Face Recognition Based on Shearlets Transform and Principle Component Analysis

Multi-resolution analysis has been known to be effective for face recognition, however, most approaches only utilize scale and position information of different scales of decomposed image, only a few approaches utilize directional information. To investigate the potential of shear lets direction, this paper presents a new method for face description and recognition using shear lets transform and principle component analysis. Motivated by multi-resolution analysis, face images are performed by shear lets transform, and then directional information is exploited along with conventional scaling and translation parameters. Finally, face feature is extracted by principle component analysis. Experimental results on ORL and FERET face database show that the proposed method can get high face recognition rates.