A real time race classification system

Abstract

This paper presents the progress toward a face detection and race classification system that is robust and works in real-time. We address the race classification problem as classifying a frontal face into Asian or non-Asian. Firstly, we propose principal component analysis (PCA) for feature generation and independent component analysis (ICA) for feature extraction. Then, we use SVM for training process and combine different SVM classifiers to some new classifiers, which improve the classification rate to a new level. Experiments show that our system achieves a classification rate of 82.5 % based on a database containing 750 face images from FERET.