STUDY ON THE INFLUENCE OF PCA PRE-TREATMENT ON PIG FACE IDENTIFICATION WITH SUPPORT VECTOR MACHINE (SVM)

Abstract

To explore the application of traditional machine learning model in the intelligent management of pigs, in this paper, the influence of Principal Components Analysis (this method is simply referred to as PCA) pre-treatment on pig face identification with Support Vector Machine (this method is simply referred to as SVM) is studied. By testing method, the kernel functions of two testing schemes, one adopting SVM alone and the other adopting PCA+SVM, were determined to be poly and Radial Basis Function, 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 88.85% from 83.66% by the improved scheme, also the training time as well as testing time were reduced to 30.1% and 20.97% of the original value in the earlier scheme, respectively. It indicates that PCA 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.