Ear recognition method based on independent component analysis and BP neural network
ZHANG Haijun, MU Zhichun, ZHANG ChengyangInformation Engineering School, University of Science and Technology Beijing, Beijing 100083, China
A new ear recognition method combining independent component analysis (ICA) and BP neural network was proposed. The FastICA algorithm was used to derive independent basic images and projection vectors out of ear images, and three-layer BP neural network was used to classify ears. The local features extraction of ICA and the adaptability of BP neural network were combined reasonably. The robustness of the system was enhanced. Experiment results show that the ear recognition rate of the ICA-BP method is improved obviously.