DocumentCode
2713818
Title
A receptive field based approach for face detection
Author
Fernandes, Bruno J T ; Cavalcanti, George D C ; Ren, Tsang I.
Author_Institution
Inf. Center, Fed. Univ. of Pernambuco, Recife, Brazil
fYear
2009
fDate
14-19 June 2009
Firstpage
803
Lastpage
810
Abstract
This paper presents a new neural network to perform the visual pattern classification task. The neural network is called I-PyraNet which is a hybrid implementation of the PyraNet and the concepts of the inhibitory fields. In order to improve the results obtained by this neural network, it is also presented the 2-D Gabor filter. Furthermore, both, the neural network and the filter, are applied over a face detection task and are compared to the results obtained by a SVM.
Keywords
Gabor filters; neural nets; object detection; support vector machines; 2D Gabor filter; I-PyraNet; SVM; face detection; inhibitory fields; neural network; receptive field based approach; visual pattern classification task; Biological neural networks; Brain modeling; Detectors; Face detection; Gabor filters; Humans; Image edge detection; Image processing; Neurons; Visual system;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2009. IJCNN 2009. International Joint Conference on
Conference_Location
Atlanta, GA
ISSN
1098-7576
Print_ISBN
978-1-4244-3548-7
Electronic_ISBN
1098-7576
Type
conf
DOI
10.1109/IJCNN.2009.5179017
Filename
5179017
Link To Document