Face recognition based on independent component analysis

Face recognition is a biometrics technology with high development potential, and research on face recognition technology is of great theoretical and practical value. Independent component analysis (ICA) is a method being developed in face recognition. In the method of ICA, not only statistical characteristics in second order or higher order are considered, but also basis vectors decomposed from face images obtained by ICA are more localized in distribution space than those by PCA. Localized characteristics are favorable for face recognition, because human faces are non-rigid bodies, and because localized characteristics are not easily influenced by face expression changes, location, position, or partial occlusion. In this paper, the methods of PCA and ICA are adopted and combined, and relatively high recognition rates (up to 99%) are obtained.