Facial Expression Recognition using Kirsch Edge Detection, LBP and Gabor Wavelets

Facial expression recognition (FER) plays a vital role in human computer interaction and has become important filed of choice for researchers in computer vision and artificial intelligence over the last two decades. Illumination, pose, zoom level are major obstacles in the classification of FER. A good preprocessing and feature extraction algorithm would improve the performance of FER. In this paper, two models are proposed for FER using Gabor wavelets and Local binary pattern (LBP) for feature extraction using kirsch edge detection algorithm for preprocessing in these methods. Support vector machine (SVM) classifier gives good recognition accuracies on benchmark datasets Cohn Kanade, JAFFE, MMI and KDEF.