Highlight Detection and Removal Based on Chromaticity

• Published in: Image Analysis and Recognition pp. 199 - 206
• Main Authors: Xu, Shu-Chang, Ye, Xiuzi, Wu, Yin, Zhang, Sanyuan
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Edition: 1ère éd
• Series: Lecture Notes in Computer Science
• Subjects: Applied sciences; Artificial intelligence; Chromaticity Space; Computer science; control theory; systems; Diffuse Chromaticity; Exact sciences and technology; Highlight Detection; Highlight Region; Pattern recognition. Digital image processing. Computational geometry; Reflection Component; Cluster analysis; Computer vision; Data analysis; Target tracking; Motion estimation; K means algorithm; Pattern recognition; Fuzzy logic; Image analysis; Vector space; Specular reflection; Classification; Chromaticity; Motion detection; Edge detection
• ISBN: 9783540290698; 3540290699
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/11559573_25

The presence of highlight can lead to erroneous results in Computer Vision applications such as edge detection, and motion tracking. Many algorithms have been developed to detect and remove highlight. In this paper, we propose a simple and effective method for detecting and removal of highlight. We first use a window to help to remove the noise and reduce the data amount for analysis. We then apply K-means algorithm in a 5-D vector space to computer diffuse chromaticity. In the case of non-white illuminant, illuminant chromaticity is estimated in the inverse-intensity space, and we use Fuzzy C-mean clustering and linear fitting to get illuminant chromaticity. Finally, we use Specular-to-Diffuse mechanism to separate specular reflection component from image. Experiments show that it is robust and can give good results.