Penerapan Teknologi CNN Dalam Proses Pendeteksi Kematangan Buah Stroberi

The process of manually identifying fruits to determine ripe and unripe can affect the production and quality of the food and beverages themselves. The CNN method is able to group images and analyze images based on objects. Therefore, it is necessary to conduct research using the CNN method on the ripeness of strawberries. This study aims to determine the level of maturity of strawberries during harvest time. The accuracy graph shows that the model is not only capable of learning the training data well but can also generalize well to the validation data. In contrast, the validation accuracy graph starts from 0.825 in the 0th epoch and rises consistently until it reaches 0.975 in the 30th epoch. Both charts remained stable above those values throughout the training period. Overall, the development of the CNN model for the detection of strawberry ripeness resulted in excellent performance. The model achieved the lowest loss of 0.0383 and an accuracy as high as 98% on the validation data, demonstrating a strong ability to accurately predict between ripe and unripe strawberries.