Deep Learning Approach for the Morphological Differentiation of Corn Seed Types

Corn is one of Indonesia’s main food ingredients that contains the second largest source of carbohydrates after rice. Classification of the type and quality of corn seeds is still conducted manually by farmers. This procedure is time-consuming and can result in inaccuracies in sorting. Morphology has important characteristics to determine varieties such as size, color, area and seed shape. Some of these attributes, if measured manually, will take a long time and its complexity requires special expertise. An effective approach for describing these characteristics is using machine learning techniques. The machine learning used is Convolutional Neural Network (CNN). The CNN models used are ResNet50, ResNet101, VGG-19 and MobileNetV2. An analysis of the performance of the model was carried out using a confusion matrix. The results of the CNN model performance parameters for the classification of corn seed varieties with the ResNet50 model showed the best performance with accuracy of accuracy of 92.54%, precision of 90.40%, a recall of 90.84% and an F₁-score of 90.26%.