Identifikasi Hama Tanaman Cabai dengan Membandingkan Principal Component Analysis dan Gray Level Co-Occurrence Matrix

Abstract

Chili is one of the highly regarded vegetables and fruits economically. Chili’s productivity is highly affected by the presence of its pests. Pest identification can done by automatic system pests identification based on image. In this research, two features extraction algorithms are used for the system, i.e. Principal Component Analysis (PCA) and the Gray Level Co-Occurrence Matrix (GLCM), and the classification method Probabilistic Neural Network (PNN). PCA parameters are setup using proportion of 80%, 90%, and 95 % while GLCM uses angles of 0o, 45o, 90o, and 135o. The results show that GLCM outperforms PCA in term of accuracy, with accuracy level 72% for GLCM and 65% for PCA.