Multi technique face recognition using PCA/ICA with wavelet and Optical Flow
Walid Amin Al-Jawhar, Ayman Mansour, Zakaria M. Kuraz · 2008
Together with the growing interest in the development of human and computer interface and biometric identification, human face recognition has become an active research area since early 90psilas. A number of current face recognition algorithms using face representations found by unsupervised statistical methods. Typically these methods find a set of basis images and represent faces as a linear combination of those images. This paper proposed an algorithm that uses PCA on wavelet subband and the optical flow (OF). In comparison with the traditional use of PCA, the proposed method gave a better recognition accuracy of up to (73.24%) on an image database of 157 human faces. Then a new method using the independent component analysis (ICA) was used to improve the recognition rate. The relative performance of PCA and ICA are compared on the same database mentioned before. A recognition accuracy rate of (90.45%) was achieved with the ICA which is much better than the PCA.