Facial Expression Recognition Based On Static Image

Facial expression recognition is an extremely promising biometric technology. It isaiming at enhance the friendliness and intelligent of human-computer interaction byrecognizing human facial expressions, and analyzing their emotions. Thus it has a wide rangeof application and possesses a practical value. In recent years, facial expression recognitiontechnology has achieved unprecedented development, but its recognition accuracy inapplications is still difficult to meet practical expectations, it is mainly due to vulnerability tointerference and the weak discrimination of expression feature. So the performance is not asgood as Face recognition and fingerprinting recognition.In this paper, we study two kinds of common facial expression recognition featureextraction algorithm, namely Gabor wavelet and Local Binary Pattern (LBP), and proposelocal Gabor binary Pattern (LGBP), it uses LBP to encode facial expression that extracted byGabor features. And we project the extract characteristic to low-dimension by using localpreservation projection (LPP) algorithm, it makes the algorithm more efficiency. By analyzingthe theory of Support Vector Machine (SVM) and K nearest neighbor classifier, we find SVMhas serious confusion in the vicinity of the sample interface, however, K nearest neighborclassifier can take advantage of information classification of samples near the surface, but theoperation is rather high. This paper focuses on the method that combine them to improve theperformance of both algorithms. And the result of simulation indicates the superiorperformance of the proposed approach.