Showing papers on "Object-class detection published in 1993"
09 Jun 1993
TL;DR: In this article, a biologically motivated compute intensive approach to computer vision is developed and applied to the problem of face recognition, based on the use of two-dimensional Gabor functions that fit the receptive fields of simple cells in the primary visual cortex of mammals.
Abstract: A biologically motivated compute intensive approach to computer vision is developed and applied to the problem of face recognition. The approach is based on the use of two-dimensional Gabor functions that fit the receptive fields of simple cells in the primary visual cortex of mammals. A descriptor set that is robust against translations is extracted by a global reduction operation and used for a search in an image database. The method was applied on a database of 205 face images of 30 persons and a recognition rate of 94% was achieved.
28 citations
14 Jul 1993
TL;DR: A specific stereo vision set-up, using two linear cameras installed on the top of a car, has been developed to capture sequences of pairs of linear images to address the problem of obstacle detection in front of vehicles.
Abstract: This paper addresses the problem of obstacle detection in front of vehicles. A specific stereo vision set-up, using two linear cameras installed on the top of a car, has been developed to capture sequences of pairs of linear images. The analysis of the left and the right images acquired simultaneously calls for a new edge matching procedure. The system has been evaluated in real traffic conditions.
11 citations
TL;DR: An algorithm for object detection that is robust against brightness variation and does not depend on the position, size, background pattern, shape, or color of target objects is presented.
Abstract: An algorithm for object detection is presented This method is robust against brightness variation and does not depend on the position, size, background pattern, shape, or color of target objects The method consists of three processes: (1) normalize the brightness of the target and reference images; (2) calculate features, called the normalized principal component features; and (3) construct a classifier by statistical learning The method is applied to car detection in a parking lot Under various conditions, at least 98 percent of the cars were detected correctly Application to moving-car detection and person detection also is presented
6 citations
05 Sep 1993
TL;DR: The authors' automated image processing method creates the velocity maps of the small regions of echocardiographic 2D images based on their velocity profiles and shows a good performance comparing with the traditional wall motion detection.
Abstract: The authors' automated image processing method creates the velocity maps of the small regions of echocardiographic 2D images. The separation and matching of this objects are based on their velocity profiles. The object-oriented programming method allows the handling such a complex problem. The automated analysis showed a good performance comparing with the traditional wall motion detection: the specificity of computer scoring was 84.4%, the sensitivity 81.2%. >
4 citations
Proceedings Article•
01 Jan 1993
TL;DR: A biologically motivated compute intensive approach to computer vision is developed and applied to the problem of face recognition based on the use of two dimensional Gabor functions that are receptive to the receptive elds of simple cells in the primary visual cortex of mammals.
Abstract: A biologically motivated compute intensive approach to computer vision is developed and applied to the problem of face recognition The approach is based on the use of two dimensional Gabor functions that t the receptive elds of simple cells in the primary visual cortex of mammals A descriptor set that is robust against translations is extracted and used for a search in an image database The method was applied on a database of face images of persons and a recognition rate of was achieved The nal version of the paper will report on the results obtained by applying a set of Gabor functions on a database of face images of persons and on the implementation on a Connection Machine CM parallel supercomputer to be installed at our university until the end of
2 citations
25 Oct 1993
TL;DR: A mathematical model of object detection is investigated, and a model which controls the viewpoint and visual field is proposed so that the model can minimize the estimation error of the position given the probability distribution of the positions of the objects.
Abstract: We investigate a mathematical model of object detection, which is one of the essential functions of a visual system. We treat the problem as the estimation problem of the position of an object from the image of an object with noise, and propose a model which controls the viewpoint and visual field so that the model can minimize the estimation error of the position given the probability distribution of the position of the objects.
19 Oct 1993
TL;DR: The multi-double-gate filter which uses the features of the target to separate targets from clutter background, is a very useful algorithm which has a higher detection rate and a smaller amount of computation than other similar algorithms.
Abstract: A new algorithm used to automatically detect targets in a complicated background is presented Based on a knowledge base and prior experimental data, the multi-double-gate filter which uses the features of the target to separate targets from clutter background, is a very useful algorithm It has a higher detection rate and a smaller amount of computation than other similar algorithms >