Classification of Shape Bean Coffee Using Convolutional Neural Network

Abstract

Deep Learning is a sub-field of Machine Learning in addresses the development of an image classification. This study uses a Deep Learning algorithm to classify the shape of coffee beans which consist of 4 types, namely defect, longberry, peaberry, and premium. We use the Convolutional Neural Network to classify the shape of the coffee beans. This study combines the Convolutional Neural Network algorithm with Adam's optimization to get the best results. The research dataset uses training data from 4800 images and testing data from 1600 images with four classes. The results of this study get an accuracy result of 90,63%, a precision result of 88,23%, and a recall result of 95,74%. Based on the results obtained the Convolutional Neural Network with Adam's optimization can be applied to the classification of coffee bean shapes with good results.