Biometric authentication using curvelet transform
Kerrache Soumia, Mohammed Beladgham, Hamza Aymen, Ibrahim Kadri · Zenodo (CERN European Organization for Nuclear Research) · 2020
In this paper, we propose a feature extraction method for two-dimensional image authentication algorithm using curvelet transform and principal component analysis (PCA). Since wavelet transform can not adequately describe facial curves features, the proposed approach involves image denoising applying a 2D-Curvelet transform to achieve compact representations of curves singularities. To assess the performance of the presented method, we have employed three classification techniques: Neural networks (NN), K-Nearest Neighbor (KNN) and Support Vector machines (SVM). Extensive experimental results and comparison with the existing methods show the effectiveness of the proposed recognition method in the ORL face database and CASIA iris database.