Facial Expression Recognition Analysis with Muti-Scale Filter

The design of filters is the key step of facial expression extraction. Frequency and orientation of the filters can simulate those of the human visual system, and they have the characteristics of being particularly appropriate for texture representation and discrimination. The paper presents the wavelet filter provided with 3 frequencies, 8 orientations. In according to actual demand, it can extract the feature of low quality facial expression image target, and have good robust for automatic facial expression recognition. Experimental results show that the performance of the proposed filter achieved excellent average recognition rates, when it is applied to facial expression recognition system. (C) 2012 Published by Elsevier B.V. Selection and/or peer-review under responsibility of Garry Lee