Showing papers on "Segmentation published in 1987"
TL;DR: The Boundary Contour System (BCS) as discussed by the authors is a real-time visual processing theory that is used to analyze and explain a wide variety of perceptual grouping and segmentation phenomena, including textured images, randomly defined images, and images built up from periodic scenic elements.
Abstract: A real-time visual processing theory is used to analyse and explain a wide variety of perceptual grouping and segmentation phenomena, including the grouping of textured images, randomly defined images, and images built up from periodic scenic elements. The theory explains how “local” feature processing and “emergent” features work together to segment a scene, how segmentations may arise across image regions which do not contain any luminance differences, how segmentations may override local image properties in favor of global statistical factors, and why segmentations that powerfully influence object recognition may be barely visible or totally invisible. Network interactions within a Boundary Contour System (BCS), a Feature Contour System (FCS), and an Object Recognition System (ORS) are used to explain these phenomena. The BCS is defined by a hierarchy of orientationally tuned interactions, which can be divided into two successive subsystems, called the OC Filter and the CC Loop. The OC Filter contains two successive stages of oriented receptive fields which are sensitive to different properties of image contrasts. The OC Filter generates inputs to the CC Loop, which contains successive stages of spatially short-range competitive interactions and spatially long-range cooperative interactions. Feedback between the competitive and cooperative stages synthesizes a global context-sensitive segmentation from among the many possible groupings of local featural elements. The properties of the BCS provide a unified explanation of several ostensibly different Gestalt rules. The BCS also suggests explanations and predictions concerning the architecture of the striate and prestriate visual cortices. The BCS embodies new ideas concerning the foundations of geometry, on-line statistical decision theory, and the resolution of uncertainty in quantum measurement systems. Computer simulations establish the formal competence of the BCS as a perceptual grouping system. The properties of the BCS are compared with probabilistic and artificial intelligence models of segmentation. The total network suggests a new approach to the design of computer vision systems, and promises to provide a universal set of rules for perceptual grouping of scenic edges, textures, and smoothly shaded regions.
547 citations
TL;DR: A procedure to detect connected planar, convex, and concave surfaces of 3-D objects by segments the range image into surface patches by a square error criterion clustering algorithm using surface points and associated surface normals.
Abstract: The recognition of objects in three-dimensional space is a desirable capability of a computer vision system. Range images, which directly measure 3-D surface coordinates of a scene, are well suited for this task. In this paper we report a procedure to detect connected planar, convex, and concave surfaces of 3-D objects. This is accomplished in three stages. The first stage segments the range image into ``surface patches'' by a square error criterion clustering algorithm using surface points and associated surface normals. The second stage classifies these patches as planar, convex, or concave based on a non-parametric statistical test for trend, curvature values, and eigenvalue analysis. In the final stage, boundaries between adjacent surface patches are classified as crease or noncrease edges, and this information is used to merge compatible patches to produce reasonable faces of the object(s). This procedure has been successfully applied to a large number of real and synthetic images, four of which we present in this paper.
482 citations
TL;DR: In this article, five main bases are discussed: geographic, demographic, psychographic, behaviouristic and image, followed by an overview of the main techniques used to establish and verify segments, including automatic interaction detector, conjoint analysis, multidimensional scaling and canonical analysis.
Abstract: It is important to remain creative when conducting segmentation research, as many different ways to segment a market can exist. Five main bases are discussed: geographic, demographic, psychographic, behaviouristic and image. This is followed by an overview of the main techniques used to establish and verify segments, including automatic interaction detector, conjoint analysis, multidimensional scaling and canonical analysis.
403 citations
TL;DR: To compute the flow predicted by the segmentation, a recent method for reconstructing the motion and orientation of planar surface facets is used and the search for the globally optimal segmentation is performed using simulated annealing.
Abstract: This paper presents results from computer experiments with an algorithm to perform scene disposition and motion segmentation from visual motion or optic flow. The maximum a posteriori (MAP) criterion is used to formulate what the best segmentation or interpretation of the scene should be, where the scene is assumed to be made up of some fixed number of moving planar surface patches. The Bayesian approach requires, first, specification of prior expectations for the optic flow field, which here is modeled as spatial and temporal Markov random fields; and, secondly, a way of measuring how well the segmentation predicts the measured flow field. The Markov random fields incorporate the physical constraints that objects and their images are probably spatially continuous, and that their images are likely to move quite smoothly across the image plane. To compute the flow predicted by the segmentation, a recent method for reconstructing the motion and orientation of planar surface facets is used. The search for the globally optimal segmentation is performed using simulated annealing.
365 citations
TL;DR: Two conceptually new algorithms are presented for segmenting textured images into regions in each of which the data are modeled as one of C MRF's, designed to operate in real time when implemented on new parallel computer architectures that can be built with present technology.
Abstract: The modeling and segmentation of images by MRF's (Markov random fields) is treated. These are two-dimensional noncausal Markovian stochastic processes. Two conceptually new algorithms are presented for segmenting textured images into regions in each of which the data are modeled as one of C MRF's. The algorithms are designed to operate in real time when implemented on new parallel computer architectures that can be built with present technology. A doubly stochastic representation is used in image modeling. Here, a Gaussian MRF is used to model textures in visible light and infrared images, and an autobinary (or autoternary, etc.) MRF to model a priori information about the local geometry of textured image regions. For image segmentation, the true texture class regions are treated either as a priori completely unknown or as a realization of a binary (or ternary, etc.) MRF. In the former case, image segmentation is realized as true maximum likelihood estimation. In the latter case, it is realized as true maximum a posteriori likelihood segmentation. In addition to providing a mathematically correct means for introducing geometric structure, the autobinary (or ternary, etc.) MRF can be used in a generative mode to generate image geometries and artificial images, and such simulations constitute a very powerful tool for studying the effects of these models and the appropriate choice of model parameters. The first segmentation algorithm is hierarchical and uses a pyramid-like structure in new ways that exploit the mutual dependencies among disjoint pieces of a textured region.
268 citations
TL;DR: A working system for segmenting images of complex scenes is presented that integrates techniques that have evolved out of many years of research in low-level image segmentation at the University of Massachusetts and elsewhere.
Abstract: THIS PAPER DESCRIBES A WORKING SYSTEM FOR SEGMENTING IMAGES OF COMPLEX SCENES. THE SYSTEM HAS EVOLVED OUT OF MANY YEARS OF RESEARCH IN LOW-LEVEL IMAGE SEGMENTATION AT THE UNIVERSITY OF MASSACHUSETTS. SEGMENTATIONS PRODUCED BY THE SYSTEM ARE USED EXTENSIVELY IN THE IMAGE INTERPRETATION WORK HERE. THE SYSTEM FIRST PRODUCES SEGMENTATIONS BASED UPON AN ANALYSIS OF SPATIALLY LOCALIZED FEATURE HISTOGRAMS. THESE SEGMENTATIONS ARE THEN POST-PROCESSED WITH A REGION MERGING ALGORITHM. A SIMPLE EXTENSION OF THE LOCAL HISTOGRAM ALGORITHM TO MULTIPLE FEATURES IS PRESENTED. ISSUES OF PARAMETER SELECTION FOR THE LOCAL HISTOGRAM SEGMENTATION ALGORITHM ARE ADDRESSED BY PRESENTING A MAPPING FROM THE MULTI-DIMENSIONAL PARAMETER SPACE TO A ONE DIMENSIONAL `SENSITIVITY'' SPACE. RESULTS ARE INCLUDED WHICH DEMONSTRATE THE ROBUST CHARACTER OF THE ALGORITHMS WHEN APPLIED TO OUTDOOR AND AERIAL IMAGERY.
180 citations
TL;DR: A new simple and computationally efficient approach to image segmentation via recursive region splitting and merging is presented, based on a generalization of a two-class gradient relaxation method.
116 citations
01 Feb 1987-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: The results of psychophysical experiments suggest the existence of a hierarchy of visual features based on the relations between image contours which correlate with the structure of the physical world that is of value for visual perception.
Abstract: The results of psychophysical experiments suggest the existence of a hierarchy of visual features based on the relations between image contours. The human visual system appears to be preattentively, selectively sensitive to image contours which contain certain of these features. These results can be used to develop computer vision algorithms for: (1) the selective enhancement of image contours which correlate with their perceptual significance; and (2) the segmentation of boundary images into sets which have a high probability of depicting a single object. The extreme simplicity of the algorithms, as well as their ability to generate perceptually significant results, demonstrate the advantages of using psychophysical results to uncover image invariants which correlate with the structure of the physical world that is of value for visual perception.
83 citations
1 Mar 1987
TL;DR: The vision system for Alvin, the Autonomous Land Vehicle, addressing in particular the task of road-following is described, which builds symbolic descriptions of the road and obstacle boundaries using both video and range sensors.
Abstract: We describe the vision system for Alvin, the Autonomous Land Vehicle, addressing in particular the task of road-following. The system builds symbolic descriptions of the road and obstacle boundaries using both video and range sensors. Road segmentation methods are described for video-based road-following, along with approaches to boundary extraction and the transformation of boundaries in the image plane into a vehicle-centered three dimensional scene model. The ALV has performed public road-following demonstrations, traveling distances up to 4.5 km at speeds up to 20 km/hr along a paved road, equipped with an RGB video camera with pan/tilt control and a laser range scanner.
83 citations
TL;DR: Experimental results show that the technique can eliminate a lot of stationary regions and thus can reduce the amount of processing required in the interpretation process.
79 citations
TL;DR: The authors demonstrate a general, flexible constrained discrimination method for testing hypotheses about the segmentability of a target population using categorical descriptors when additional information is available.
Abstract: The authors demonstrate a general, flexible constrained discrimination method for testing hypotheses about the segmentability of a target population using categorical descriptors when additional in...
01 Oct 1987-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: A segmentation algorithm based on deterministic relaxation with varying neighborhood structures for the segmentation of noisy images, modeled as a discrete-valued Markov random field, corrupted by additive, independent, Gaussian noise is presented.
Abstract: This paper presents a segmentation algorithm based on deterministic relaxation with varying neighborhood structures for the segmentation of noisy images. The image is modeled as a discrete-valued Markov random field (MRF), or equivalently a Gibbs random field, corrupted by additive, independent, Gaussian noise; although, additivity and Gaussian assumptions are not necessary for the algorithm. The algorithm seeks to determine the maximum a posteriori (MAP) estimate of the noiseless scene. Using varying neighborhoods during relaxation helps pick up certain directional features in the image which are otherwise smoothed out. The parallelism of the algorithm is underscored by providing its mapping to mesh-connected and systolic array processors suitable for VLSI implementation. Segmentation results are given for 2- and 4-level Gibbs distributed and geometric images corrupted by noise of different levels. A comparative study of this segmentation algorithm with other relaxation algorithms and a single-sweep dynamic programming algorithm, all seeking the MAP estimate, is also presented.
TL;DR: Test results indicate that the proposed context-directed algorithm for segmenting connected numeral strings into their components is very effective in providing an accurate segmentation in a form suitable for further processing by a recognition algorithm.
TL;DR: An algorithm for automatic image segmentation using a ‘homogeneity’ measure and a “contrast” measure defined on the co-occurrence matrix of the image are described and the comparison of its performance with the existing ones are demonstrated.
1 Oct 1987
TL;DR: Two algorithms are described for automatic image segmentation using a homogeneity measure and a contrast measure defined on the co-occurrence matrix of the image using the concept of logarithmic response of the human visual system.
Abstract: Two algorithms are described for automatic image segmentation using a homogeneity measure and a contrast measure defined on the co-occurrence matrix of the image. The measure of contrast involves the concept of logarithmic response (adaptability with background intensity) of the human visual system. Provisions are made in two different ways to remove the undesirable thresholds. The effectiveness of the algorithms is demonstrated for a set of images having different types of histograms. Their performance is compared to that of existing algorithms.
Journal Article•
TL;DR: Different methods for the automated segmentation of microscopic cell scenes are presented with examples, which are more robust against insignificant changes in the scene and perform more reliably as more a priori knowledge about the scene is incorporated in the segmentation algorithm.
Abstract: Different methods for the automated segmentation of microscopic cell scenes are presented with examples. The techniques discussed include edge detection by thresholding, "blob" detection by split-and-merge algorithm, global thresholding using gray-level histograms, hierarchic thresholding using color information, global thresholding using two-dimensional histograms and segmentation by "blob" labeling. Methods are more robust against insignificant changes in the scene and perform more reliably as more a priori knowledge about the scene is incorporated in the segmentation algorithm. The inclusion of both photometric and geometric a priori knowledge can result in a high level of correct segmentations, the cost of which is increased computation time.
1 Jan 1987
TL;DR: The range of grouping capabilities and discriminations exhibited by the human visual system are explored and the application of the meaningfulness measure to each of them are discussed.
Abstract: We describe a new approach to low-level vision in which the task of image segmentation is to distinguish meaningful relationships between image elements from a background distribution of random alignments Unlike most previous approaches, which start from idealized models of what we wish to detect in the world, this approach is not based on prior world knowledge and uses measurements which can be computed directly from the input signal Groupings of image elements are formed over a wide range of sizes and classes while attempting to make use of all available statistical information at each level of the grouping hierarchy, resulting in far more sensitive discrimination than is possible from just local measurements This paper explores the range of grouping capabilities and discriminations exhibited by the human visual system and discusses the application of the meaningfulness measure to each of them
1 May 1987
TL;DR: A novel view of the segmentation/ description process is presented and an effective algorithm based on the model is described.
Abstract: Edge-based binocular correspondence produces a sparse disparity map, available information being distributed along space curves which project to matched image edges. To become useful, these contours must be parsed into describable sections. A novel view of the segmentation/ description process is presented and an effective algorithm based on the model is described.
Patent•
2 Mar 1987
TL;DR: In this paper, the correspondence between the distance information estimated from the position information and a map and other distance information obtained actually from a distance measuring means to estimate the accurate present position and replacing the map is secured.
Abstract: PURPOSE: To obtain the information needed for guide control of a mobile object by securing the correspondence between the distance information estimated from the position information and a map and other distance information obtained actually from a distance measuring means to estimate the accurate present position and replacing the map. CONSTITUTION: The distance data to be obtained from a distance measuring sensor is estimated by a distance data producing part 11 based on the position/ direction data on a mobile object obtained from a position sensor and a priori map. This estimated distance data and the distance data actually obtained from the distance measuring sensor are supplied to the segmentation parts 12a and 12b so that the correspondence is secured between both distance data by a low level matching part 13 and a high level matching part 14. Thus the accurate position and direction of the mobile object are decided. Then finally a priori map is corrected by a map replacement part 16 based on the result of said correspondence and the accurate position and direction of the mobile object. COPYRIGHT: (C)1988,JPO&Japio
1 Apr 1987
TL;DR: Scale-space filtering, proposed by Witkin (ICASSP 84) for describing natural structure in one-dimensional signals, has been extended for application to segmentation and description of vector-valued functions of time, such as speech spectrograms.
Abstract: Scale-space filtering, proposed by Witkin (ICASSP 84) for describing natural structure in one-dimensional signals, has been extended for application to segmentation and description of vector-valued functions of time, such as speech spectrograms. By analyzing the rate of change of a vector trajectory at many different scales of time-smoothing, a tree of natural segments can be constructed. At various levels in the tree (i.e., at various scales), these segments are found to agree well with the kind of linguistically and perceptually important segments that spectrogram readers use to describe sound patterns of speech. Scale-space segmentations of cochleagrams (spectrograms based on a computational model of the peripheral auditory system) have been experimentally applied to word recognition. Recognition using fixed-scale segmentations with finite-state word models and a Viterbi search has led to speaker-independent digit recognition accuracies of greater than 97%, about the same as in tests with non-segmented cochleagrams. More complex recognition algorithms that use the segmentation tree are being developed, and scale-space experiments with connected digits and sentences are also underway.
Journal Article•
TL;DR: An image segmentation method which may be applied to various tasks such as natural segmentation of monochromatic or color, three dimensional seismic or scanner images, based on the region growing principle is presented.
Abstract: We present an image segmentation method which may be applied to various tasks such as natural segmentation of monochromatic
or color, three dimensional seismic or scanner images . Our algorithme is based on the region growing principle. Its originality
lies on optimising the use of a sequence of criteria . We separate the common strategy of using segmentation criteria from the
task specific definition of those criteria . This separation between algorithm and mathematical aspects of our method provides
for its generality . Experiments results are shown .
1 Jan 1987
Abstract: A multiple pass procedure for the automatic segmentation of syllabic units is described which involves (1) a broad segmentation triggered by the dips in the intensity curve of band-pass
1 Dec 1987
TL;DR: The regular spacing of the segments and the fact that the entire range of defects is inducible by ether are further consistent with the hypothesis that at least part of the segmentation process may consist of physicochemical reactions coordinated over the whole body.
Abstract: Drosophila embryos, exposed to ether between 1 and 4 h after oviposition, develop defects ranging from the complete lack of segmentation to isolated gaps in single segments. Between these extremes are varying extents of incomplete and abnormal segmentation. On the basis of both their temporal and spatial characteristics, five major phenotype classes may be distinguished: headless — unsegmented or incompletely segmented anteriorly; gap — interruptions of segmentation not obviously periodic; alternating segment gaps — interruptions with double segment periodicities; fused segments; and short segments — truncations with single segment periodicities. Many defects resemble known mutant phenotypes. The disturbances in segmentation are predominantly global and frequently accompanied by alterations in segment specification, such that the segments obtained show no resemblance to the normal homologues. These features, together with the distinctive spatiotemporal characteristics of the defects, all point to segmentation as a dynamic process. The regular spacing of the segments and the fact that the entire range of defects is inducible by ether are further consistent with the hypothesis that at least part of the segmentation process may consist of physicochemical reactions coordinated over the whole body. The relationship between our data and data from genetic and other analyses are briefly discussed.
1 Jan 1987
TL;DR: A new strategy for image segmentation of different biological tissue sections is presented and the basic underlying idea of this segmentation has been developed and tested on more than 20,000 stained white blood cells.
Abstract: A new strategy for image segmentation of different biological tissue sections is presented. Color differences, geometric operations and an object model are the major components of the segmentation process. In a light microscope the depth of focus is so small that only a part of a 1.5–10 micron thick section is visible; more than one measurement is necessary for image acquisition, segmentation and analysis of the whole section. The image segmentation process is generally the same for different biological tissue sections, regardless of how they have been prepared and stained. Only some factors depend on the optical magnification and the biological material. The basic underlying idea of this segmentation has been developed and tested on more than 20,000 stained white blood cells.
1 Apr 1987
TL;DR: The simulated annealing based segmentation algorithm presented in this paper can also be viewed as a two-step iterative algorithm in the spirit of the EM algorithm.
Abstract: This paper presents a segmentation algorithm for noisy textured images. To represent noisy textured images, we propose a hierarchical stochastic model that consists of three levels of random fields: the region process, the texture processes and the noise. The hierarchical model also includes local blurring and nonlinear image transformation as results of the image corrupting effects. Having adopted a statistical model, the maximum a posteriori (MAP) estimation is used to find the segmented regions through the restored(noise-free) textured image data. Since the joint a posteriori distribution at hand is a Gibbs distribution, we use simulated annealing as a maximization technique. The simulated annealing based segmentation algorithm presented in this paper can also be viewed as a two-step iterative algorithm in the spirit of the EM algorithm [10].
1 Apr 1987
TL;DR: A new segmentation method based on the properties of the human visual system that is part of a new second generation image coder and one of the properties is that it is not necessary to transmit (or store) the visual residual for use in reconstructing the received signal.
Abstract: A new segmentation method based on the properties of the human visual system is described in this paper. The segmentation method is part of a new second generation image coder. In addition, one of the properties is that it is not necessary to transmit (or store) the visual residual for use in reconstructing the received signal. It is assumed that the characteristics of this visual residual are known at the receiver and can be used in the reconstruction process.
Journal Article•
TL;DR: Different segmentation methods for the separation of nuclei, nucleoli and whole cells in methacrylate-embedded sections of rat liver were investigated and reasonable segmentation results were obtained.
Abstract: The segmentation of scenes of fixed tissue sections for quantitative histopathology is the crucial step for further image processing. Different segmentation methods for the separation of nuclei, nucleoli and whole cells in methacrylate-embedded sections of rat liver were investigated. Reasonable segmentation results were obtained using a contrast-enhanced polar-coordinate transformation to distinguish nuclei, a compactness algorithm to distinguish nucleoli and a skeletonization algorithm to delineate cells when a priori information on the morphometric and photometric properties of the liver tissue was included.
1 Jan 1987
TL;DR: A new method for the matching of 2-dimensional scenes of single and multiple objects with a previously formed model database is presented and discussed, based on a two-tier organisation of the model database consisting of object centred and binary relation centred structures.