Showing papers on "Segmentation-based object categorization published in 1999"

Color image segmentation

Abstract: In this work, a new approach to fully automatic color image segmentation, called JSEG, is presented. First, colors in the image are quantized to several representing classes that can be used to differentiate regions in the image. Then, image pixel colors are replaced by their corresponding color class labels, thus forming a class-map of the image. A criterion for "good" segmentation using this class-map is proposed. Applying the criterion to local windows in the class-map results in the "J-image", in which high and low values correspond to possible region boundaries and region centers, respectively. A region growing method is then used to segment the image based on the multi-scale J-images. Experiments show that JSEG provides good segmentation results on a variety of images.

A Survey of Current Methods in Medical Image Segmentation

Abstract: Image segmentation plays a crucial role in many medical imaging applications by automating or facilitating the delineation of anatomical structures and other regions of interest. We present herein a critical appraisal of the current status of semi-automated and automated methods for the segmentation of anatomical medical images. Current segmentation approaches are reviewed with an emphasis placed on revealing the advantages and disadvantages of these methods for medical imaging applications. The use of image segmentation in different imaging modalities is also described along with the difficulties encountered in each modality. We conclude with a discussion on the future of image segmentation methods in biomedical research.

Elastic model-based segmentation of 3-D neuroradiological data sets

Abstract: This paper presents a new technique for the automatic model-based segmentation of three-dimensional (3-D) objects from volumetric image data. The development closely follows the seminal work of Taylor and Cootes on active shape models, but is based on a hierarchical parametric object description rather than a point distribution model. The segmentation system includes both the building of statistical models and the automatic segmentation of new image data sets via a restricted elastic deformation of shape models. Geometric models are derived from a sample set of image data which have been segmented by experts. The surfaces of these binary objects are converted into parametric surface representations, which are normalized to get an invariant object-centered coordinate system. Surface representations are expanded into series of spherical harmonics which provide parametric descriptions of object shapes. It is shown that invariant object surface parametrization provides a good approximation to automatically determine object homology in terms of sets of corresponding sets of surface points. Gray-level information near object boundaries is represented by 1-D intensity profiles normal to the surface. Considering automatic segmentation of brain structures as their driving application, the authors' choice of coordinates for object alignment was the well-accepted stereotactic coordinate system. Major variation of object shapes around the mean shape, also referred to as shape eigenmodes, are calculated in shape parameter space rather than the feature space of point coordinates. Segmentation makes use of the object shape statistics by restricting possible elastic deformations into the range of the training shapes. The mean shapes are initialized in a new data set by specifying the landmarks of the stereotactic coordinate system. The model elastically deforms, driven by the displacement forces across the object's surface, which are generated by matching local intensity profiles. Elastical deformations are limited by setting bounds for the maximum variations in eigenmode space. The technique has been applied to automatically segment left and right hippocampus, thalamus, putamen, and globus pallidus from volumetric magnetic resonance scans taken from schizophrenia studies. The results have been validated by comparison of automatic segmentation with the results obtained by interactive expert segmentation.

Background estimation and segmentation based on range and color

Abstract: Segmentation of background and foreground objects in an image is based upon the joint use of both range and color data. Range-based data is largely independent of color image data, and hence not adversely affected by the limitations associated with color-based segmentation, such as shadows and similarly colored objects. Furthermore, color segmentation is complementary to range measurement in those cases where reliable range data cannot be obtained. These complementary sets of data are used to provide a multidimensional background estimation. The segmentation of a foreground object in a given frame of an image sequence is carried out by comparing the image frames with background statistics relating to range and normalized color, using the sets of statistics in a complementary manner.

Image segmentation using evolutionary computation

Abstract: Image segmentation denotes a process by which a raw input image is partitioned into nonoverlapping regions such that each region is homogeneous and the union of any two adjacent regions is heterogeneous. A segmented image is considered to be the highest domain-independent abstraction of an input image. The image segmentation problem is treated as one of combinatorial optimization. A cost function which incorporates both edge information and region gray-scale uniformity is defined. The cost function is shown to be multivariate with several local minima. The genetic algorithm, a stochastic optimization technique based on evolutionary computation, is explored in the context of image segmentation. A class of hybrid evolutionary optimization algorithms based on a combination of the genetic algorithm and stochastic annealing algorithms such as simulated annealing, microcanonical annealing, and the random cost algorithm is shown to exhibit superior performance as compared with the canonical genetic algorithm. Experimental results on gray-scale images are presented.

Visual segmentation by contextual influences via intra-cortical interactions in the primary visual cortex

Abstract: Stimuli outside classical receptive fields have been shown to exert a significant influence over the activities of neurons in the primary visual cortex. We propose that contextual influences are used for pre-attentive visual segmentation. The difference between contextual influences near and far from region boundaries makes neural activities near region boundaries higher than elsewhere, making boundaries more salient for perceptual pop-out. The cortex thus computes global region boundaries by detecting the breakdown of homogeneity or translation invariance in the input, using local intra-cortical interactions mediated by the horizontal connections. This proposal is implemented in a biologically based model of V1, and demonstrated using examples of texture segmentation and figure-ground segregation. The model is also the first that performs texture or region segmentation in exactly the same neural circuit that solves the dual problem of the enhancement of contours, as is suggested by experimental observations. The computational framework in this model is simpler than previous approaches, making it implementable by V1 mechanisms, though higher-level visual mechanisms are needed to refine its output. However, it easily handles a class of segmentation problems that are known to be tricky. Its behaviour is compared with psycho-physical and physiological data on segmentation, contour enhancement, contextual influences and other phenomena such as asymmetry in visual search.

A VOP generation tool: automatic segmentation of moving objects in image sequences based on spatio-temporal information

Abstract: The new MPEG-4 video coding standard enables content-based functionalities. In order to support the philosophy of the MPEG-4 visual standard, each frame of video sequences should be represented in terms of video object planes (VOPs). In other words, video objects to be encoded in still pictures or video sequences should be prepared before the encoding process starts. Therefore, it requires a prior decomposition of sequences into VOPs so that each VOP represents a moving object. This paper addresses an image segmentation method for separating moving objects from the background in image sequences. The proposed method utilizes the following spatio-temporal information. (1) For localization of moving objects in the image sequence, two consecutive image frames in the temporal direction are examined and a hypothesis testing is performed by comparing two variance estimates from two consecutive difference images, which results in an F-test. (2) Spatial segmentation is performed to divide each image into semantic regions and to find precise object boundaries of the moving objects. The temporal segmentation yields a change detection mask that indicates moving areas (foreground) and nonmoving areas (background), and spatial segmentation produces spatial segmentation masks. A combination of the spatial and temporal segmentation masks produces VOPs faithfully. This paper presents various experimental results.

Image Sequence Analysis via Partial Differential Equations

Abstract: This article deals with the problem of restoring and motion segmenting noisy image sequences with a static background Usually, motion segmentation and image restoration are considered separately in image sequence restoration Moreover, motion segmentation is often noise sensitive In this article, the motion segmentation and the image restoration parts are performed in a coupled way, allowing the motion segmentation part to positively influence the restoration part and vice-versa This is the key of our approach that allows to deal simultaneously with the problem of restoration and motion segmentation To this end, we propose a theoretically justified optimization problem that permits to take into account both requirements The model is theoretically justified Existence and unicity are proved in the space of bounded variations A suitable numerical scheme based on half quadratic minimization is then proposed and its convergence and stability demonstrated Experimental results obtained on noisy synthetic data and real images will illustrate the capabilities of this original and promising approach

Game-theoretic integration for image segmentation

Abstract: Robust segmentation of structures from an image is essential for a variety of image analysis problems. However, the conventional methods of region-based segmentation and gradient-based boundary finding are often frustrated by poor image quality. Here we propose a method to integrate the two approaches using game theory in an effort to form a unified approach that is robust to noise and poor initialization. This combines the perceptual notions of complete boundary information using edge data and shape priors with gray-level homogeneity using two computational modules. The novelty of the method is that this is a bidirectional framework, whereby both computational modules improve their results through mutual information sharing. A number of experiments were performed both on synthetic datasets and datasets of real images to evaluate the new approach and it is shown that the integrated method typically performs better than conventional gradient-based boundary finding.

Co-dimension 2 Geodesic Active Contours for MRA Segmentation

Abstract: Automatic and semi-automatic magnetic resonance angiography (MRA) segmentation techniques can potentially save radiologists large amounts of time required for manual segmentation and can facilitate further data analysis. The proposed MRA segmentation method uses a mathematical modeling technique which is well-suited to the complicated curve-like structure of blood vessels. We define the segmentation task as an energy minimization over all 3D curves and use a level set method to search for a solution. Our approach is an extension of previous level set segmentation techniques to higher co-dimension.

Toboggan-based intelligent scissors with a four-parameter edge model

Abstract: Intelligent Scissors is an interactive image segmentation tool that allows a user to select piece-wise globally optimal contour segments that correspond to a desired object boundary. We present a new and faster method of computing the optimal path by over-segmenting the image using tobogganing and then imposing a weighted planar graph on top of the resulting region boundaries. The resulting region-based graph is many times smaller than the previous pixel-based graph, thus providing faster graph searches and immediate user interaction. Further tobogganing provides an new systematic and predictable framework for computing edge model parameters, allowing subpixel localization as well as a measure of edge blur.

Algorithms for Fuzzy Segmentation

Abstract: Fuzzy segmentation is an effective way of segmenting out objects in pictures containing both random noise and shading. This is illustrated both on mathematically created pictures and on some obtained from medical imaging. A theory of fuzzy segmentation is presented. To perform fuzzy segmentation, a `connectedness map' needs to be produced. It is demonstrated that greedy algorithms for creating such a connectedness map are faster than the previously used dynamic programming technique. Once the connectedness map is created, segmentation is completed by a simple thresholding of the connectedness map. This approach is efficacious in instances where simple thresholding of the original picture fails.

Evaluation of texture segmentation algorithms

Abstract: This paper presents a method of evaluating unsupervised texture segmentation algorithms. The control scheme of texture segmentation has been conceptualized as two modular processes: (1) feature computation and (2) segmentation of homogeneous regions based on the feature values. Three feature extraction methods are considered: gray level co-occurrence matrix, Laws' texture energy and Gabor multi-channel filtering. Three segmentation algorithms are considered: fuzzy c-means clustering, square-error clustering and split-and-merge. A set of 35 real scene images with manually-specified ground truth was compiled. Performance is measured against ground truth on real images using region-based and pixel-based performance metrics.

Histogram clustering for unsupervised image segmentation

Abstract: This paper introduces a novel statistical mixture model for probabilistic grouping of distributional (histogram) data. Adopting the Bayesian framework, we propose to perform annealed maximum a posteriori estimation to compute optimal clustering solutions. In order to accelerate the optimization process, an efficient multiscale formulation is developed. We present a prototypical application of this method for the unsupervised segmentation of textured images based on local distributions of Gabor coefficients. Benchmark results indicate superior performance compared to K-means clustering and proximity-based algorithms.

An Architecture for a CBR Image Segmentation System

Abstract: Image Segmentation is a crucial step if extracting information from a digital image. It is not easy to set up the segmentation parameter so that it fits best over the entire set of images, which should be segmented. In the paper, we propose a novel architecture for image segmentation method based on CBR, which can adapt to changing image qualities and environmental conditions. We describe the whole architecture, the methods used for the various components of the systems and show how it performs on medical images.

An integrated approach for content-based video object segmentation and retrieval

Abstract: Object-based video data representations enable unprecedented functionalities of content access and manipulation. We present an integrated approach using region-based analysis for semantic video object segmentation and retrieval. We first present an active system that combines low-level region segmentation with user inputs for defining and tracking semantic video objects. The proposed technique is novel in using an integrated feature fusion framework for tracking and segmentation at both region and object levels. Experimental results and extensive performance evaluation show excellent results compared to existing systems. Building upon the segmentation framework, we then present a unique region-based query system for semantic video object. The model facilitates powerful object search, such as spatio-temporal similarity searching at multiple levels.

Motion segmentation based on factorization method and discriminant criterion

Abstract: A motion segmentation algorithm based on factorization method and discriminant criterion is proposed. This method uses a feature with the most useful similarities for grouping, selected using motion information calculated by factorization method and discriminant criterion. A group is extracted based on discriminant analysis for the selected feature's similarities. The same procedure is applied recursively to the remaining features to extract other groups. This grouping is robust against noise and outliers because features with no useful information are automatically rejected. Numerical computation is simple and stable. No prior knowledge is needed on the number of objects. Experimental results are shown for synthetic data and real image sequences.

Bias field estimation and adaptive segmentation of MRI data using a modified fuzzy C-means algorithm

Abstract: In this paper, we present a novel algorithm for adaptive fuzzy segmentation of MRI data and estimation of intensity inhomogeneities using fuzzy logic. MRI intensity inhomogeneities can be attributed to imperfections in the RF coils or some problems associated with the acquisition sequences. The result is a slowly-varying shading artifact over the image that can produce errors with conventional intensity-based classification. Our algorithm is formulated by modifying the objective function of the standard fuzzy c-means (FCM) algorithm to compensate for such inhomogeneities and to allow the labeling of a pixel (voxel) to be influenced by the labels in its immediate neighborhood. The neighborhood effect acts as a regularizer and biases the solution towards piecewise-homogeneous labelings. Such a regularization is useful in segmenting scans corrupted by salt and pepper noise. Experimental results on both synthetic images and MR data are given to demonstrate the effectiveness and efficiency of the proposed algorithm.

Simplified segmentation for compound image compression

Abstract: There are three basic segmentation schemes for compound image compression: object-based, layer-based, and block-based. This paper discusses the relative advantages of each scheme and architecture, and studies the use of fast classification techniques for a segmentation that can be used together with a chosen compression architecture. Particularly, we consider classification techniques working on approximate object boundaries, which reaches the localization and precision of the segmentation, but in exchange allows faster, one-pass segmentation, low memory requirements, and segmentation map that is better matched to existing compression methods. We show numerical results obtained on a printer application environment, where rigorous standards of visual quality have to be satisfied.

A fast and robust moving object segmentation in video sequences

Abstract: The new video coding standard MPEG-4 is enabling content-based functionalities as well as high coding efficiency considering shape information of moving objects. A novel algorithm for segmentation of moving objects in video sequences and VOP (video object planes) extraction is presented. This algorithm begins with a robust double edge map from the difference between two successive frames. After removing edges which belong to previous frame, the edge map, named ME (moving edge) is used to extract VOP. The proposed algorithm is evaluated for MPEG-4 test sequences and produces promising results.

Disparity/segmentation analysis: matching with an adaptive window and depth-driven segmentation

Abstract: Most of the emerging content-based multimedia technologies are based on efficient methods to solve machine early vision tasks. Among other tasks, object segmentation is perhaps the most important problem in single image processing, whereas pixel-correspondence estimation is the crucial task in multiview image analysis. The solution of these two problems is the key for the development of the majority of leading-edge interactive video-communication technologies and telepresence systems. In this paper, we present a robust framework comprised of joined pixel-correspondence estimation and image segmentation in video sequences taken simultaneously from different perspectives. An improved concept for stereo-image analysis based on block matching with a local adaptive window is introduced. The size and shape of the reference window is calculated adaptively according to the degree of reliability of disparities estimated previously. Considerable improvements are obtained just within object borders or image areas that become occluded by applying the proposed block-matching model. An initial object segmentation is obtained by merging neighboring sampling positions with disparity vectors of similar size and direction. Starting from this initial segmentation, true object borders are detected using a contour-matching algorithm. In this process, the contour of the initial segmentation is taken as a reference pattern, and the edges extracted from the original images, by applying a multiscale algorithm, are the candidates for the true object contour. The performance of the introduced methods has been verified.

Model-based three-dimensional medical image segmentation

Abstract: In this thesis, we describe a knowledge-based approach to segmentation of three-dimensional medical imagery. This approach emphasizes the role of four complementary kinds of knowledge or models in medical segmentation: intensity models that describe the gray-level appearance of different tissues, imaging models that describe the characteristics of the imaging process, geometric models that describe the spatial relationships between structures, and shape models that describe the shapes of individual structures. We instantiate this approach in a novel Bayesian method for segmentation of Magnetic Resonance images. This method uses Expectation-Maximization to iteratively estimate the classification of an input image. Intensity models and geometric models are formulated as probability distributions, and are used as priors in the Bayesian classification. A well-known imaging model is used to account for the inhomogeneities due to the MR acquisition process. A Gibbs model is used to impose piecewise homogeneity of tissue class, which reduces the fragmentation effects in the segmentation that are caused by the presence of thermal noise in MR. Geometric relationships are described as spatially varying probability distributions on geometric primitives such as distances and normals that relate pairs of structures, and are constructed from segmented training data. We demonstrate the results of using this segmentation method in two application areas: segmentation of bones and cartilage from knee MRI, and segmentation of white matter, gray matter, fluid, and skin from brain MRI. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)

Line-based recognition using a multidimensional Hausdorff distance

Abstract: A line-feature-based approach for model based recognition using a four-dimensional Hausdorff distance is proposed. This approach reduces the problem of finding the rotation, scaling, and translation transformations between a model and an image to the problem of finding a single translation minimizing the Hausdorff distance between two sets of points in a four-dimensional space. The implementation of the proposed algorithm can be naturally extended to higher dimensional spaces to efficiently find correspondences between n-dimensional patterns. The method performance and sensitivity to segmentation problems are quantitatively characterized using an experimental protocol with simulated data. It is shown that the algorithm performs well, is robust to occlusion and outliers, and that it degrades nicely as the segmentation problems increase. Experiments with real images are also presented.

Rule-based moving object segmentation

Abstract: A rule-based method which detects and tracks the moving objects in video frames in an automated way is invented. The method can be used in object based image sequence compression applications. Motion of pixels between two consecutive frames are estimated using a block based motion estimation method, and the resultant dense motion vector field is segmented. Using the same method, a second segmentation is achieved based on partitioning of the image according to color values of the pixels. The image, which is formed by the translation of the final segmentation results of the previous frame using the estimated motion vectors, is used as the third segmentation. By the help of a sequence of rules, which uses the three different segmentation masks as its inputs, detection and tracking of moving objects in the scene is achieved within accurate boundaries; the problems caused by occlusion or uncovered background are insignificant.