Title :
A novel contextual descriptors for category recognition
Author :
Ouyang, Yi ; Tang, Ming ; Cheng, Jian ; Wang, Jinqiao ; Lu, Hanqing ; Ma, Songde
Author_Institution :
Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing
fDate :
June 23 2008-April 26 2008
Abstract :
In this paper, we propose a novel contextual descriptor which combines the contextual information and local appearance. Based on Gibbs distribution, a local descriptor is designed. By assembling the contextual information and local descriptors, a new partial contextual descriptor (PCD) is finally presented. Combining pyramid match kernel (PMK) and SVM, we test our new descriptor and obtain higher average precision of classification than using local appearance descriptor.
Keywords :
image classification; object recognition; Gibbs distribution; SVM; category recognition; contextual descriptors; contextual information; local appearance descriptor; pyramid match kernel; Assembly; Computational complexity; Kernel; Laboratories; Pattern recognition; Shape; Support vector machine classification; Support vector machines; Testing; Video surveillance; PMK; category recognition; contextual descriptor; object classification;
Conference_Titel :
Multimedia and Expo, 2008 IEEE International Conference on
Conference_Location :
Hannover
Print_ISBN :
978-1-4244-2570-9
Electronic_ISBN :
978-1-4244-2571-6
DOI :
10.1109/ICME.2008.4607693
