Adaptive Elimination of False Edges for First Order Detectors

In this paper, we propose a new rule for the elimination of false edges produced by gradient detectors. This rule is based on the characteristics of the image and the properties of the detector used. The rule has been tested on realistic images using multi-scale edge detectors.

[1]  James J. Clark.  Authenticating Edges Produced by Zero-Crossing Algorithms , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Mubarak Shah,et al.  Edge Characterization Using Normalized Edge Detector , 1993, CVGIP Graph. Model. Image Process..

[3]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Salvatore Tabbone,et al.  A multi-scale edge detector , 1993, Pattern Recognit..