On optimal linear filtering for edge detection

IEEE Transactions on Image Processing - Tập 11 Số 7 - Trang 728-737 - 2002
D. Demigny1
1Signal Processing Research Laboratory (ETIS), Cergy-Pontoise University, Cergy-Pontoise, France

Tóm tắt

In this paper, we revisit the analytical expressions of the three Canny's (1983) criteria for edge detection quality: good detection, good localization, and low multiplicity of false detections. Our work differs from Canny's work on two essential points. Here, the criteria are given for discrete sampled signals, i.e., for the real, implemented filters. Instead of a single-step edge as input signal, we use pulses of various width. The proximity of other edges affects the quality of the detection process. This is taken into account in the new expressions of these criteria. We derive optimal filters for each of the criteria and for any combination of them. In particular, we define an original filter which maximizes detection and localization and a simple approximation of the optimal filter for the simultaneous maximization of the three criteria. The upper bounds of the criteria are computed which allow users to measure the absolute and relative performance of any filter (exponential, Deriche (1987), and first derivative of Gaussian filters are evaluated). Our criteria can also be used to compute the optimal value of the scale parameter of a given filter when the resolution of the detection is fixed.

Từ khóa

#Maximum likelihood detection #Image edge detection #Nonlinear filters #Finite impulse response filter #Space vector pulse width modulation #Upper bound #Markov random fields #Surface morphology #Mathematical model #Kernel

Tài liệu tham khảo

10.1109/34.134047 10.1109/34.103275 10.1109/34.62607 10.1109/34.297960 10.1109/34.632980 10.1109/ICIP.1995.537441 10.1109/34.41386 pipes, 1971, the calculus of finite differences and linear difference equations with constant coefficients, Applied Mathematics for Engineers and Physicists, 272 demigny, 2001, fast recursive implementation of the gaussian filter, Proc 11th IFIP Int Conf Very Large Scale Integration, 339 prewitt, 1970, object enhancement and extraction, Picture Processing and Psychopictories, 75 10.1109/34.120331 shen, 1990, new edge detection methods based on exponential filter, Proc ICPR, 10 canny, 1983, Finding edges and lines in images 10.1007/BF00123164 10.1016/1049-9652(92)90060-B 10.1109/34.56205 10.1016/0031-3203(93)90135-J 10.1109/TPAMI.1986.4767851