Canny edge detection enhancement by scale multiplication

Description

We developed a scale multiplication-based scheme to improve the performance of traditional Canny edge detector. Taking the advantage of similarities in the filter’s responses at adjacent scales, the new scheme multiplies the responses to enhance edge structures while diluting noise and detect the edges as the local maxima in the scale products. Our theoretical analyses show that scale multiplication can improve the edge localization accuracy and then yield better edge detection results. Experiments on synthetic and natural images were made to test the proposed method.

(a) Noisy image House. (b) Edge map by CED at a small scale s1. (c) Edge
map by CED at a large scale s2. (d) Edge map by ADED. (e) Edge map by the
proposed SMED with s1 and s2.

ref :

Bao, P., Zhang, L., & Wu, X. (2005). Canny edge detection enhancement by scale multiplication. IEEE transactions on pattern analysis and machine intelligence, 27(9), 1485-1490.

Traffic sign detection based on color and shape detection

Optimal detection, separation, and analysis of FISH images