Klasifikasi Citra Menggunakan Metode Minor Component Analysis pada Sistem Temu Kembali Citra

Abstract

This paper presents a method for image classification. In content-based image retrieval (CBIR) system, retrieving process is done by comparing a query image to all images from image database. This process is not effective because spends much times besides the retrieved images are not always match with the query image particularly for large databases. To solve this problem, image classification is proposed. In this research, minor component analysis (MCA) is used for images classification. For each image, a feature vector describing color, shape and texture. MCA vector will be formed as a representative pattern for each images class. In classification process, image database divided for image training and testing. Train data used to build classification model while test data used for test the accuracy of classification model. From this research it can be concluded that usage of MCA can improve the accuracy about 33.20%. This improvement shows that MCA can be applied in CBIR system, especially for large images database.