To explore the application of traditional machine learning model in the intelligent management of pigs, in this paper, the influence of LDA pre- treatment on pig face identification with SVM is studied. By testing method, the kernel functions of two testing schemes, one adopting SVM alone and the other adopting LDA+SVM, were determined to be poly and RBF, whose coefficients were 0.03 and 0.01, respectively. With individual identification tests carried out on 10 pigs respectively, the identification accuracy was increased to 86.30% from 83.66% by the improved scheme, also the training time as well as testing time were reduced to 0.7% and0.3% of the original value in the earlier scheme, respectively. It indicates that LDA pre-treatment had a positive effect on improving the efficiency of individual pig identification with SVM. It provides experimental support for the mobile terminals and embedded application of SVM classifiers.