As an effective approach of blind source separation (BSS)

independent component analysis (ICA) is a recently developed method in facial expression recognition field

which is used to effectively extract the hidden information of expression images and can improve the rate of expression recognition. Facial expression provides a crucial measure for studies of human emotion

cognitive processes

and social interaction. The key focuses of facial expression recognition are the extraction of expression features and the expression states using features. This paper proposes an expression recognition system based on ICA and hidden markov model (HMM). The system includes two parts: First

it is applied to extraction of expression features using ICA algorithm. In this process it adopts FastICA algorithm in order to increase the speed of feature extraction and its function is prior to primary component analysis (PCA). Second

it is applied to recognizing facial expression using seven HMMs its time efficiency is prior to support vector machine (SVM). Experimental results show that the system increases the whole effectiveness and accuracy of facial expression recognition

and prove that the algorithm is efficient and feasible.