A Face Recognition Method Based on Total Variation Minimization and Log-Gabor Filter

A new face recognition method is proposed by using total variation minimization and Log-Gabor filter. First of all, facial images are transformed by total variation minimization model. Secondly, the facial feature is extracted by Log-Gabor filter from the result of the former transformation. Then, dimensionality reduction is realized by using principle component analysis. Finally, classification is achieved by using nearest neighbor classifier. This method is a kind of combination of advantage between total variation minimization and Log-Gabor filter which holds edge feature and describes textural feature of facial image reasonably. The experiment is conducted on Yale Face database. Compared with the methods such as Gabor filter based feature extraction, et al., the face recognition method we presented has better recognition performance. The correct recognition rate reaches to 86.36%.