Defect Detection of Agricultural Commodities using Image Processing and Artificial Neural Networks

Abstract

Production losses of agricultural commodities on agricultural land due to product defects depend on the level of pest and disease attacks. Defects cause the product not to be harvested or rejected by the market. Data from the Ministry of Agriculture of the Republic of Indonesia in 2021 shows the percentage of defective products for this commodity is 5%. This study aims to detect defects in agricultural products using image processing and artificial neural networks. We used the screening threshold method with potato research samples from Dieng, Indonesia. The study results for spot defects showed that from 100 training data, there were five incorrect identification data, so the accuracy of the training process was 95%. At the same time, the hole defect accuracy is better, which is 97%. It shows that defects in agricultural commodities can be detected using this method. For further research, the development of agricultural product sorting can combine sorting techniques with this method.