Biometric authenticator algorithm based on multiresolution analysis

Kerrache Soumia (Tahri Mohammed Bechar University)
Beladgham Mohammed (Tahri Mohammed Bechar University)
Hamza Aymen (Tahri Mohammed Bechar University)
Kadri Ibrahim (Tahri Mohammed Bechar University)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 20, No 3: December 2020

In this paper, we propose a feature extraction method for two-dimensional imageauthentication algorithm using curvelet transform and principal component analysis(PCA). Since wavelet transform can not adequately describe facial curves features,Theproposed approach involves image denoising applying a 2D-Curvelet transform toachieve compact representations of curves singularities. To assess the performanceof the presented method, we have employed three classifification techniques: Neuralnetworks (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 CASIAiris database.