期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2013
卷号：2
期号：3
页码：604
出版社：S&S Publications
摘要：This paper describes a face detection method using Artificial Neural Network (ANN) and Gabor filters. This method achieves rotation invariant and extremely high face detection rate using Gabor wavelets. Gabor filters have optimal localization properties in both spatial and frequency domain. By using these desirable characteristics, Gabor filters extract facial features from the local image. These extracted features work as the input to image classifier which is a Feed Forward Neural Network (FFNN).This network works on a reduced feature subspace learned by an approach simpler than principal component analysis (PCA). Face classification is currently implemented in software. This study gives an impression of Gabor filters in image processing and emphasis on its characteristics of spatial locality and orientation selectivity.
