Title :
Fast Separation of Reflection Components using a Specularity-Invariant Image Representation
Author :
Kuk-Jin Yoon ; Yoojin Choi ; In So Kweon
Author_Institution :
Dept. Electr. Eng. & Comput. Sci., KAIST, Seoul, South Korea
Abstract :
In this paper, we propose a fast method for separating reflection components using a single color image. We first propose a specular-free two-band image that is a specularity-invariant color image representation. Reflection components separation is achieved by comparing local ratios at each pixel and making those ratios equal in an iterative framework. The proposed method is very fast and shows reasonable results for textured indoor/outdoor images.
Keywords :
image colour analysis; image representation; image texture; iterative methods; color image; image representation; iterative framework; reflection components separation; specular-free two-band image; textured indoor-outdoor image; Argon; Color; Computer vision; Filters; Image representation; Image segmentation; Layout; Lighting; Polarization; Reflection; Image color analysis; image representations; reflection;
Conference_Titel :
Image Processing, 2006 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
1-4244-0480-0
DOI :
10.1109/ICIP.2006.312650
