this paper. The proposed algorithm does not require a prior knowledge of the number of clusters; an improved variant of the clonal selection algorithm is used to determine the satisfied number of clusters and the appropriate partitioning of the data set as well. In addition, a novel operation called antibody gene transposon is introduced to the framework of clonal selection algorithm which can realize to find the satisfied number of cluster automatically. The proposed method has been extensively compared with iterated local search approach (ILS) and three well-known automatic clustering algorithms, including automatic clustering using an improved differential evolution algorithm (ACDE); variable-string-length genetic algorithm based clustering techniques (VGA) and the dynamic clustering approach based on particle swarm optimization (DCPSO). 23 datasets with widely varying characteristics are used to demonstrate the superiority of the GTCSA. In addition, GTCSA is applied to a real world application, namely natural image segmentation, with a good performance obtained.

INTELLIGENT UNDERSTANDING OF USER INTERACTION IN IMAGE SEGMENTATION

We have developed interactive tools for graph-based segmentation of natural images, in which the user guides object delineation by drawing strokes (markers) inside and outside the object. A suitable arc-weight estimation is paramount to minimize user time and maximize segmentation accuracy in these tools. However, it depends on discriminative image properties for object and background. These properties can be obtained from some marker pixels, but their identification is a hard problem during delineation. Careless arc-weight re-estimation reduces user control and drops performance, while interactive arc-weight estimation in a step before interactive object extraction is the best option so far, albeit it is not intuitive for nonexpert users. We present an effective solution using the unified framework of the image foresting transform (IFT) with three operators: clustering for interpreting user interaction and determining when and where arc weights need to be re-estimated; fuzzy classification for arc-weight estimation; and marker competition based on optimum connectivity for object extraction. For validation, we compared the proposed approach with another interactive IFT-based method, which computes arc weights before extraction. Evaluation involved multiple users (experts and nonexperts), a dataset with several natural images, and measurements to quantify accuracy, precision, efficiency (user time and computation time), and user control, being some of them novel measurements, proposed in this work.

Segmentation of Natural Images Using an Improved Thresholding-Based Technique

This paper investigates fundamental problems in image segmentation using traditional segmentation techniques and proposed an improved technique for segmenting images captured under natural environment. Image segmentation refers to a process of partitioning a digital image into multiple regions with the aim to extracts object of interest from the background. However, the segmentation process is very challenging especially for experiment which conducted in outdoor environment. It is difficult to produce a significant threshold value which required for segmenting images due to non uniform illumination and difference of reflection. Different illuminations may produce different colour intensity of the object surface and thus lead to inaccurate segmented images. The widely used traditional thresholding and clustering segmentation techniques are Otsu and Fuzzy c-means (FCM), respectively. Both traditional methods were unable to produce good quality segmented areas due to the complex background and non-uniform illumination of images captured under natural environment. Therefore, this paper proposed an improved thresholding-based segmentation integrated with an inverse technique (TsTN) that was able to partition natural images correctly. The three segmentation techniques were implemented on fruit images and their performance was evaluated based on the ground truth. The segmentation techniques performance was compared quantitatively using evaluation method, Rand Index (RI). The analysis results showed that TsTN has the ability to produce good quality segmented images. Furthermore, this segmentation technique was proven to be more accurate than the traditional thresholding and clustering techniques.

Multitude Regional Texture Extraction for Image Segmentation of Aerial and Natural Images

Image processing plays a major role in evaluation of images in many concerns. Manual interpretation of the image is time consuming process and it is susceptible to human errors. Computer assisted approaches for analyzing the images have increased in latest evolution of image processing. Also it has highlighted its performance more in the field of medical sciences. Many techniques are available for the involvement in processing of images, evaluation, extraction etc. The main goal of image segmentation is cluster pixeling the regions corresponding to individual surfaces, objects, or natural parts of objects and to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. The proposed method is to conquer segmentation and texture extraction with Regional and Multitude and techniques involved in it. First for aerial and natural imaging we present region based segmentation. Homogeneous regions depend on image granularity features. Second a local threshold based multitude texture regional seed segmentation for Aerial and natural image segmentation is proposed. Here extraction is done with dimensions comparable to the speckle size are to be extracted. The algorithm provides a less natural metrics awareness in a minimum user interaction environment. The shape and size of the growing regions depend on look up table entries. The experimental evaluation is conducted with training samples of natural and aerial images to show the performance of multitude textural extraction for more efficient image segmentation with sharp demarcation of edge portions along with intensity levels.

Nonlocal Active Contours

This article introduces a novel class of active contour models for image segmentation. It makes use of nonlocal comparisons between pairs of patches within each region to be segmented. The corresponding variational segmentation problem is implemented using a level set formulation that can handle an arbitrary number of regions. The pairwise interaction of features constrains only the local homogeneity of image features, which is crucial in capturing regions with smoothly spatially varying features. This segmentation method is generic and can be adapted to various segmentation problems by designing an appropriate metric between patches. We instantiate this framework using several classes of features and metrics. Piecewise smooth grayscale and color images are handled using $L^2$ distance between image patches. We show examples of efficient segmentation of natural color images. Locally oriented textures are segmented using the $L^2$ distance between patches of Gabor coefficients. We use a Wasserstein distance between local empirical distributions for locally homogeneous random textures. A correlation metric between local motion signatures is able to segment piecewise smooth optical flows.

Comparison of perceptual color spaces for natural image segmentation tasks

Color image segmentation largely depends on the color space chosen. Furthermore, spaces that show perceptual uniformity seem to outperform others due to their emulation of the human perception of color. We evaluate three perceptual color spaces, CIELAB, CIELUV, and RLAB, in order to determine their contribution to natural image segmentation and to identify the space that obtains the best results over a test set of images. The nonperceptual color space RGB is also included for reference purposes. In order to quantify the quality of resulting segmentations, an empirical discrepancy evaluation methodology is discussed. The Berkeley Segmentation Dataset and Benchmark is used in test series, and two approaches are taken to perform the experiments: supervised pixelwise classification using reference colors, and unsupervised clustering using k-means. A majority filter is used as a postprocessing stage, in order to determine its contribution to the result. Furthermore, a comparison of elapsed times taken by the required transformations is included. The main finding of our study is that the CIELUV color space outperforms the other color spaces in both discriminatory performance and computational speed, for the average case.

New insight at level set & Gaussian mixture model for natural image segmentation

Level set method and Gaussian Mixture model (GMM) are two very valuable tools for natural image segmentation. The former aims to acquire good geometrical continuity of segmentation boundaries, while the latter focuses on analyzing statistical properties of image feature data. Some studies on the integration between them have been reported due to their complementarity in the last 10 years. However, these studies generally supposed that the image-featured data density distribution of every segmented domain is independent with each other and can be separately approximated by Gaussian model or GMM, which conflicts with the fundamental idea of GMM clustering-based image segmentation. To remedy this problem, we give a new insight at image segmentation objective under the combined framework between Bayesian theory and GMM density approximation. Thereby, a novel level set image segmentation method integrated with GMM (GMMLS) is proposed. Then, the theoretical analysis on GMMLS is given, in which some valuable results are demonstrated. At last, several types of natural image segmentation experiments are reported and the corresponding results indicate that GMMLS can obtain better or at least equivalent performance compared with existing relevant methods in almost all cases.

Self-Organizing Map-Based Color Image Segmentation with k-Means Clustering and Saliency Map

Natural image segmentation is an important topic in digital image processing, and it could be solved by clustering methods. We present in this paper an SOM-based k-means method (SOM-K) and a further saliency map-enhanced SOM-K method (SOM-KS). In SOM-K, pixel features of intensity and L∗u∗v∗ color space are trained with SOM and followed by a k-means method to cluster the prototype vectors, which are filtered with hits map. A variant of the proposed method, SOM-KS, adds a modified saliency map to improve the segmentation performance. Both SOM-K and SOM-KS segment the image with the guidance of an entropy evaluation index. Compared to SOM-K, SOM-KS makes a more precise segmentation in most cases by segmenting an image into a smaller number of regions. At the same time, the salient object of an image stands out, while other minor parts are restrained. The computational load of the proposed methods of SOM-K and SOM-KS are compared to J-image-based segmentation (JSEG) and k-means. Segmentation evaluations of SOM-K and SOM-KS with the entropy index are compared with JSEG and k-means. It is observed that SOM-K and SOM-KS, being an unsupervised method, can achieve better segmentation results with less computational load and no human intervention.

Image segmentation by iterative optimization of multiphase multiple piecewise constant model and Four-Color relabeling

In the paper an iteratively unsupervised image segmentation algorithm is developed, which is based on our proposed multiphase multiple piecewise constant (MMPC) model and its graph cuts optimization. The MMPC model use multiple constants to model each phase instead of one single constant used in Chan and Vese (CV) model and cartoon limit so that heterogeneous image object segmentation can be effectively dealt with. We show that the multiphase optimization problem based on our proposed model can be approximately solved by graph cuts methods. Four-Color theorem is used to relabel the regions of image after every iteration, which makes it possible to represent and segment an arbitrary number of regions in image with only four phases. Therefore, the computational cost and memory usage are greatly reduced. The comparison with some typical unsupervised image segmentation methods using a large number of images from the Berkeley Segmentation Dataset demonstrates the proposed algorithm can effectively segment natural images with a good performance and acceptable computational time.

Segmentation of Natural Images by Texture and Boundary Compression

We present a novel algorithm for segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations that a homogeneously textured region of a natural image can be well modeled by a Gaussian distribution and the region boundary can be effectively coded by an adaptive chain code. The optimal segmentation of an image is the one that gives the shortest coding length for encoding all textures and boundaries in the image, and is obtained via an agglomerative clustering process applied to a hierarchy of decreasing window sizes as multi-scale texture features. The optimal segmentation also provides an accurate estimate of the overall coding length and hence the true entropy of the image. We test our algorithm on the publicly available Berkeley Segmentation Dataset. It achieves state-of-the-art segmentation results compared to other existing methods.

Natural Image Segmentation Based on Tree Equipartition, Bayesian Flooding and Region Merging

We propose a general purpose image segmentation framework, which involves feature extraction and classification in feature space, followed by flooding and merging in spatial domain. Region growing is based on the computed local measurements and distances from the distribution of features describing the different classes. Using the properties of the label dependent distances spatial coherence is ensured, since the image features are described globally. The distribution of the features for the different classes are obtained by block-wise unsupervised clustering based on the construction of the minimum spanning tree of the blocks' grid using the Mallows distance and the equipartition of the resulting tree. The final clustering is obtained by using the k-centroids algorithm. With high probability and under topological constraints, connected components of the maximum likelihood classification map are used to compute a map of initially labelled pixels. An efficient flooding algorithm is introduced, namely, Priority Multi-Class Flooding Algorithm (PMCFA), that assign pixels to labels using Bayesian dissimilarity criteria. A new region merging method, which incorporates boundary information, is introduced for obtaining the final segmentation map. Therefore, the merging stage is based on region features and edge localization. Segmentation results on the Berkeley benchmark data set demonstrate the effectiveness of the proposed methods.

Self-Validated Labeling of Markov Random Fields for Image Segmentation

This paper addresses the problem of self-validated labeling of Markov random fields (MRFs), namely to optimize an MRF with unknown number of labels. We present graduated graph cuts (GGC), a new technique that extends the binary s-t graph cut for self-validated labeling. Specifically, we use the split-and-merge strategy to decompose the complex problem to a series of tractable subproblems. In terms of Gibbs energy minimization, a suboptimal labeling is gradually obtained based upon a set of cluster-level operations. By using different optimization structures, we propose three practical algorithms: tree-structured graph cuts (TSGC), net-structured graph cuts (NSGC), and hierarchical graph cuts (HGC). In contrast to previous methods, the proposed algorithms can automatically determine the number of labels, properly balance the labeling accuracy, spatial coherence, and the labeling cost (i.e., the number of labels), and are computationally efficient, independent to initialization, and able to converge to good local minima of the objective energy function. We apply the proposed algorithms to natural image segmentation. Experimental results show that our algorithms produce generally feasible segmentations for benchmark data sets, and outperform alternative methods in terms of robustness to noise, speed, and preservation of soft boundaries.

Texture segmentation in natural images: Contribution of higher-order image statistics to psychophysical performance

Texture segmentation in natural images: Contribution of higher-order image statistics to psychophysical performance

An adaptive unsupervised approach toward pixel clustering and color image segmentation

This paper proposes an adaptive unsupervised scheme that could find diverse applications in pattern recognition as well as in computer vision, particularly in color image segmentation. The algorithm, named Ant Colony–Fuzzy C-means Hybrid Algorithm (AFHA), adaptively clusters image pixels viewed as three dimensional data pieces in the RGB color space. The Ant System (AS) algorithm is applied for intelligent initialization of cluster centroids, which endows clustering with adaptivity. Considering algorithmic efficiency, an ant subsampling step is performed to reduce computational complexity while keeping the clustering performance close to original one. Experimental results have demonstrated AFHA clustering's advantage of smaller distortion and more balanced cluster centroid distribution over FCM with random and uniform initialization. Quantitative comparisons with the X-means algorithm also show that AFHA makes a better pre-segmentation scheme over X-means. We further extend its application to natural image segmentation, taking into account the spatial information and conducting merging steps in the image space. Extensive tests were taken to examine the performance of the proposed scheme. Results indicate that compared with classical segmentation algorithms such as mean shift and normalized cut, our method could generate reasonably good or better image partitioning, which illustrates the method's practical value.

Image Segmentation Based on GrabCut Framework Integrating Multiscale Nonlinear Structure Tensor

In this paper, we propose an interactive color natural image segmentation method. The method integrates color feature with multiscale nonlinear structure tensor texture (MSNST) feature and then uses GrabCut method to obtain the segmentations. The MSNST feature is used to describe the texture feature of an image and integrated into GrabCut framework to overcome the problem of the scale difference of textured images. In addition, we extend the Gaussian Mixture Model (GMM) to MSNST feature and GMM based on MSNST is constructed to describe the energy function so that the texture feature can be suitably integrated into GrabCut framework and fused with the color feature to achieve the more superior image segmentation performance than the original GrabCut method. For easier implementation and more efficient computation, the symmetric KL divergence is chosen to produce the estimates of the tensor statistics instead of the Riemannian structure of the space of tensor. The Conjugate norm was employed using Locality Preserving Projections (LPP) technique as the distance measure in the color space for more discriminating power. An adaptive fusing strategy is presented to effectively adjust the mixing factor so that the color and MSNST texture features are efficiently integrated to achieve more robust segmentation performance. Last, an iteration convergence criterion is proposed to reduce the time of the iteration of GrabCut algorithm dramatically with satisfied segmentation accuracy. Experiments using synthesis texture images and real natural scene images demonstrate the superior performance of our proposed method.

Interactive Natural Image Segmentation via Spline Regression

This paper presents an interactive algorithm for segmentation of natural images. The task is formulated as a problem of spline regression, in which the spline is derived in Sobolev space and has a form of a combination of linear and Green's functions. Besides its nonlinear representation capability, one advantage of this spline in usage is that, once it has been constructed, no parameters need to be tuned to data. We define this spline on the user specified foreground and background pixels, and solve its parameters (the combination coefficients of functions) from a group of linear equations. To speed up spline construction, K-means clustering algorithm is employed to cluster the user specified pixels. By taking the cluster centers as representatives, this spline can be easily constructed. The foreground object is finally cut out from its background via spline interpolation. The computational complexity of the proposed algorithm is linear in the number of the pixels to be segmented. Experiments on diverse natural images, with comparison to existing algorithms, illustrate the validity of our method.

Texture Analysis and Segmentation Using Modulation Features, Generative Models, and Weighted Curve Evolution

In this work we approach the analysis and segmentation of natural textured images by combining ideas from image analysis and probabilistic modeling. We rely on AM-FM texture models and specifically on the Dominant Component Analysis (DCA) paradigm for feature extraction. This method provides a low-dimensional, dense and smooth descriptor, capturing essential aspects of texture, namely scale, orientation, and contrast. Our contributions are at three levels of the texture analysis and segmentation problems: First, at the feature extraction stage we propose a Regularized Demodulation Algorithm that provides more robust texture features and explore the merits of modifying the channel selection criterion of DCA. Second, we propose a probabilistic interpretation of DCA and Gabor filtering in general, in terms of Local Generative Models. Extending this point of view to edge detection facilitates the estimation of posterior probabilities for the edge and texture classes. Third, we propose the Weighted Curve Evolution scheme that enhances the Region Competition/ Geodesic Active Regions methods by allowing for the locally adaptive fusion of heterogeneous cues. Our segmentation results are evaluated on the Berkeley Segmentation Benchmark, and compare favorably to current state-of-the-art methods.