Based on the static gray image expression database, a recognition algorithm is given by using multiple facial expression features to construct multi-classifier. Aiming to improving speed of extracting features, features of expression that are extracted by local Gabor wavelet transformation on the selected facial landmark are used to constructing facial elastic templates. Geometric features and Fisherfaces features are extracted on the facial effective area extracted by elastic templates. Primary integrated SVM should be constructed by combining with Geometric features; Secondary integrated SVM should be constructed by combining with Fisherfaces features. Compared with the single features, the experimental results showed that recognition rate and robustness are improved by using multiple facial expression features to construct multi-classifier.