Paper Details: Downloads: 3161
Serial Number: P1152107693
Title: Face Recognition using Fast Fourier Transform and SVM Techniques
Authors: S. Ben Chaabane and R. Harrabi and I. Labiedh and H. Seddik
Abstract: A new method of face recognition based on fast Fourier Transform (FFT) and SVM techniques is presented. The FFT is applied to the entire database, the absolute values of FFT features are computed for each image also arranged in column vector, and the same is repeated on test database. The Principal Component Analysis (PCA) is used to generate a final set of features whereas; the SVM is employed for classification task. Face recognition from the proposed method is validated and the True Success Rate (TSR) for the test data available is evaluated. Then a comparative study versus existing techniques is presented. Face Recognition using FFT and SVM is better compared to existing state of the art methods.
Keywords: Face recognition, Fast Fourier Transform, Principal Component Analysis, True Success Rate, Support vector machine, Classification
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 21
Issue: 1
Submission Date: 2/7/2021 12:00:00 AM
Review Date: 2/11/2021 12:00:00 AM
Publishing Date: 4/8/2021 12:00:00 AM
Article Downloads: 3161
Download:

Facebook