30 October 2009 The usage of color invariance in SURF
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 749508 (2009) https://doi.org/10.1117/12.833509
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
SURF (Scale Invariant Feature Transform) is a robust local invariant feature descriptor. However, SURF is mainly designed for gray images. In order to make use of the information provided by color (mainly RGB channels), this paper presents a novel colored local invariant feature descriptor, CISURF (Color Invariance based SURF). The proposed approach builds the descriptors in a color invariant space, which stems from Kubelka-Munk model and provides more valuable information than the gray space. Compared with the conventional SURF and SIFT descriptors, the experimental results show that descriptors created by CISURF is more robust to the circumstance changes such as the illumination direction, illumination intensity, and the viewpoints, and are more suitable for the deep space background objects.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Gang Meng, Gang Meng, Zhiguo Jiang, Zhiguo Jiang, Danpei Zhao, Danpei Zhao, } "The usage of color invariance in SURF", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749508 (30 October 2009); doi: 10.1117/12.833509; https://doi.org/10.1117/12.833509
PROCEEDINGS
7 PAGES


SHARE
RELATED CONTENT

The least square optimization in image mosaic
Proceedings of SPIE (March 06 2015)
A review of salient region extraction
Proceedings of SPIE (August 19 2010)

Back to Top