<![CDATA[Classification of types of chili vegetables is an important aspect in the agricultural industry to increase the efficiency of product management, packaging and distribution. This research aims to implement the Principal Component Analysis (PCA) method in the process of classifying vegetables and types of chilies. PCA is used to reduce the dimensionality of the data and extract the main features that are significant in distinguishing vegetable categories. The research dataset consists of digital images of chili vegetables which are extracted into color, texture and shape attributes. The research results show that PCA is able to significantly improve classification accuracy by minimizing computational complexity. Experiments were carried out with various numbers of principal components in PCA to determine the optimal configuration. In the best configuration, this method achieves classification accuracy of 90%, with PCA effectively reducing data dimensionality by up to 95% without losing important information. In conclusion, this approach has great potential to be implemented in vegetable classification automation systems to support efficiency in agricultural supply chains.]]>
