Indonesian Coffee Bean Quality Classification Using Convolutional Neural Network (CNN)

Coffee is one of Indonesia's agricultural / plantation products. To make processed coffee products, coffee of certain quality is required in accordance with SNI 01-2907-2008. The classification of the quality of coffee beans so far has relied on human capabilities with all its weaknesses. In this paper, we performed the classification of coffee beans using the VGG16 architecture of the Convolutional Neural Network (CNN). The test results show that CNN is able to classify the image of coffee beans quite well, the level of accuracy that has been reached by 80%.