Title :
Mercer kernels for object recognition with local features
Author_Institution :
Dept. of Comput. Sci., Dartmouth Coll., Hanover, NH, USA
Abstract :
A new class of kernels for object recognition based on local image feature representations are introduced in this paper. These kernels satisfy the Mercer condition and incorporate multiple types of local features and semilocal constraints between them. Experimental results of SVM classifiers coupled with the proposed kernels are reported on recognition tasks with the COIL-100 database and compared with existing methods. The proposed kernels achieved competitive performance and were robust to changes in object configurations and image degradations.
Keywords :
feature extraction; image classification; image representation; object recognition; support vector machines; visual databases; COIL-100 database; Mercer kernels; SVM classifiers; image degradations; image feature representations; object configuration; object recognition; semilocal constraints; Application software; Computer science; Computer vision; Degradation; Kernel; Noise robustness; Object recognition; Spatial databases; Support vector machine classification; Support vector machines;
Conference_Titel :
Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on
Print_ISBN :
0-7695-2372-2
DOI :
10.1109/CVPR.2005.223