Abstract not found

Many approaches to Bayesian image segmentation have used maximum a posteriori (MAP) estimation in conjunction with Markov random fields (MRF). While this approach performs well, it has a number of disadvantages. In particular, exact MAP estimates cannot be computed, approximate MAP estimates are computationally expensive to compute, and unsupervised parameter estimation of the MRF is difficult. In this paper, we propose a new approach to Bayesian image segmentation which directly addresses these problems. The new method replaces the MRF model with a novel multiscale random field (MSRF), and replaces the MAP estimator with a sequential MAP (SMAP) estimator derived from a novel estimation criteria. Together, the proposed estimator and model result in a segmentation algorithm which is not iterative and can be computed in time proportional to MN where M is the number of classes and N is the number of pixels. We also develop a computationally effcient method for unsupervised estimation of m...

journal = {Signal Processing}, publisher = {Elsevier}, volume = {31}, number = {2}, year = {1993}, pages = {165--180}} This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by the authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder. document created on: December 20, 2006 created from file: sp93cdcoverpage.tex cover page automatically created with CoverPage.sty (available at your favourite CTAN mirror) L

Among the existing texture segmentation methods, those relying on Markov random fields have retained substantial interest and have proved to be very efficient in supervised mode. The use of Markov random fields in unsupervised mode is however hampered by the parameter estimation problem. The recent solutions proposed to overcome this difficulty rely on the assumptions that the shapes of the textured regions are simple or that there is only a limited number of textures in the input image. Besides the fact that these assumptions may not be satisfied in practice, Markov random fields based methods are often computationally expensive. In this paper, an evolutionary approach, selectionist relaxation, is proposed as a solution to the problem of segmenting Markov random field modeled textures in unsupervised mode. In selectionist relaxation, the computation is distributed among a population of units that iteratively evolves according to simple and local evolutionary rules. A unit is an associ...

The emerging video coding standard MPEG-4 enables various content-based functionalities for multimedia applications. To support such functionalities, as well as to improve coding e#ciency, MPEG-4 relies on a decomposition of each frame of an image sequence into video object planes (VOP's). Each VOP corresponds to a single moving object in the scene. In this thesis, a new method for automatic segmentation of moving objects in image sequences is presented. We formulate the problem as graph labeling over a region adjacency graph (RAG), based on motion information. The label field is modeled as a Markov random field (MRF).

Markov random fields are used extensively in modelbased approaches to image segmentation and, under the Bayesian paradigm, are implemented through Markov chain Monte Carlo (MCMC) methods. In this paper, we describe a class of such models (the double Markov random field) for images composed of several textures, which we consider to be the natural hierarchical model for such a task. We show how several of the Bayesian approaches in the literature can be viewed as modifications of this model, made in order to make MCMC implementation possible. From a simulation study, conclusions are made concerning the performance of these modified models.

This paper compares the discrimination ability of two texture analysis methods: Markov random fields (MRFs) and gray-level cooccurrence probabilities (GLCPs). There exists limited published research comparing different texture methods, especially with regard to segmenting remotely sensed imagery. The role of window size in texture feature consistency and separability as well as the role in handling of multiple textures within a window are investigated. Necessary testing is performed on samples of synthetic (MRF generated), Brodatz, and synthetic aperture radar (SAR) sea ice imagery. GLCPs are demonstrated to have improved discrimination ability relative to MRFs with decreasing window size, which is important when performing image segmentation. On the other hand, GLCPs are more sensitive to texture boundary confusion than MRFs given their respective segmentation procedures.

Texture plays an increasingly important role in computer vision. It has found wide application in remote sensing, medical diagnosis, quality control, food inspection and so forth. This thesis investigates the problem of classifying texture in digital images, following the convention of splitting the problem into feature extraction and classification. Texture feature descriptions considered in this thesis include Liu's features, features from the Fourier transform using geometrical regions, the Statistical Gray-Level Dependency Matrix, and the Statistical Feature Matrix. Classification techniques that are considered in this thesis include the K-Nearest Neighbour Rule and the Error Back-Propagation method. Novel techniques developed during the author's Ph.D study include (1) a Generating Shrinking Algorithm that builds a three-layer feed-forward network to classify arbitrary patterns with guaranteed convergence and known generalisation behaviour, (2) a set of Statistical Geometrical Feat...

Abstract. Texture analysis and synthesis is very important for computer graphics, vision, and image processing. This paper describes an algorithm which can produce new textures with a matching visual appearance from a given example image. Our algorithm is based on a model that characterizes textures using a nonlinear deterministic function. During analysis, an example texture is summarized into this function using tree structure vector quantization. An output texture, initially random noise, is then synthesized from this estimated function. Compared to existing approaches, our algorithm can efficiently generate a wide variety of textures. The effectiveness of our approach is demonstrated using standard test images from the Brodatz texture album.

A systematic approach towards the problem of designing integrated methods for image segmentation has been developed in this thesis. This is aimed towards the analysis of underlying structures in an image which is crucial for a variety of image analysis and computer vision applications. However, a robust identification and measurement of such structure is not always achievable by using a single technique that depends on a single image feature. Thus, it is necessary to make use of various image features, such as gradients, curvatures, homogeneity of intensity values, textures, etc. as well as modelbased information (such as shape). Integration provides a way to make use of the rich information provided by the various information sources, whereby consistent information from the different sources are reinforced while noise and errors are attenuated. As a first step, integration is achieved in this work by using region information in addition to gradient information within the deformable boundary finding framework. This considerably increases the robustness of the final boundary output to noise and initial estimate.