PCA Based Extracting Feature Using Fast Fourier Transform for Facial Expression Recognition

Abstract

Facial expression recognition is prevalent in research area, and Principal Component Analysis (PCA) is a very common method in use. Noticing that few researches focus on pre-processing of images, which also enhances the results of PCA algorithm, we propose an improved approach of PCA based on facial expression recognition algorithm using Fast Fourier Transform (FFT), which combines amplitude spectrum of one image with phase spectrum of another image as a mixed image. Our experiments are based on Yale database and self-made image database. Testing and evaluating in several ways, the experimental results indicate our approach is effective. ?