Face Feature Extraction Based on Fast 2D-DCT Algorithm
LI Zu-yu · Computer and Modernization · 2013
Discrete cosine transform(DCT) has an advantage that is the image signal processing without affecting image quality.The paper proposes a new algorithm for face feature extraction.The face image is the first segmented in average,and the fast 2D-DCT algorithm instead of common DCT algorithm is used in the stage of feature vector extraction.The new algorithm has been tested,and the result proves that 2D-DCT can reduce most of time for the stage of face recognition or can extract more DCT coefficient than common DCT algorithm.Experimental results show that the proposed algorithm is fast and effective.