Wavelet-Based Facial recognition

To recognize and automatically identify the identities of individuals, there are several biometric identification systems based on physiological and behavioral characteristics, in our work we are interested in face recognition, which is a recent biometric authentication technology. This technology offers a reasonable level of precision. In this paper, we propose a method of biometric recognition of a person by their face using the wavelet transform. For our application, we have opted for different types of wavelets in order to decompose the region of interest. The evaluation and judgment of each type in relation to the other is given by the calculation of the parameters Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR). The experimental results were performed using the FEI database.