Face Recognition Using Various Feature Extraction Approaches

Abstract

This paper introduces an experimental study on the recognition of the person’s face by utilizing three Techniques of extraction: Principle Components Analysis (PCA), Linear Discriminant Analysis (LDA) and Contourlet- Curvelet Transform (CCT). The results of these approaches were observed and compared to discover the perfect scheme for identification of human faces. The tests have been carried out on the faces databases of (ORL),(UMIST), and (JAFFE). The results acquired by the methods were quantified by altering the ratio of train to test photos in three categories: 75/25, 55/45 and 35/65. The evaluation results showed that the CCT extraction method provides better results than the others. The highest recognition rate was recorded for the CCT approach (recognition rate=98.980%) when the (train/test) photos ratio is (75/25). Furthermore, the best recognition rates for the LDA and PCA were 96.391% and 95.127% respectively. The Matlab R2019b program was used for implementing and testing the algorithms.