Classification of Mangosteen Surface Quality Based on Image Processing Using Support Vector Machine

Mangosteen is one of the highest export commodities among other fruits in Indonesia. Mangosteen should be free from defects and damages to be accepted as export quality. In most of the mangosteen plantation in Indonesia, sorting of mangosteen is performed manually with human eye. This method is less effective and inaccurate because it depends on workers’ conditions and perceptions. The use of image processing technology for quality inspection has been done for various fruits. However, mangosteen quality inspection in Indonesia has not used image processing technology. The objective of this research is to develop a method using support vector machine to classify defect and non-defect mangosteen surface. The method involved mangosteen surface image capture, pre-processing, defect features extraction using Curvelet transformation and classification using support vector machine. The proposed method was implemented on 120 images which produced 96.67% of accuracy. It can be concluded that the proposed method has successful classify mangosteen surfac