The usage of color invariance in SURF

Gang Meng; Zhiguo Jiang; Danpei Zhao

doi:10.1117/12.833509

30 October 2009 The usage of color invariance in SURF

Gang Meng, Zhiguo Jiang, Danpei Zhao

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.

Citation Download Citation

Gang Meng, Zhiguo Jiang, and Danpei Zhao "The usage of color invariance in SURF", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749508 (30 October 2009); https://doi.org/10.1117/12.833509

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available