Recognition of facial expression is a challenging problem for machine in comparison to human and it has encouraged numerous advanced machine learning algorithms. It is one of the methods for emotion recognition as the emotion of a particular person can be found out by studying his or her facial expressions. In this paper, we proposes a generic algorithms for recognition of emotions and illustrates a fundamental steps of the four algorithms such as Eigenfaces (Principal Component Analysis [PCA]), Fisherfaces, Local Binary Pattern Histogram (LBP) and SURF with FLANN over two databases Cohn-kanade database and IIT BHU student face images as benchmark database.The objective of this book chapter is to recognize the emotions from facial images of individuals and compare the performances of holistic algorithms like Eigenfaces, Fisherfaces, and texture based recognition algorithms LBPH, hybrid algorithm SURF and FLANN. Matching efficiency of individual emotions from facial expression databases are labeled for training and testing phases. The set of features is extracted from labeled dataset for training purpose and test images are matched with discriminative set of feature points. Based on that comparison, we conclude that Eigenfaces and Fisherfaces yields good recognition accuracy on the benchmark database than others and the efficiency of SURF with FLANN algorithm can be enhanced significantly by changing the parameters.
Top1. Introduction
The automatic recognition of emotions from facial expression is a well-known problem in field of computer vision, pattern recognition and image analysis. The image analysis includes both computations and measurements from facial motion to recognize the expression. It is getting proliferations in the variety field of applications and uses. But it has major challenges problems due to large intra-class variation, varying pose, illumination change, partial occlusion, and cluttered background in the field of computer vision. The research study of facial expression of emotion has long been the focus of theoretical controversy and empirical research (Allport, 1924) (Birdwhistell, 1963) (Coleman, 1949), (Darwin, 1872a,1998b), (Ekman, 1973a, 1994b) (Fridlund, 1999), (Hunt, 1941) (Landis, 1924), (Mead, 1975), (Munn, 1940), (Osgood, 1966), (Russell, 1994), (Schlosberg, 1954) (Woodworth, 1938), (Keltner et al., 2003). However, scientist and researchers have recently made momentous progresses on a particularly interesting subset of object recognition problems: face (Rowley, Baluja & Kanade, 1998), (Viola, & Jones., 2004), (Xiao et al., 2007) and human detection (Dalal N, & Triggs, 2005) achieving near 90% detection rate on the frontal face in real-time (Viola, & Jones, 2004) using a boosting based approach. Meanwhile, with the recent advance on robust facial expression detection, some major image search engines start to use high level image features to filter text based image search results (Cui et al., 2008). For example, recognition of facial expression form given database already integrated human face detection as a high level filter in computer vision approaches. However, designing of efficient algorithm for facial expression of human face is still a challenging problem.