Texture classification using spectral histograms

Based on a local spatial/frequency representation,we employ a spectral histogram as a feature statistic for texture classification. The spectral histogram consists of marginal distributions of responses of a bank of filters and encodes implicitly the local structure of images through the filtering stage and the global appearance through the histogram stage. The distance between two spectral histograms is measured using /spl chi//sup 2/-statistic. The spectral histogram with the associated distance measure exhibits several properties that are necessary for texture classification. A filter selection algorithm is proposed to maximize classification performance of a given dataset. Our classification experiments using natural texture images reveal that the spectral histogram representation provides a robust feature statistic for textures and generalizes well. Comparisons show that our method produces a marked improvement in classification performance. Finally we point out the relationships between existing texture features and the spectral histogram, suggesting that the latter may provide a unified texture feature.     

Image segmentation using a texture gradient based watershed transform

The segmentation of images into meaningful and homogenous regions is a key method for image analysis within applications such as content based retrieval. The watershed transform is a well established tool for the segmentation of images. However, watershed segmentation is often not effective for textured image regions that are perceptually homogeneous. In order to segment such regions properly, the concept of the "texture gradient" is introduced. Texture information and its gradient are extracted using a novel nondecimated form of a complex wavelet transform. A novel marker location algorithm is subsequently used to locate significant homogeneous textured or non textured regions. A marker driven watershed transform is then used to segment the identified regions properly. The combined algorithm produces effective texture and intensity based segmentation for application to content based image retrieval.     

Image segmentation and inpainting using hierarchical level set and texture mapping

Image inpainting is an artistic procedure to recover a damaged painting or picture. We propose a novel approach for image inpainting by using the Mumford-Shah (MS) model and the level set method to estimate image structure of the damaged regions. This approach has been successfully used in image segmentation problem. Compared to some other inpainting methods, the MS model approach detects and preserves edges in the inpainting areas. We propose a fast and efficient algorithm that achieves both inpainting and segmentation. In previous works on the MS model, only one or two level set functions are used to segment an image. While this approach works well on simple cases, detailed edges cannot be detected in complicated image structures. Although multi-level set functions can be used to segment an image into many regions, the traditional approach causes extensive computations and the solutions depend on the location of initial curves. Our proposed approach utilizes faster hierarchical level set method and guarantees convergence independent of initial conditions. Because we detect both the main structure and the detailed edges, our approach preserves edges in the inpainting area. Also, exemplar-based approach for filling textured regions is employed. Experimental results demonstrate the advantage of our method.     

Image indexing using compressed colour histograms

The distribution of colours in an image has proven to be very useful for object recognition. Building on Swain's colour indexing, colour distributions are now an integral part of many recognition schemes. This is not to say that colour alone suffices but rather that colour is one important cue that aids recognition. Colour indexing is performed on colour distribution histograms, and as such, the speed of the system is directly related to the size of the histogram to be indexed. It is shown how colour histograms can be effectively compressed and how compressed colour histograms can be compared for indexing. The authors make two important contributions. First, they show that an opponent colour histogram can be compressed more readily than can conventional colour space. Secondly, they use the standard transform encoding methods (the Karhunen-Loeve transform, the discrete cosine transform, the Hadamard transform and hybrid transforms) to compress colour histograms. Experiments show that compression rates of up to 250:1 are possible without affecting indexing performance. This means that a database can be searched that is 250 times larger in the same time as that searched by conventional indexing     

Vegetation segmentation based on variational level set using multi-channel local wavelet texture and color

The existing spectrum index-based methods for detecting vegetation coverage suffer from an over-dependence on spectrum. To address these issues, this paper proposes a graph cut-based variational level set segmentation algorithm that combines multi-channel local wavelet texture (MCLWT) and color. First, the prior color is generated by automatic estimation based on the mathematical morphology with a color histogram. Then, local wavelet texture features are extracted using a multi-scale and orientation Gabor wavelet transformation followed by local median and entropy filtering. Next, in addition to the energy of color, that of MCLWT is integrated into the variational level set model based on kernel density estimation. Consequently, all energies are integrated into the graph cut-based variational level set model. Finally, the proposed energy functional is made convex to obtain a global optimal solution, and a primal-dual algorithm with global relabeling is adopted to accelerate the evolution of the level sets. A comparison of the segmentation results from our proposed algorithm and other state-of-the-art algorithms showed that our algorithm effectively reduces the over-dependence on color and yields more accurate results in detecting vegetation coverage.     

Efficient multispectral texture segmentation using multivariatestatistics

A complete, low computational cost method is presented for multispectral textured image segmentation. The procedure performs a tesselation of the image into non-overlapped rectangular regions and decides about the homogeneity of each region, using statistical hypothesis testing. Regions labelled as homogeneous are used to estimate the parameters that are necessary to classify the pixels of the heterogeneous regions. The proposed scheme can also be used to estimate the number of different textures in the image. This represents an efficient alternative to other computationally expensive methods, such as those that employ clustering techniques     

LS-SVM based image segmentation using color and texture information

Image segmentation partitions an image into nonoverlapping regions, which ideally should be meaningful for a certain purpose. Automatic segmentation of images is a very challenging fundamental task in computer vision and one of the most crucial steps toward image understanding. In recent years, many image segmentation algorithms have been developed, but they are often very complex and some undesired results occur frequently. In this paper, we present an effective color image segmentation approach based on pixel classification with least squares support vector machine (LS-SVM). Firstly, the pixel-level color feature, Homogeneity, is extracted in consideration of local human visual sensitivity for color pattern variation in HSV color space. Secondly, the image pixel’s texture features, Maximum local energy, Maximum gradient, and Maximum second moment matrix, are represented via Gabor filter. Then, both the pixel-level color feature and texture feature are used as input of LS-SVM model (classifier), and the LS-SVM model (classifier) is trained by selecting the training samples with Arimoto entropy thresholding. Finally, the color image is segmented with the trained LS-SVM model (classifier). This image segmentation not only can fully take advantage of the local information of color image, but also the ability of LS-SVM classifier. Experimental evidence shows that the proposed method has very effective segmentation results and computational behavior, and decreases the time and increases the quality of color image segmentation in comparison with the state-of-the-art segmentation methods recently proposed in the literature.     

基于LBP纹理特征的随机游走图像分割

本文通过求解融入纹理特征信息的对称、半正定线性方程组,提出一种新的基于随机游走(Random Walker)的纹理图像分割算法。为了构造该方程组,首先通过局部二元模式(Local binary pattern,简称LBP)算子来描述纹理,将图像映射至不同纹理之间有显著区别的LBP图(LBP map)上,进而将其与梯度和几何信息结合并构造倒数型像素相似度,形成方程所需的权值矩阵,在随机游走模型下使已标号区域向未知区域传递,从而实现纹理图像分割。最后以纹理图像、噪声合成图像、MRI、CT图像为实验对象来验证算法的有效性。定性及定量实验结果表明,在多目标分割任务下,本方法有更好的有效性和精确性。     

Bayesian image segmentation using local iso-intensity structural orientation.

Image segmentation is a fundamental problem in early computer vision. In segmentation of flat shaded, nontextured objects in real-world images, objects are usually assumed to be piecewise homogeneous. This assumption, however, is not always valid with images such as medical images. As a result, any techniques based on this assumption may produce less-than-satisfactory image segmentation. In this work, we relax the piecewise homogeneous assumption. By assuming that the intensity nonuniformity is smooth in the imaged objects, a novel algorithm that exploits the coherence in the intensity profile to segment objects is proposed. The algorithm uses a novel smoothness prior to improve the quality of image segmentation. The formulation of the prior is based on the coherence of the local structural orientation in the image. The segmentation process is performed in a Bayesian framework. Local structural orientation estimation is obtained with an orientation tensor. Comparisons between the conventional Hessian matrix and the orientation tensor have been conducted. The experimental results on the synthetic images and the real-world images have indicated that our novel segmentation algorithm produces better segmentations than both the global thresholding with the maximum likelihood estimation and the algorithm with the multilevel logistic MRF model.     

Image segmentation and selective smoothing by using Mumford-Shah model.

Recently, Chan and Vese developed an active contour model for image segmentation and smoothing by using piecewise constant and smooth representation of an image. Tsai et al. also independently developed a segmentation and smoothing method similar to the Chan and Vese piecewise smooth approach. These models are active contours based on the Mumford-Shah variational approach and the level-set method. In this paper, we develop a new hierarchical method which has many advantages compared to the Chan and Vese multiphase active contour models. First, unlike previous works, the curve evolution partial differential equations (PDEs) for different level-set functions are decoupled. Each curve evolution PDE is the equation of motion of just one level-set function, and different level-set equations of motion are solved in a hierarchy. This decoupling of the motion equations of the level-set functions speeds up the segmentation process significantly. Second, because of the coupling of the curve evolution equations associated with different level-set functions, the initialization of the level sets in Chan and Vese's method is difficult to handle. In fact, different initial conditions may produce completely different results. The hierarchical method proposed in this paper can avoid the problem due to the choice of initial conditions. Third, in this paper, we use the diffusion equation for denoising. This method, therefore, can deal with very noisy images. In general, our method is fast, flexible, not sensitive to the choice of initial conditions, and produces very good results.     

利用图像纹理特征的图像检索

随着多媒体技术的发展，大容量图像库得到了广泛的应用，基于内容的图像检索（CBIR）技术则是进行管理和检索的有效手段。介绍了利用图像的纹理特征进行图像检索的方法、具体算法和CBIR系统的实现，给出了试验结果。     

Image segmentation using hidden Markov Gauss mixture models.

Image segmentation is an important tool in image processing and can serve as an efficient front end to sophisticated algorithms and thereby simplify subsequent processing. We develop a multiclass image segmentation method using hidden Markov Gauss mixture models (HMGMMs) and provide examples of segmentation of aerial images and textures. HMGMMs incorporate supervised learning, fitting the observation probability distribution given each class by a Gauss mixture estimated using vector quantization with a minimum discrimination information (MDI) distortion. We formulate the image segmentation problem using a maximum a posteriori criteria and find the hidden states that maximize the posterior density given the observation. We estimate both the hidden Markov parameter and hidden states using a stochastic expectation-maximization algorithm. Our results demonstrate that HMGMM provides better classification in terms of Bayes risk and spatial homogeneity of the classified objects than do several popular methods, including classification and regression trees, learning vector quantization, causal hidden Markov models (HMMs), and multiresolution HMMs. The computational load of HMGMM is similar to that of the causal HMM.     

Abdominal organ segmentation using texture transforms and aHopfield neural network

Abdominal organ segmentation is highly desirable but difficult, due to large differences between patients and to overlapping grey-scale values of the various tissue types. The first step in automating this process is to cluster together the pixels within each organ or tissue type. We propose to form images based on second-order statistical texture transforms (Haralick transforms) of a CT or MRI scan. The original scan plus the suite of texture transforms are then input into a Hopfield neural network (HNN). The network is constructed to solve an optimization problem, where the best solution is the minima of a Lyapunov energy function. On a sample abdominal CT scan, this process successfully clustered 79-100% of the pixels of seven abdominal organs. It is envisioned that this is the first step to automate segmentation. Active contouring (e.g., SNAKE's) or a back-propagation neural network can then be used to assign names to the clusters and fill in the incorrectly clustered pixels.     

基于局部空间密度峰值的图像分割算法

针对现实中真实图像含有大量的噪声及复杂纹理,提出了基于局部空间密度峰值的图像分割算法。该算法采用基于局部空间信息下的距离,结合密度峰值,通过捕捉图像的内部局部结构特征,获得较为准确的区域分割结果,最后对分割区域的离群点作二次划分,来进一步消除噪声及纹理的影响。通过对三类不同的图像(噪声图像、纹理图像、自然图像)进行图像分割的实验结果显示:相比K-Means和FCM算法,该算法可有效地分割含有噪声和复杂纹理的图像。     

Unsupervised texture segmentation of images using tuned matchedGabor filters

Recent studies have confirmed that the multichannel Gabor decomposition represents an excellent tool for image segmentation and boundary detection. Unfortunately, this approach when used for unsupervised image analysis tasks imposes excessive storage requirements due to the nonorthogonality of the basis functions and is computationally highly demanding. In this correspondence, we propose a novel method for efficient image analysis that uses tuned matched Gabor filters. The algorithmic determination of the parameters of the Gabor filters is based on the analysis of spectral feature contrasts obtained from iterative computation of pyramidal Gabor transforms with progressive dyadic decrease of elementary cell sizes. The method requires no a priori knowledge of the analyzed image so that the analysis is unsupervised. Computer simulations applied to different classes of textures illustrate the matching property of the tuned Gabor filters derived using our determination algorithm. Also, their capability to extract significant image information and thus enable an easy and efficient low-level image analysis will be demonstrated.     

Unsupervised texture segmentation using multichannel decompositionand hidden Markov models

In this paper, we describe an automatic unsupervised texture segmentation scheme using hidden Markov models (HMMs). First, the feature map of the image is formed using Laws' micromasks and directional macromasks. Each pixel in the feature map is represented by a sequence of 4-D feature vectors. The feature sequences belonging to the same texture are modeled as an HMM. Thus, if there are M different textures present in an image, there are M distinct HMMs to be found and trained. Consequently, the unsupervised texture segmentation problem becomes an HMM-based problem, where the appropriate number of HMMs, the associated model parameters, and the discrimination among the HMMs become the foci of our scheme. A two-stage segmentation procedure is used. First, coarse segmentation is used to obtain the approximate number of HMMs and their associated model parameters. Then, fine segmentation is used to accurately estimate the number of HMMs and the model parameters. In these two stages, the critical task of merging the similar HMMs is accomplished by comparing the discrimination information (DI) between the two HMMs against a threshold computed from the distribution of all DI's. A postprocessing stage of multiscale majority filtering is used to further enhance the segmented result. The proposed scheme is highly suitable for pipeline/parallel implementation. Detailed experimental results are reported. These results indicate that the present scheme compares favorably with respect to other successful schemes reported in the literature.     

Image segmentation using data-modulated nonlinear diffusion

Effective object segmentation is achieved by applying a novel data-modulated nonlinear diffusion technique. The advantages of this strategy are a considerable smoothing of the detail of the scene image within the boundaries of the object while inhibiting the diffusion across the boundaries, as well as preserving and even enhancing the object borders     

Hidden Markov Bayesian texture segmentation using complex wavelet transform

The authors propose a multiscale Bayesian texture segmentation algorithm that is based on a complex wavelet domain hidden Markov tree (HMT) model and a hybrid label tree (HLT) model. The HMT model is used to characterise the statistics of the magnitudes of complex wavelet coefficients. The HLT model is used to fuse the interscale and intrascale context information. In the HLT, the interscale information is fused according to the label transition probability directly resolved by an EM algorithm. The intrascale context information is also fused so as to smooth out the variations in the homogeneous regions. In addition, the statistical model at pixel-level resolution is formulated by a Gaussian mixture model (GMM) in the complex wavelet domain at scale 1, which can improve the accuracy of the pixel-level model. The experimental results on several texture images are used to evaluate the algorithm.