Share Email Print

Proceedings Paper

Techniques for detection and classification of edges in color images
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We introduce a novel method of splitting up color spaces into different components and then performing edge detection on individual color planes. The two general approaches taken for this are monochromatic and vector based. Also a new color space will be introduced in this paper, which is an improved version of the PCA algorithm. By analyzing the results of these algorithms we are able to determine which color space and edge detector is best suited for each algorithm. We test these methods using a number of well known edge detectors and color spaces. All the algorithms are tested on 17 different color images (12 natural, 5 synthetic). To analyze the results we use Pratt's Figure of Merit and Bovik's SSIM measures.

Paper Details

Date Published: 3 April 2008
PDF: 11 pages
Proc. SPIE 6982, Mobile Multimedia/Image Processing, Security, and Applications 2008, 69820W (3 April 2008); doi: 10.1117/12.777703
Show Author Affiliations
Karen Panetta, Tufts Univ. (United States)
Sadaf Qazi, Tufts Univ. (United States)
Sos Agaian, The Univ. of Texas at San Antonio (United States)

Published in SPIE Proceedings Vol. 6982:
Mobile Multimedia/Image Processing, Security, and Applications 2008
Sos S. Agaian; Sabah A. Jassim, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?