Azriel Rosenfeld

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.

Seeing and understanding: representing the visual world

Abstract: Most research in computational vision has concentrated on efforts to recover three-dimensional (3D) metric structure from images. This may be because research communities are influenced by fashion. Our views about the architecture of an intelligent system possessing perception, that is, its components and their relationships, are influenced by the current dominant views regarding intelligence, the mind, and brain. One view about the brain, which has been and still is widely held by neurologists, assumes that there is a separation between the “two causally linked faculties of seeing and understanding, the former a passive and the latter an active process” [Zeki 1993]. As a consequence of this view, computational vision is commonly treated as a discipline whose goal is the recovery of metric descriptions of the scene that can be utilized for reasoning. After considerable effort and many theoretical results about scene recovery, computational vision is now moving into a relatively mature stage. It is now well understood that when we make assumptions about the scene, that is, impose specific models on the visible world, recovery of the model is usually possible provided the assumptions actually hoI d. For simple models of the geometry and the physical properties of the scene, we already have working systems that are finding their way into industry. But developing vision systems for particular environm ents, although useful, does not ./.

Extraction of key frames from videos by polygon simplification

Abstract: We apply the polygon simplification method to automatically obtain the most relevant key frames. First a video sequence is mapped to a polyline in R/sup 37/. By simplifying this polyline, we obtain a summarization (i.e., a small set of the most relevant frames) that is representative of the whole video sequence. The degree of the simplification is either determined automatically or selected by the user.

A Computational Approach to Edge Detection

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.

Textural Features for Image Classification

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.

A theory for multiresolution signal decomposition: the wavelet representation

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. >

Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

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.