Performance Evaluation of Face Recognition Based on DWT and DT-CWT Using Multi-matching Classifiers

Biometrics recognition tool has great emphasis in both research and practical applications. With an increasing requirement on security, automated personal identification and verification based biometrics has been receiving extensive attention over the past decade. In this paper Performance Evaluation of Face Recognition based on DWT and DT-CWT using Multi-matching Classifiers (FRMC) is proposed. The face images captured from the persons differ in size and hence image dimensions are converted into 2n * 2n dimension, for DT-CWT. The two level DWT is applied on face images to generate four sub bands. The DT-CWT is applied on only LL sub band to generate DT-CWT coefficients, which forms features for face images. The features of database and test face are compared using Euclidian Distance, Random Forest and Support Vector Machine matching algorithms. It is observed that correct recognition rate, false acceptance rate and false reject rate are better in the case of proposed method as compared to existing techniques.