Showing papers by "Azriel Rosenfeld published in 1988"
Journal Article•
[...]
TL;DR: How the field of computer (and robot) vision has evolved, particularly over the past 20 years, is described, and its central methodological paradigms are introduced.
3,112 citations
TL;DR: Algorithms based on minimization of compactness and of fuzziness are developed whereby it is possible to obtain both fuzzy and nonfuzzy (thresholded) versions of an ill-defined image.
279 citations
01 Aug 1988
TL;DR: The author provides a general introduction to computer vision by focusing on two-dimensional object recognition, i.e. recognition of an object whose spatial orientation, relative to the viewing direction, is known.
Abstract: The author provides a general introduction to computer vision. He discusses basic techniques and computer implementations, and also indicates areas in which further research is needed. He focuses on two-dimensional object recognition, i.e. recognition of an object whose spatial orientation, relative to the viewing direction is known. >
106 citations
01 Mar 1988-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: Several methods of Hough transform computation suitable for implementation on a mesh-connected SIMD parallel processor, such as Goddard Space Flight Center's Massively Parallel Processor (MPP) or Martin Marietta Corp.'s Geometric Arithmetic Parallel processor (GAPP), are compared.
Abstract: Hough transform techniques for straight line detection play a key role in the road following algorithms developed by the University of Maryland for the DARPA Autonomous Land Vehicle Project. This report compares several methods of Hough transform computation suitable for implementation on a mesh-connected SIMD parallel processor, such as Goddard Space Flight Center's Massively Parallel Processor (MPP) or Martin Marietta Corp.'s Geometric Arithmetic Parallel Processor (GAPP).
74 citations
TL;DR: A method of fitting κ straight lines to a set of data points using an algorithm analogous to the Isodata, or κ-means, clustering technique for partitioning a setof data points into κ compact clusters is described.
28 citations
01 Jun 1988-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: It is shown how computation of geometric properties of a region represented by a linear quadtree can be speeded up by about a factor of p by using a p -processor CREW PRAM model of parallel computation.
Abstract: We show how computation of geometric properties of a region represented by a linear quadtree can be speeded up by about a factor of p by using a p -processor CREW PRAM model of parallel computation. Similar speedups are obtained for computing the union and intersection of two regions, and the complement of a region, using linear quadtree representations.
23 citations
TL;DR: A parallel method based on connecting locally computed centroids to extract polygonal approximations of multiscale planar curves at different resolutions is proposed, making use of a new pyramidal data structure, the chain pyramid.
20 citations
TL;DR: A method of detecting thin curvilinear features in an image based on a detailed analysis of the local gray level patterns at each pixel is described, which allows operations such as thinning and gap filling to be based on more accurate information.
19 citations
01 Mar 1988-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: This paper presents algorithm to compute the contour, perimeter, and area of the region covered by a set of n upright rectangles in O ( n ) time using O (n ) processors for the shared memory model, and using O 2 processors for mesh-connected computers.
Abstract: The medial axis transform (MAT) represents a region of a digital image as the union of maximal upright squares contained in the region. This paper presents algorithm to compute the contour, perimeter, and area of the region covered by a set of n upright rectangles in O ( n ) time using O ( n ) processors for the shared memory model, and using O ( n 2 ) processors for mesh-connected computers.
18 citations
01 Dec 1988-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: It is shown that homogeneous parts of the low resolution representations of the input image may be recovered by renormalizing the corrupted weights, and it is proposed that some of these pyramidal algorithms may also serve as computational models for perceptual phenomena.
Abstract: Image pyramids have been used by many investigators as computational structures for multiresolution image processing and analysis. We have subjected such pyramids to various structural perturbations and investigated their effects on the functions of the pyramid. The perturbations ranged from adding Gaussian noise to the weights of the generating kernel, to generating a hierarchy of completely irregular tessellations of the image field. We have shown that homogeneous parts of the low resolution representations of the input image may be recovered by renormalizing the corrupted weights. Multiresolution algorithms transposed to irregular (stochastic) structures exhibited only a small decrease in performance. We conclude that pyramidal algorithms are robust and are only weakly dependent on the underlying structure. We propose that some of these pyramidal algorithms may also serve as computational models for perceptual phenomena.
16 citations
01 May 1988-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: The topics covered include architectures; computational techniques; feature detection, segmentation, and image analysis; matching, stereo, and time-varying imagery; shape and geometry; color and texture; and three-dimensional scene analysis.
Abstract: This paper presents a bibliography of over 1400 references related to computer vision and image analysis, arranged by subject matter. The topics covered include architectures; computational techniques; feature detection, segmentation, and image analysis; matching, stereo, and time-varying imagery; shape and geometry; color and texture; and three-dimensional scene analysis. A few references are also given on related topics, such as computer graphics, image input/output, image processing, optical processing, neural nets, visual perception, pattern recognition, and artificial intelligence.
TL;DR: This work considers an order statistics problem, a variant of the selection problem, and presents an optimal parallel algorithm to find the highest k elements out of a set of n totally ordered (but not sorted) elements.
05 Jun 1988
TL;DR: A benchmark is presented that was designed to evaluate the merits of various parallel architectures as applied to image understanding (IU) to gain a better understanding of vision architecture requirements, which can be used to guide the development of the next generation of vision architectures.
Abstract: A benchmark is presented that was designed to evaluate the merits of various parallel architectures as applied to image understanding (IU). This benchmark exercise addresses the issue of system performance on an integrated set of tasks, where the task interactions that are typical of complex vision application are present. The goal of this exercise is to gain a better understanding of vision architecture requirements, which can be used to guide the development of the next generation of vision architectures. >
TL;DR: This paper shows how to combine these two approaches by using p processors to process compactly encoded strings, e.g. using run length code to speed up string operations.
TL;DR: This report considers the problem of identifying a random field belonging to a given class, given sample generation by that random field, and uses Monte Carlo simulations to evaluate the performance of estimators and to investigate the tightness of some theoretical bounds for their confidence levels.
01 Jun 1988-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: An approach to interpreting line drawings under assumptions which are ubiquitous in natural scenes, that at least one of the many features is paralled to the image plane, and thus gives the real dimensions of a feature.
Abstract: This paper describes an approach to interpreting line drawings under assumptions which are ubiquitous in natural scenes. The assumptions are that many identical, essentially two-dimensional features are depicted and they are arranged in random orientations. We assume that at least one of the many features is paralled to the image plane, and thus gives the real dimensions of a feature. From this, the orientations of the other features can be easily recovered. Four examples of this approach are shown to give quite natural results.
29 Mar 1988
TL;DR: In the field of computer vision, computer vision deals with the extraction of information about a scene by analysis of images of that scene as mentioned in this paper, which deals with scenes that were essentially two-dimensional: documents, microscope images, high-altitude images of the earth's surface.
Abstract: Computer vision deals with the extraction of information about a scene by analysis of images of that scene. The field had its origins over 30 years ago. Traditionally, it dealt with scenes that were essentially two-dimensional: documents, microscope images, high-altitude images of the earth's surface. The classical approach to analyzing such images involves segmentation of the image into parts corresponding to meaningful parts of the scene; measurement of properties of and relations among the parts; and object recognition based on comparison of the configuration of parts, properties and relations (essentially a labeled graph) with standard configurations representing the objects of interest.
01 Apr 1988