Title :
Kernel Function Characteristic Analysis Based on Support Vector Machine in Face Recognition
Author :
Cao, Wei-feng ; Li, Lei ; Lv, Xiao-li
Author_Institution :
Nanjing Univ. of Posts & Telecommun., Nanjing
Abstract :
The application areas of four usual kernel functions in Support Vector Machine are discussed in this paper, and also the selection of kernel function parameters. The characteristic of four usual kernel functions in face recognition is compared and analyzed. One kind of new kernel function used in face recognition is introduced.
Keywords :
face recognition; support vector machines; face recognition; kernel function characteristic analysis; support vector machine; Cybernetics; Face recognition; Information analysis; Kernel; Machine learning; Neural networks; Statistical learning; Support vector machine classification; Support vector machines; Training data; Face recognition; Kernel function; Support vector machine;
Conference_Titel :
Machine Learning and Cybernetics, 2007 International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-0973-0
Electronic_ISBN :
978-1-4244-0973-0
DOI :
10.1109/ICMLC.2007.4370637
