Single-input and multi-input local binary pattern classification

Identification and classification of species are crucial for maintaining genetic diversity and supporting sustainable agricultural practices. The Toraja Buffalo, a unique type of buffalo in Indonesia, holds high cultural and economic value. Accurate classification of this species is essential to preserving genetic resources and improving breeding programs. Previous studies using single classification methods have shown limitations in complex cases such as the Toraja Buffalo, which has numerous physiological characteristics such as body size, head, horns, tail, and eyes. The purpose of this study is to evaluate and compare the performance of single-classification and multi-category methods for identifying Toraja Buffalo. Several algorithms, including K-Nearest Neighbors (K-NN), Random Forest, Support Vector Machine (SVM), and Naive Bayes, were tested using Local Binary Pattern (LBP) for feature extraction. Decision Tree and others were observed, showing 85.83% accuracy in single-input, while multi-input accuracy reached 92.08%. The multi-input approach consistently improved performance across all algorithms. Multi-input classifiers significantly outperformed single-feature methods, with Random Forest being the most efficient algorithm. Future research could incorporate additional variables such as skin color or genetic profiles to further enhance accuracy.