Salient Edge Detection in Natural Images

Yihang BO  Siwei LUO  Qi ZOU 

Publication
IEICE TRANSACTIONS on Information and Systems  Vol.E92-D  No.5  pp.1209-1212
Publication Date: 2009/05/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
Keyword: 
salient edge detection,  boundary detection,  salient point detection, 

Full Text: PDF(503.6KB)

Summary: 
Salient edge detection which is mentioned less frequently than salient point detection is another important cue for subsequent processing in computer vision. How to find the salient edges in natural images is not an easy work. This paper proposes a simple method for salient edge detection which preserves the edges with more salient points on the boundaries and cancels the less salient ones or noise edges in natural images. According to the Gestalt Principles of past experience and entirety, we should not detect the whole edges in natural images. Only salient ones can be an advantageous tool for the following step just like object tracking, image segmentation or contour detection. Salient edges can also enhance the efficiency of computing and save the space of storage. The experiments show the promising results.