DocumentCode
3179426
Title
A new invariant representation for color images and its application
Author
Ibrahim, Abdelhameed F. ; Ali, Hesham A.
Author_Institution
Comput. & Syst. Eng. Dept., Mansoura Univ., Mansoura, Egypt
fYear
2011
fDate
Nov. 29 2011-Dec. 1 2011
Firstpage
267
Lastpage
272
Abstract
Factors such as shading, shadow, and highlight, observed from object surfaces in a scene, affect seriously the appearance and analysis of the color images. In this paper, we propose a new invariant representation that is derived from the standard dichromatic reflection model for inhomogeneous dielectric and the extended dichromatic reflection model for homogeneous metal. The illumination color is estimated from the specular reflection component on inhomogeneous surfaces without using a reference white standard. The overall performance of the proposed invariant representation is examined in experiments using real-world objects including metals and dielectrics. The feasibility of effective edge detection is introduced and compared with the state-of-the-art invariant methods.
Keywords
edge detection; image colour analysis; image representation; metals; color images; dichromatic reflection model; edge detection; highlight; homogeneous metal; inhomogeneous dielectric; invariant representation; shading; shadow; specular reflection component; standard dichromatic reflection model; Color; Image color analysis; Image edge detection; Lighting; Metals; Nonhomogeneous media; Vectors; color image processing; dichromatic reflection models; image edge detection; image representation; invariant feature;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Engineering & Systems (ICCES), 2011 International Conference on
Conference_Location
Cairo
Print_ISBN
978-1-4577-0127-6
Type
conf
DOI
10.1109/ICCES.2011.6141054
Filename
6141054
Link To Document