DocumentCode
2617307
Title
Backpropagation and SOM for face feature recognition
Author
Ruiz, José ; Jaime, René
Author_Institution
Fac. de Ingenieria Mecanica, Electr. y Electron., Univ. de Guanajuato, Salamanca Guanajuato, Mexico
Volume
3
fYear
1996
fDate
16-19 Sep 1996
Firstpage
487
Abstract
A face feature extraction system is proposed, based on previous works that utilize Gabor filters and self-organizing maps, but having the difference that we use a final stage consisting of a backpropagation network to improve the recognition. Besides this addition, we look forward to a more convenient place to locate the center frequencies of the filters, and also we apply a Fourier transformation to the self-organizing map output to get translation invariance in the feature map, before the backpropagation network
Keywords
Fourier transforms; backpropagation; band-pass filters; face recognition; feature extraction; self-organising feature maps; Fourier transformation; Gabor filters; SOM; backpropagation neural network; center frequencies; face feature recognition; feature extraction; feature map; filters; self-organizing maps; translation invariance; Backpropagation; Band pass filters; Computer vision; Electronic mail; Face recognition; Feature extraction; Frequency; Gabor filters; Neurons; Pixel;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing, 1996. Proceedings., International Conference on
Conference_Location
Lausanne
Print_ISBN
0-7803-3259-8
Type
conf
DOI
10.1109/ICIP.1996.560537
Filename
560537
Link To Document