Research on Face Recognition Method based on Cognitive Mechanism

A face recognition method similar to human cognitive mechanism has been proposed. Motivated by the continuity rule of a same class samples, face recognition can be regarded as face pattern cognition. Compared with traditional statistical pattern based face recognition, it has a kind of relationship with human´s cognitive mechanism. When face coverage of different people overlap, a person´s face distribution in low dimension space has a certain kind of cohesion. With the increase of space dimension, the cohesion of a same class samples decreases, meanwhile the repellency of different class samples increases. However, with further increasing of dimension, both the cohesion of a same class and the repellency of different class decrease. The coverage of candidate face recognition is processed in a certain space. If it belongs to several candidate face coverage, Fisher LDA method can be applied to obtain the final results. Experiments based on ORL have proved that untrained random objects can be recognized perfectly.