Vol 18 no.2 2018

Abimbola Ganiyat AKINTOLA1, Abdul-hafiz Taiwo ONIYANGI1, Muhammed Besiru JIBRIN2

1University of Ilorin, Department of Computer Science, Ilorin, Nigeria; 2Federal University of Kashere, Department of Computer Science, Gombe, Nigeria

Abstract

The necessary step that must be considered in developing efficient face recognition is feature extraction. The recognition accuracy of a face is determined by the amount of measurable and relevant features extracted from the face image. A number of feature extraction methods in appearance-based technique such as commonly used linear subspace techniques: Linear Discriminant Analysis (LDA), Locality Preserving Projections (LPP) Independent Component Analysis (ICA) and Principal Component Analysis (PCA) have been used in face recognition. The focus of this paper is to conduct comparative analysis on three appearance-based feature extraction algorithms: Linear Discriminant Analysis, Locality Preserving Projections and Principal Component Analysis by applying Contrast Limited Adaptive Histogram Equalization (CLAHE) approach to further know the influence on the performance of face recognition system.

Full Text:

PDF