scispace - formally typeset
Search or ask a question
Author

Azriel Rosenfeld

Other affiliations: Meiji University
Bio: Azriel Rosenfeld is an academic researcher from University of Maryland, College Park. The author has contributed to research in topics: Image processing & Feature detection (computer vision). The author has an hindex of 94, co-authored 595 publications receiving 49426 citations. Previous affiliations of Azriel Rosenfeld include Meiji University.


Papers
More filters
Journal ArticleDOI
TL;DR: A bibliography of nearly 1900 references related to computer vision and image analysis, arranged by subject matter is presented, covering topics including architectures; computational techniques; feature detection and segmentation; image analysis; and motion.
Abstract: This paper presents a bibliography of nearly 1900 references related to computer vision and image analysis, arranged by subject matter. The topics covered include architectures; computational techniques; feature detection and segmentation; image analysis; two-dimensional shape; pattern; color and texture; matching and stereo; three-dimensional recovery and analysis; three-dimensional shape; and motion. A few references are also given on related topics, such as geometry, graphics, image input/output and coding, image processing, optical processing, visual perception, neural nets, pattern recognition, and artificial intelligence, as well as on applications.

11 citations

Journal ArticleDOI
TL;DR: The structure of the response is to define the central problems of computer vision and the methodological paradigms that have been developed over the past 35 years, and to address the question of why vision is hard.
Abstract: In their paper, Jain and Binford claim that the ignorance, myopia, and naivete of today’s computer vision systems are due to the inadequacy of our methodological paradigms. They attempt to define the central problems in the field, and they make recommendations as to how these problems can be successfully addressed. The structure of our response is as follows: We start by defining the central problems of computer vision and the methodological paradigms that have been developed over the past 35 years. Then we address the question of why vision is hard, and we build around the authors’ statements our suggestions as to how progress in the field can be accelerated. We do not find computer vision to be a field in shambles. On the contrary, we find that it is becoming a well defined science and is well on its way to becoming a postparadigmatic field in the sense that research projects evolve naturally from a central paradigm.’

11 citations

Journal ArticleDOI
TL;DR: A simple curve extraction process involving only local isotropic parallel operations is described, compared with more abstract, essentially one-dimensional contour summarization processes.
Abstract: The human visual system has the impressive ability to quickly extract simple, global, curvilinear structure from input that may locally not even contain small fragments of this structure. Curves are easy to see globally even when they are locally broken, blurred, or jagged. Because the character of curve input can change with the scale at which it is considered, a hierarchical “pyramid” data structure is suggested. This paper describes a simple curve extraction process involving only local isotropic parallel operations. The noise-cleaned input image is smoothed and subsampled into a pyramid of lower-resolution versions by recursive computation of Gaussian-weighted sums. Curves are localized to thin strings of ridges and peaks at each scale. The method is compared with more abstract, essentially one-dimensional contour summarization processes.

11 citations

Journal ArticleDOI
TL;DR: A bibliography of over 800 references related to the computer processing of pictorial information, arranged by subject matter is presented, restricted to a selected set of U.S. journals and proceedings of specialized meetings.

11 citations

Journal ArticleDOI
TL;DR: This paper discusses the concept of a reconfigurable cellular computer, in which each p/sub i/ can receive information from a set s/ Sub i/ of the other ps, and the s/ sub i/s are all of bounded size, but they need not remain fixed throughout a computation.
Abstract: When a collection of processors c=(p/sub 1/, ..., p/sub n/) operates in parallel, it is desirable that at any given stage of the computation, each p/sub i/ should have a task of about the same size to perform, and each p/sub i/ should require about the same amount of information from the other ps in order to perform its task. To the extent that these conditions are violated, parallelism is impaired, in the sense that the ps are not all used with equal efficiency. In cellular computers, e.g. as they might be used for parallel image processing, these conditions are maintained by having the ps all perform similar computations on different parts of the input data, and by allowing each p/sub i/ to receive information from a fixed set of the others (its neighbours), where these sets are all of bounded size. This paper discusses, on an abstract level, the concept of a reconfigurable cellular computer, in which each p/sub i/ can receive information from a set s/sub i/ of the other ps, and the s/sub i/s are all of bounded size, but they need not remain fixed throughout a computation. Requiring the s/sub i/s to have bounded size impliesmore » that most ps cannot communicate directly; the expected time required for two arbitrary ps to communicate depends on the graph structure defined by the sets s/sub i/. The question of how to change the s/sub i/s in parallel during the course of a computation is also discussed. 15 references.« less

10 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.
Abstract: This paper describes a computational approach to edge detection. The success of the approach depends on the definition of a comprehensive set of goals for the computation of edge points. These goals must be precise enough to delimit the desired behavior of the detector while making minimal assumptions about the form of the solution. We define detection and localization criteria for a class of edges, and present mathematical forms for these criteria as functionals on the operator impulse response. A third criterion is then added to ensure that the detector has only one response to a single edge. We use the criteria in numerical optimization to derive detectors for several common image features, including step edges. On specializing the analysis to step edges, we find that there is a natural uncertainty principle between detection and localization performance, which are the two main goals. With this principle we derive a single operator shape which is optimal at any scale. The optimal detector has a simple approximate implementation in which edges are marked at maxima in gradient magnitude of a Gaussian-smoothed image. We extend this simple detector using operators of several widths to cope with different signal-to-noise ratios in the image. We present a general method, called feature synthesis, for the fine-to-coarse integration of information from operators at different scales. Finally we show that step edge detector performance improves considerably as the operator point spread function is extended along the edge.

28,073 citations

Journal ArticleDOI
01 Nov 1973
TL;DR: These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.
Abstract: Texture is one of the important characteristics used in identifying objects or regions of interest in an image, whether the image be a photomicrograph, an aerial photograph, or a satellite image. This paper describes some easily computable textural features based on gray-tone spatial dependancies, and illustrates their application in category-identification tasks of three different kinds of image data: photomicrographs of five kinds of sandstones, 1:20 000 panchromatic aerial photographs of eight land-use categories, and Earth Resources Technology Satellite (ERTS) multispecial imagery containing seven land-use categories. We use two kinds of decision rules: one for which the decision regions are convex polyhedra (a piecewise linear decision rule), and one for which the decision regions are rectangular parallelpipeds (a min-max decision rule). In each experiment the data set was divided into two parts, a training set and a test set. Test set identification accuracy is 89 percent for the photomicrographs, 82 percent for the aerial photographic imagery, and 83 percent for the satellite imagery. These results indicate that the easily computable textural features probably have a general applicability for a wide variety of image-classification applications.

20,442 citations

Journal ArticleDOI
TL;DR: In this paper, it is shown that the difference of information between the approximation of a signal at the resolutions 2/sup j+1/ and 2 /sup j/ (where j is an integer) can be extracted by decomposing this signal on a wavelet orthonormal basis of L/sup 2/(R/sup n/), the vector space of measurable, square-integrable n-dimensional functions.
Abstract: Multiresolution representations are effective for analyzing the information content of images. The properties of the operator which approximates a signal at a given resolution were studied. It is shown that the difference of information between the approximation of a signal at the resolutions 2/sup j+1/ and 2/sup j/ (where j is an integer) can be extracted by decomposing this signal on a wavelet orthonormal basis of L/sup 2/(R/sup n/), the vector space of measurable, square-integrable n-dimensional functions. In L/sup 2/(R), a wavelet orthonormal basis is a family of functions which is built by dilating and translating a unique function psi (x). This decomposition defines an orthogonal multiresolution representation called a wavelet representation. It is computed with a pyramidal algorithm based on convolutions with quadrature mirror filters. Wavelet representation lies between the spatial and Fourier domains. For images, the wavelet representation differentiates several spatial orientations. The application of this representation to data compression in image coding, texture discrimination and fractal analysis is discussed. >

20,028 citations

Journal ArticleDOI
TL;DR: The analogy between images and statistical mechanics systems is made and the analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations, creating a highly parallel ``relaxation'' algorithm for MAP estimation.
Abstract: We make an analogy between images and statistical mechanics systems. Pixel gray levels and the presence and orientation of edges are viewed as states of atoms or molecules in a lattice-like physical system. The assignment of an energy function in the physical system determines its Gibbs distribution. Because of the Gibbs distribution, Markov random field (MRF) equivalence, this assignment also determines an MRF image model. The energy function is a more convenient and natural mechanism for embodying picture attributes than are the local characteristics of the MRF. For a range of degradation mechanisms, including blurring, nonlinear deformations, and multiplicative or additive noise, the posterior distribution is an MRF with a structure akin to the image model. By the analogy, the posterior distribution defines another (imaginary) physical system. Gradual temperature reduction in the physical system isolates low energy states (``annealing''), or what is the same thing, the most probable states under the Gibbs distribution. The analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations. The result is a highly parallel ``relaxation'' algorithm for MAP estimation. We establish convergence properties of the algorithm and we experiment with some simple pictures, for which good restorations are obtained at low signal-to-noise ratios.

18,761 citations