An Innovative Study on PCA and ICA Based Face Recognition System for Static Images Using Interval Type2 Fuzzy Logic

Within the last several years, Recognition of Human's Facial Expression has been very active research area of computer vision. It has the important role in the human-computer interaction (HCI) systems. This paper proposes a novel interval type2 fuzzy method for facial expression recognition on still images of the face. The new technique involves in extracting mathematical data from some special regions of the face and fed them to an interval type2 fuzzy rule-based system. Fuzzy fictions operation uses trapezoidal membership functions for both input and output. The Distinct feature of a system is its simplicity and high accuracy. Experimental results on database indicate good performance of the developed technique. New approach of information extraction based on interval type2 fuzzy logic, which can be used for robust face recognition system is proposed here. The results clearly confirmed the superiority of proposed approach. To improve the face recognition performance, a PCA-ICA signal preprocessing and interval type2 fuzzy based recognition algorithm is proposed. In this approach, signals of human face are firstly preprocessed effectively by combination of Principal Component Analysis (PCA) and Independent Component Analysis (ICA), and then processed with interval type2 fuzzy logic for the purpose of face recognition.