Using Discriminant Eigenfeatures for Image Retrieval
IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting Faces in Images: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
Self-Organizing Maps
Hi-index | 0.00 |
We propose a method of face recognition that can consistentlyidentify every face angle, assuming it will beused in open spacessuch as a normal room. We obtain the learning images not from anideal world but from the real world, where users can move aroundfreely with noconstraints. We then automatically classify the faceimages that vary according to the user's position and posture byself-organization (unsupervised learning), and create adiscrimination circuit using only the best face images for therecognition task. We show that the recognition rate for images withvarious facial angles in the real world can be improved byautomatic classification through self-organization.