An Efficient Facial Expression Recognition Using Curvelet Transform Based RLBP and Distinct LBP Feature

Abstract: The project presents human emotion recognition from face images based on textural analysis and knn classifier. Automatic facial expressionrecognition (FER) plays an important role in HCI systems for measuring people‟s emotions has dominated psychology by linking expressions to a group of basic emotions (i.e., anger, disgust, fear, happiness, sadness, andsurprise). The recognition system involves face detection, features extraction and finally classification. The face detection module will be used to obtain face images, which have normalized intensity, are uniform in size and shape anddepict only the face region. The distinct LBP is used to extract the features texture from face regions to discriminate the illumination changes also RLBP for texture feature extraction. These features are useful to distinguish the maximum number of samples accurately and the KNN classifier based on discriminant analysis is used to classify the six different expressions. The simulated results will be shown that the DLBP and RLBP based feature extraction with used classifier gives much better accuracy with lesser algorithmic complexity than other facial expression recognition approaches.

Keywords: Pre-processing, Curvelet Transform, Distinct LBP, RLBP, KNN classifier.