Title :
Edge detection, classification, and measurement
Author_Institution :
AT&T Bell Lab., Murray Hill, NJ, USA
Abstract :
An edge detector is proposed which consists of a pair of a pattern and a linear filter. It is shown that for an edge in the input signal, there is a scaled pattern in the filter response. The location of the pattern is the location of the edge, and the scaling factor of the pattern is the size of the edge. Therefore the problem of edge detection and measurement is reduced to searching for the (scaled) pattern in the filter response. In the presence of noise, the pattern matching is approximate. A statistical approach for the pattern search is proposed. Optimal detectors which minimize the effects of noise are studied; for white noise, the optimal detectors are natural splines. Testing results on real images are reported
Keywords :
filtering and prediction theory; pattern recognition; picture processing; statistical analysis; edge detection; linear filter; pattern matching; pattern recognition; picture processing; scaled pattern; scaling factor; splines; statistical approach; white noise; Detectors; Image edge detection; Layout; Lighting; Nonlinear filters; Optical filters; Optical noise; Reflectivity; Testing; White noise;
Conference_Titel :
Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89., IEEE Computer Society Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-8186-1952-x
DOI :
10.1109/CVPR.1989.37822
