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: Methods of detecting and extracting (“delineating,” i.e., segmenting) compact objects from an image are described, designed for implementation on an exponentially tapering “pyramid” of processors, and require only O (log n ) time for an n by n image.
Abstract: This paper describes methods of detecting and extracting (“delineating,” i.e., segmenting) compact objects from an image. The methods are designed for implementation on an exponentially tapering “pyramid” of processors, and require only O (log n ) time for an n by n image. Objects are detected using an “interest measure” derived from local comparisons between fathers and sons in the pyramid. They are extracted by a top-down tree growing process in which the leaves of the tree are the pixels belonging to the detected object.

51 citations

Journal ArticleDOI
TL;DR: In this paper, a method for recognizing a two-dimensional shape from a single perspective projection image taken from an unknown (three-dimensional) viewpoint is presented. But the method is based on quadratic approximations to the effect of the slant of an inverse perspective transformation on angles and lengths.
Abstract: This paper presents a new method of recognizing a two-dimensional shape from a single perspective projection image taken from an unknown (three-dimensional) viewpoint. The method is based on quadratic approximations to the effect of the slant of an inverse perspective transformation on angles and lengths. These approximations allow us to define contour-based properties that are invariant under perspective transformation. The method can be used to recognize partially occluded shapes, as well as shapes that are not exactly related by perspective transformations. When a shape is recognized, the method also provides estimates of its tilt and slant.

50 citations

Journal ArticleDOI
TL;DR: A divide-and-conquer Hough transform technique for detecting a given number of straight edges or lines in an image that requires only O(log n) computational steps for an image of size n × n.

50 citations

Journal ArticleDOI
TL;DR: A simple space-domain model is presented which assumes the presence in the visual system of bar-detecting units whose receptive fields have various sizes and orientations, with the maximum response from any unit to a given stimulus determining the visibility of that stimulus.

50 citations

Journal ArticleDOI
TL;DR: Probabilistic relaxation labeling processes are iterative parallel schemes that use contextual information to reduce local ambiguities.
Abstract: Probabilistic relaxation labeling processes are iterative parallel schemes that use contextual information to reduce local ambiguities. The behavior of these processes can be described by examining the rates of change and entropies of the probability vectors at each iteration. Examples are given comparing three relaxation processes as applied to several basic image analysis tasks.

50 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