Comparitive Study of Dimension Reduction Techniques for Mood Detection

The expression recognition system is closely related to face recognition where a lot of research has been done and a vast array of algorithms has been introduced. The mood detection system can also be considered as a special case of a pattern recognition problem and many techniques are available. In the designing of a Mood Detection System, we can take advantage of these resources and use existing algorithms as buildin g blocks of our system. In this research work comparative study of mood detection techniques namely Principal Component analysis (PCA), PCA with Fisher face is done. The major part of this paper will explore and compare that the combination of PCA and Fisher face is more optimized than former technique. The experiments have been performed on real time database to figure out the performance of desired algorithm in terms of recognition rate and computational time. There are five different moods which are to be recognized are: Happy, Disgust, Angry, Sad and Surprise.