Facial Emotion Recognition Using Different Multi-resolution Transforms

The present work investigates the performance of different multiresolution transforms in the application of emotion recognition from facial images. Multi-resolution analysis of image provides frequency information along with time information in different scale, orientation and locations. The emotion information from facial images was being captured by different multiresolution algorithm such as Wavelet Transform, Curvelet Transform and Contourlet Transform. Wavelet transform mainly approximate frequency information along with time whereas curvelet transform is best to capture edges information with very few coefficients. Various statistical features obtained from different algorithms have been used to build reference model. The classification part was done using support vector machine (SVM) and K-Nearest Neighbor (KNN) classifier with JAFFE, a Japanese facial emotion database. The individual as well as comparative study of different algorithms was done successfully.