Title :
Illumination Invariant Texture Retrieval
Author :
Haindl, Michal ; Vácha, Pavel
Author_Institution :
Inst. of Inf. Theor. & Autom., Acad. of Sci., Prague
Abstract :
Two fast illumination invariant image retrieval methods for scenes comprising textured objects with variable illumination are introduced. Both methods are based on texture gradient modeled by efficient set of random field models. We developed the illumination insensitive measures for textured images representation and compared them favorably with steerable pyramid and Gabor features in the illumination invariant BTF texture recognition
Keywords :
content-based retrieval; image representation; image retrieval; image texture; object recognition; Gabor features; illumination invariant image retrieval methods; illumination invariant texture retrieval; image representation; random field models; steerable pyramid; texture gradient; texture recognition; textured objects; Automation; Chromium; Image recognition; Image representation; Image retrieval; Information retrieval; Information theory; Layout; Lighting; Robustness;
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2521-0
DOI :
10.1109/ICPR.2006.678
