Chilli Quality Classification using Deep Learning
Sudianto Sudianto, Yeni Herdiyeni, Anggra Haristu, Hendradi Hardhienata
Abstract
Chilli peppers (Capsicum annuum) are potential commodities in Indonesia that have relatively high economic value. Sorting and grading of chilli peppers after harvesting is very important for separating the post-harvest results to determine whether the chillies are in good or bad conditions. Currently, these activities are still done manually using visual observation. The problem of using this manual method is that the process often becomes time-consuming. Another drawback of utilizing manual methods is that it has often inconsistent results. This study aims to develop a decision support system for classifying the quality of chillies using deep learning. The development of the science and technology of digital image processing makes it possible to sort agricultural and plantation products automatically. In this research, we employ “You Only Look Once” (YOLO) method which is one technique of the deep learning methods that is widely used for image recognition in real-time. Simulation results from the custom model show that the classification accuracy obtained from the simple test is 99.4% and the challenging test is 75.6%.