Title :
Human eyes detection using hybrid neural method
Author :
Peng, Hui ; Zhang, Changshui ; Bian, Zhaoqi
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Abstract :
In this paper, a novel hybrid neural method for human eyes detection is proposed. Firstly, the input facial image is preprocessed for normalization. Then, the candidates of eyes regions are detected based on a modified version of radial basis function (RBF) neural networks. Finally, a hierarchical knowledge-based approach is presented to validate these candidates and to locate the positions of both eyes. Our method has been tested on a database of facial images and achieves a good performance
Keywords :
eye; face recognition; feature extraction; image recognition; knowledge based systems; radial basis function networks; RBF neural networks; eyes regions; face recognition; facial image database; hierarchical knowledge-based approach; human eyes detection; hybrid neural method; input facial image; normalization; radial basis function; Data preprocessing; Eyes; Face detection; Face recognition; Facial features; Humans; Image edge detection; Image resolution; Mouth; Neural networks;
Conference_Titel :
Signal Processing Proceedings, 1998. ICSP '98. 1998 Fourth International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-4325-5
DOI :
10.1109/ICOSP.1998.770805
