Face recognition based on LDA and SOM neural nets
Anderson Rodrigo dos Santos, Adilson Gonzaga · 2005
The use of biometric technique for automatic personal identification is one of the biggest challenges in the security field. The process is complex, because it is influenced by many factors related to the form, position, illumination, rotation, translation, disguise and occlusion of face characteristics. This work presents a searching method to identify a face in a training database. We have proposed an algorithm for face recognition based on LDA subspace using a SOM neural net to memorize each class (face) in the stage of classification / identification. The interaction between the number of eigenvectors in the PCA and LDA subspaces has been analyzed to establish the rate recognition. 1