Title :
Multi-sphere classification algorithm based on 1-SVM
Author :
Hongbo, Wang ; Guangzhou, Zhao ; Yilong, Qu ; Donglian, Qi
Author_Institution :
Coll. of Electr. Eng., Zhejiang Univ., Hangzhou, China
Abstract :
The multi-sphere 1-SVM classifier(MSVDD) is proposed by expending the 1-SVM to multi-class model. When classifying, in order to ensure that boundaries are obtained using 1-SVM tight enough for characterizing all classes in a given data set, introduce implicitly decomposition tactics, and propose MSVDD method in two different mathematical formulations in this paper. The simulation results show that the algorithm can be efficiently applied to License Plate Recognition System.
Keywords :
image classification; object recognition; support vector machines; traffic engineering computing; video surveillance; MSVDD; decomposition tactics; license plate recognition system; mathematical formulation; multiclass model; multisphere 1-SVM classifier; multisphere support vector data description; Classification algorithms; Educational institutions; Electrical engineering; Electronic mail; Glass; Licenses; Support vector machines; 1-SVM; license plate recognition; multi-sphere; multiple classifiers;
Conference_Titel :
Control Conference (CCC), 2012 31st Chinese
Conference_Location :
Hefei
Print_ISBN :
978-1-4673-2581-3
