An Image-Based Identification System of Bubalus Bubalis Using Image Processing Feature Extraction by Linear Discriminant Analysis

Abstract

Animal identification allows producers to keep records on the most important information such as breed, date of birth, and gender. Plastic tags on water buffaloes (Bubalus Bubalis) are prone to damage and in order to be read, they should be restrained. The main objective of the study is to create a portable device that can identify the buffalo by taking its facial image. This study shows that with the use of Linear Discrimant Analysis (LDA), the water buffaloes can be identified by just taking a photo of its face for training images and testing images. In comparison with various algorithms used for the identification of water buffaloes, Local Binary Patterns Histograms (LBPH) shows more accurate results compared to other algorithms such as Principal Component Analysis (PCA), Linear Discriminant Analysis with Support Vector Machine (LDA+SVM) and LDA alone. The output of the simulated training images and testing images show favourable results indicating effectiveness of the study.