scispace - formally typeset
Search or ask a question

Showing papers on "Image segmentation published in 1991"


Journal ArticleDOI
TL;DR: A fast and flexible algorithm for computing watersheds in digital gray-scale images is introduced, based on an immersion process analogy, which is reported to be faster than any other watershed algorithm.
Abstract: A fast and flexible algorithm for computing watersheds in digital gray-scale images is introduced. A review of watersheds and related motion is first presented, and the major methods to determine watersheds are discussed. The algorithm is based on an immersion process analogy, in which the flooding of the water in the picture is efficiently simulated using of queue of pixel. It is described in detail provided in a pseudo C language. The accuracy of this algorithm is proven to be superior to that of the existing implementations, and it is shown that its adaptation to any kind of digital grid and its generalization to n-dimensional images (and even to graphs) are straightforward. The algorithm is reported to be faster than any other watershed algorithm. Applications of this algorithm with regard to picture segmentation are presented for magnetic resonance (MR) imagery and for digital elevation models. An example of 3-D watershed is also provided. >

4,983 citations


Journal ArticleDOI
TL;DR: The authors present a fuzzy validity criterion based on a validity function which identifies compact and separate fuzzy c-partitions without assumptions as to the number of substructures inherent in the data.
Abstract: The authors present a fuzzy validity criterion based on a validity function which identifies compact and separate fuzzy c-partitions without assumptions as to the number of substructures inherent in the data. This function depends on the data set, geometric distance measure, distance between cluster centroids and more importantly on the fuzzy partition generated by any fuzzy algorithm used. The function is mathematically justified via its relationship to a well-defined hard clustering validity function, the separation index for which the condition of uniqueness has already been established. The performance of this validity function compares favorably to that of several others. The application of this validity function to color image segmentation in a computer color vision system for recognition of IC wafer defects which are otherwise impossible to detect using gray-scale image processing is discussed. >

3,237 citations


Journal ArticleDOI
TL;DR: A texture segmentation algorithm inspired by the multi-channel filtering theory for visual information processing in the early stages of human visual system is presented, which is based on reconstruction of the input image from the filtered images.

2,351 citations


Journal ArticleDOI
Gabriel Taubin1
TL;DR: It is shown how this unified representation can be used for object recognition, object position estimation, and segmentation of objects into meaningful subobjects, that is, the detection of 'interest regions' that are more complex than high curvature regions and, hence, more useful as features for object Recognition.
Abstract: The author addresses the problem of parametric representation and estimation of complex planar curves in 2-D surfaces in 3-D, and nonplanar space curves in 3-D. Curves and surfaces can be defined either parametrically or implicitly, with the latter representation used here. A planar curve is the set of zeros of a smooth function of two variables x-y, a surface is the set of zeros of a smooth function of three variables x-y-z, and a space curve is the intersection of two surfaces, which are the set of zeros of two linearly independent smooth functions of three variables x-y-z For example, the surface of a complex object in 3-D can be represented as a subset of a single implicit surface, with similar results for planar and space curves. It is shown how this unified representation can be used for object recognition, object position estimation, and segmentation of objects into meaningful subobjects, that is, the detection of 'interest regions' that are more complex than high curvature regions and, hence, more useful as features for object recognition. >

1,155 citations


Journal ArticleDOI
TL;DR: A multiple resolution algorithm is presented for segmenting images into regions with differing statistical behavior and an algorithm is developed for determining the number of statistically distinct regions in an image and estimating the parameters of those regions.
Abstract: A multiple resolution algorithm is presented for segmenting images into regions with differing statistical behavior. In addition, an algorithm is developed for determining the number of statistically distinct regions in an image and estimating the parameters of those regions. Both algorithms use a causal Gaussian autoregressive model to describe the mean, variance, and spatial correlation of the image textures. Together, the algorithms can be used to perform unsupervised texture segmentation. The multiple resolution segmentation algorithm first segments images at coarse resolution and then progresses to finer resolutions until individual pixels are classified. This method results in accurate segmentations and requires significantly less computation than some previously known methods. The field containing the classification of each pixel in the image is modeled as a Markov random field. Segmentation at each resolution is then performed by maximizing the a posteriori probability of this field subject to the resolution constraint. At each resolution, the a posteriori probability is maximized by a deterministic greedy algorithm which iteratively chooses the classification of individual pixels or pixel blocks. The unsupervised parameter estimation algorithm determines both the number of textures and their parameters by minimizing a global criterion based on the AIC information criterion. Clusters corresponding to the individual textures are formed by alternately estimating the cluster parameters and repartitioning the data into those clusters. Concurrently, the number of distinct textures is estimated by combining clusters until a minimum of the criterion is reached. >

423 citations


Journal ArticleDOI
TL;DR: A clustering algorithm based on the minimum volume ellipsoid (MVE) robust estimator is proposed that was successfully applied to several computer vision problems formulated in the feature space paradigm: multithresholding of gray level images, analysis of the Hough space, and range image segmentation.
Abstract: A clustering algorithm based on the minimum volume ellipsoid (MVE) robust estimator is proposed. The MVE estimator identifies the least volume region containing h percent of the data points. The clustering algorithm iteratively partitions the space into clusters without prior information about their number. At each iteration, the MVE estimator is applied several times with values of h decreasing from 0.5. A cluster is hypothesized for each ellipsoid. The shapes of these clusters are compared with shapes corresponding to a known unimodal distribution by the Kolmogorov-Smirnov test. The best fitting cluster is then removed from the space, and a new iteration starts. Constrained random sampling keeps the computation low. The clustering algorithm was successfully applied to several computer vision problems formulated in the feature space paradigm: multithresholding of gray level images, analysis of the Hough space, and range image segmentation. >

290 citations


Journal ArticleDOI
TL;DR: The thresholding method, called the local intensity gradient (LIG) method, was implemented in C using a Sun4 host running UNIX and properly thresholds a larger set of images than does any other method examined over the sample images tested.
Abstract: The thresholding method involves first locating objects in an image by using the intensity gradient, then noting the levels that correspond to the objects in various areas of the image, and finally using these levels as initial guesses at a threshold. This method is capable of thresholding images that have been produced in the context of variable illumination. The thresholding method, called the local intensity gradient (LIG) method, was implemented in C using a Sun4 host running UNIX. The LIG method was compared against iterative selection (IS), gray level histograms (GLHs) and two correlation based algorithms on a dozen sample images under three different illumination effects. Overall, the LIG method, while it takes significantly longer, properly thresholds a larger set of images than does any other method examined over the sample images tested. >

189 citations


Journal ArticleDOI
TL;DR: The two-dimensional Gabor filters possess strong optimality properties for this task, and local spatial frequency estimation approaches are suggested that use the responses as constraints in estimating the locally emergent texture frequencies.
Abstract: A model for texture analysis and segmentation using multiple oriented channel filters is analyzed in the general framework. Several different arguments are applied leading to the conclusion that the two-dimensional Gabor filters possess strong optimality properties for this task. Properties of the multiple-channel segmentation approach are analyzed. In particular, perturbations of textures from an ideal model are found to have important effects on the segmentation that can usually be ameliorated by simply preceding the segmentation process by a logarithmic operation and using a low-pass postfilter prior to making region assignments. The difficult problems of space-variant textures and multiple component textures are also considered. Local spatial frequency estimation approaches are suggested that use the responses as constraints in estimating the locally emergent texture frequencies. Complex texture aggregates containing multiple shared frequency components can be analyzed if the textures are distinct and few in number. >

187 citations


Journal Article
Huang Yumin1
01 Jan 1991-Robot
TL;DR: An algorithm of color image understanding which segments the image after analyzing sur-faces with color variations due to lighting condition and object colors and gives forth a physical des-cription of imaging process, including intrinsic images, segmented image, the color of light and objects.
Abstract: We present an algorithm of color image understanding which segments the image after analyzing sur-faces with color variations due to lighting condition and object colors. The work is based on dichromaticreflection model according to the strategy of hypothesis plus test, following the continuity of image and thefeature of color clusters, the algorithm completes the image segmentation and gives forth a physical des-cription of imaging process, including intrinsic images, segmented image, the color of light and objects. Re-flecting respectively the propertics of light condition and every objects, both matte image and highlight im-age compose the intrinsic images.

183 citations


Proceedings ArticleDOI
07 Oct 1991
TL;DR: In this article, the authors address the problem of motion segmentation using the singular value decomposition of a feature track matrix and show that, under general assumptions, the number of numerically nonzero singular values can be used to determine the count of motions.
Abstract: The authors address the problem of motion segmentation using the singular value decomposition of a feature track matrix. It is shown that, under general assumptions, the number of numerically nonzero singular values can be used to determine the number of motions. Furthermore, motions can be separated using the right singular vectors associated with the nonzero singular values. A relationship is derived between a good segmentation, the number of nonzero singular values in the input and the sum of the number of nonzero singular values in the segments. The approach is demonstrated on real and synthetic examples. The paper ends with a critical analysis of the approach. >

182 citations


Journal ArticleDOI
Norbert Diehl1
TL;DR: In this paper, a method for segmenting video scenes hierarchically into several differently moving objects and subobjects is presented, where both contour and texture information from the single images and information from successive images are used to split up a scene into various objects.
Abstract: This contribution presents a method for segmenting video scenes hierarchically into several differently moving objects and subobjects. To this end, both contour and texture information from the single images and information from successive images is used to split up a scene into various objects. Furthermore, each of these objects is characterized by a transform h ( x,T ) with a parameter vector T which implicitely describes the surface shape and the three-dimensional motion of the objects in the scene. In order to estimate T of these transforms, an efficient algorithm is introduced. Thus, we obtain an object-oriented segmentation and a prediction of the image contents from one image to the next, which can be used in low bit-rate image coding.

Journal ArticleDOI
TL;DR: This procedure can be used in a preliminary diagnosis in brain surgery without much effort of users, because of whole procedure including threshold selection and segmentation is performed automatically for rendering a three-dimensional image of soft-tissue's surface on a graphic terminal.

Journal ArticleDOI
TL;DR: In this article, a Markov random field (MRF) formalism is proposed to unify several approaches to image segmentation in early vision under a common framework, in which the probability distributions are specified by an energy function.
Abstract: We attempt to unify several approaches to image segmentation in early vision under a common framework. The Bayesian approach is very attractive since: (i) it enables the assumptions used to be explicitly stated in the probability distributions, and (ii) it can be extended to deal with most other problems in early vision. Here, we consider the Markov random field formalism, a special case of the Bayesian approach, in which the probability distributions are specified by an energy function. We show that: (i) our discrete formulations for the energy function is closely related to the continuous formulation; (ii) by using the mean field (MF) theory approach, introduced by Geiger and Girosi [1991], several previous attempts to solve these energy functions are effectively equivalent; (iii) by varying the parameters of the energy functions we can obtain connections to nonlinear diffusion and minimal description length approaches to image segmentation; and (iv) simple modifications to the energy can give a direct relation to robust statistics or can encourage hysteresis and nonmaximum suppression.

Proceedings ArticleDOI
16 Jun 1991
TL;DR: The objective of this paper is to extend the Otsu method to the 2-dimensional histogram and find that the proposed method performs much better when the images are corrupted by noise.
Abstract: One of the most useful thresholding techniques using gray-level histogram of an image is the Otsu method. The objective of this paper is to extend it to the 2-dimensional histogram. The 2-dimensional Otsu method utilizes the gray-level information of each pixel and its spatial correlation information within the neighborhood. This method was compared with the 1-dimensional Otsu method. It was found that the proposed method performs much better when the images are corrupted by noise. >

Proceedings ArticleDOI
07 Oct 1991
TL;DR: A layered model of scene segmentation based on explicitly representing the support of a homogeneous region is introduced, which employs parallel robust estimation techniques, and uses a minimal-covering optimization to estimate the number of objects in the scene.
Abstract: In order to recover an accurate representation of a scene containing multiple moving objects, one must use estimation methods that can recover both model parameters and segmentation at the same time. Traditional approaches to this problem rely on an edge-based discontinuity model, and have problems with transparent phenomena. The authors introduce a layered model of scene segmentation based on explicitly representing the support of a homogeneous region. The model employs parallel robust estimation techniques, and uses a minimal-covering optimization to estimate the number of objects in the scene. Using a simple direct motion model of translating objects, they successfully segment real image sequences containing multiple motions. >

Proceedings ArticleDOI
07 Oct 1991
TL;DR: In this paper, a method for segmenting monocular images of people in motion from a cinematic sequence of frames is described, based on image intensities, motion, and an object model.
Abstract: A method for segmenting monocular images of people in motion from a cinematic sequence of frames is described. This method is based on image intensities, motion, and an object model-i.e., a model of the image of a person in motion. Though each part of a person may move in different directions at any instant, the time averaged motion of all parts must converge to a global average value over a few seconds. People in an image may be occluded by other people, and usually it is not easy to detect their boundaries. These boundaries can be detected with motion information if they move in different directions, even if there are almost no apparent differences among object intensities or colors. Each image of a person in a scene usually can be divided into several parts, each with distinct intensities or colors. The parts of a person can be merged into a single group by an iterative merging algorithm based on the object model and the motion information because the parts move coherently. This merging is analogous to the property of perceptual grouping in human visual perception of motion. Experiments based on a sequence of complex real scenes produced results that are supportive of the authors approach to the segmentation of people in motion. >

Journal ArticleDOI
TL;DR: An adaptive split-and-merge image segmentation algorithm based on characteristic features and a hypothesis model is proposed and one of the key processes, the determination of region homogeneity, is treated as a sequence of decision problems in terms of predicates in the hypothesis model.

Journal ArticleDOI
TL;DR: The image segmentation problem is solved by extracting kernel information from the input image to provide an initial interpretation of the image and by using a knowledge-based hierarchical classifier to discriminate between major land-cover types in the study area.
Abstract: A knowledge-based approach for Landsat image segmentation is proposed. The image segmentation problem is solved by extracting kernel information from the input image to provide an initial interpretation of the image and by using a knowledge-based hierarchical classifier to discriminate between major land-cover types in the study area. The proposed method is designed in such a way that a Landsat image can be segmented and interpreted without any prior image-dependent information. The general spectral land-cover knowledge is constructed from the training land-cover data, and the road information of an image is obtained through a road-detection program. >

Proceedings ArticleDOI
03 Jun 1991
TL;DR: The problem of measuring the motion of deformable objects from image sequences is addressed by modeling the overall boundary of the object as a deformable contour and then tracking local segments of the contour through the temporal sequence, resulting in a composite flow field over the entire sequence.
Abstract: The problem of measuring the motion of deformable objects from image sequences is addressed. The approach is based upon modeling the overall boundary of the object as a deformable contour and then tracking local segments of the contour through the temporal sequence. Motion computation involves first matching the local segments between pairs of contours by minimizing the deformation between the segments using a measure of bending energy. Results from the match process are incorporated into an optimization functional, along with a general smoothness term, whose local minimum results in a smooth flow field that is consistent with the match data. The computation is performed for all pairs of frames in the temporal sequence, resulting in a composite flow field over the entire sequence. The technique is applied to synthetic contour sequences and the problem of tracking left ventricular (LV) endocardial motion from medical image sequences. >

Patent
27 Jun 1991
TL;DR: In this paper, a method for rendering scene information in images having a large dynamic range is proposed, i.e. sunny and shady areas. But the method is not suitable for outdoor scenes.
Abstract: The invention concerns a method for rendering scene information in images having a large dynamic range, i.e. sunny and shady areas. The method takes particular advantage of image segmentation and computations employed in compression of images for electronic still photography. In distinguishing large areas, the method selectively adjusts the brightness of all portions of the area without necessarily preserving contrast which avoids halo artifacts. Those portions in areas of intermediate size are subjected to a smoothing feature which avoids the production of artifacts in the form of a line at the boundary.

Journal ArticleDOI
TL;DR: A 3-D segmentation algorithm is presented, based on a split, merge and group approach, that uses a mixed (oct/quad)tree implementation and a number of homogeneity criteria is discussed and evaluated.

Journal ArticleDOI
TL;DR: A unified theory is developed for the mathematical description of the morphological skeleton decomposition of discrete and binary images through repeated erosions and set transformations.
Abstract: A general theory for the morphological representation of discrete and binary images is presented. The basis of this theory relies on the generation of a set of nonoverlapping segments of an image via repeated erosions and set transformations, which in turn produces a decomposition that guarantees exact reconstruction. The relationship between the proposed representation and some existing shape analysis tools (e.g., discrete size transform, pattern spectrum, skeletons) is investigated, thus introducing the representation as the basis of a unified theory for geometrical image analysis. Particular cases of the general representation scheme are shown to yield a number of useful image decompositions which are directly related to various forms of morphological skeletons. The relationship between the representation and the various forms of morphological skeletons is studied. As a result of this study, a unified theory is developed for the mathematical description of the morphological skeleton decomposition of discrete and binary images. >

Proceedings ArticleDOI
03 Jun 1991
TL;DR: An integrated segmentation technique that combines the strengths of the previous two techniques while eliminating their weaknesses is proposed and is truly unsupervised, since it eliminates the need for knowing the exact number of texture categories in the image.
Abstract: Multichannel filtering techniques are presented for obtaining both region- and edge-based segmentations of textured images. The channels are represented by a bank of even-symmetric Gabor filters that nearly uniformly covers the spatial-frequency domain. Feature images are obtained by subjecting each (selected) filtered image to a nonlinear transformation and computing a measure of energy around each pixel. Region-based segmentations are obtained by using a square-error clustering algorithm. Edge-based segmentations are obtained by applying an edge detector to each feature image and combining their magnitude responses. An integrated segmentation technique that combines the strengths of the previous two techniques while eliminating their weaknesses is proposed. The integrated approach is truly unsupervised, since it eliminates the need for knowing the exact number of texture categories in the image. >

Journal ArticleDOI
TL;DR: A method is described for reducing the information contained in an image sequence, while retaining the information necessary for the interpretation of the sequence by a human observer.
Abstract: A method is described for reducing the information contained in an image sequence, while retaining the information necessary for the interpretation of the sequence by a human observer. The method consists of first locating the redundant information, reducing the degree of redundancy, and coding the result. The sequence is treated as a single 3D data volume, the voxels of which are grouped into several regions, obtained by a 3D split and merge algorithm. The information is coded by representing the borders of the regions using a pyramidal structure in the x, y, t space. The coefficients of the approximating polynomials are coded in a straightforward manner. For 256*256 pixel, 25 frame/s image sequences, compressions allowing transmission rates near 64 kbit/s are obtained. >

Proceedings ArticleDOI
03 Jun 1991
TL;DR: An algorithm that systematically uses nonuniform smoothing to find boundary components in the form of connected, regularized curves is presented.
Abstract: A global model which integrates three sequential steps for segmenting an image, namely, noise-filtering, local edge-detection, and integration of local edges into object boundaries, is described. The model overcomes some of the difficulties inherent in earlier global models, particularly their tendency to oversegment, and the lack of practical numerical algorithms for implementing them. The model consists of two coupled elliptic functionals, one for smoothing out the noise, and the other for boundary detection. The latter is obtained by regularizing the usual pointwise thresholding employed for boundary detection. The first variation of these functionals leads to coupled system of diffusion equations which are implemented by a simple finite difference scheme. The scheme may easily be converted into a parallel algorithm. >

Journal ArticleDOI
TL;DR: A system for automatically determining the contour of the left ventricle (LV) and its bounded area, from transesophageal echocardiographic (TEE) images is presented.
Abstract: A system for automatically determining the contour of the left ventricle (LV) and its bounded area, from transesophageal echocardiographic (TEE) images is presented. It uses knowledge of both heart anatomy and echocardiographic imaging to guide the selection of image processing methodologies for thresholding, edge detection, and contour following and the center-based boundary-finding technique to extract the contour of the LV region. To speed up the processing a rectangular region of interest from a TEE picture is first isolated and then reduced to a coarse version, one-ninth original size. All processing steps, except the final contour edge extraction, are performed on this reduced image. New methods developed for automatic threshold selection, region segmentation, noise removal, and region center determination are described. >

Journal ArticleDOI
TL;DR: An improved method of automatic image segmentation, the principal component transformation split-and-merge clustering (PCTSMC) algorithm, is presented and applied to cloud screening of both nighttime and daytime AVHRR data.

Proceedings ArticleDOI
03 Jun 1991
TL;DR: A technique for constructing shape representation from images using free-form deformable surfaces is presented, which is used to segment objects even in cluttered or unstructured environments.
Abstract: A technique for constructing shape representation from images using free-form deformable surfaces is presented. The authors model an object as a closed surface that is deformed subject to attractive fields generated by input data points and features. Features affect the global shape of the surface, while data points control its local shape. This approach is used to segment objects even in cluttered or unstructured environments. The algorithm is general in that it makes few assumptions on the type of features, the nature of the data, and the type of objects. Results for a wide range of applications are presented: reconstruction of smooth isolated objects such as human faces, reconstruction of structured objects such as polyhedra, and segmentation of complex scenes with mutually occluding objects. The algorithm has been successfully tested using data from different sensors including grey-coding range finders and video cameras, using one or several images. >

Proceedings ArticleDOI
03 Jun 1991
TL;DR: A split-and-merge algorithm is proposed for the segmentation of the digitized surface of a range image into planar regions, which allows a better adaptation of the range image segmentation to the surface boundaries.
Abstract: A split-and-merge algorithm is proposed for the segmentation of the digitized surface of a range image into planar regions. The geometric data structure used is a triangular tessellation of image domain. This data structure, combined with an adaptive surface approximation technique, allows a better adaptation of the range image segmentation to the surface boundaries. It also provides an efficient neighborhood referencing mechanism, thus resulting in a fast algorithm. >

Proceedings ArticleDOI
07 Oct 1991
TL;DR: A closed-form solution for motion estimation from first-order flow in two 'distinct' image regions is described, which is more robust than other techniques that require the knowledge of the full flow or information up to the second-order terms of it.
Abstract: A closed-form solution for motion estimation from first-order flow in two 'distinct' image regions is described. Uniqueness is guaranteed when these correspond to surface patches with different normal vectors. given an image sequence, the authors show how the image many be segmented into regions with the necessary properties, optical flow is computed for these regions, and motion parameters are computed. The method can be applied to arbitrary scenes and camera motion. The authors explain why it is more robust than other techniques that require the knowledge of the full flow or information up to the second-order terms of it. Experimental results are presented to support the theoretical derivations. >