Classification of jackfruit and cempedak using convolutional neural network and transfer learning

Jackfruit (Artocarpus integer) and Cempedak heterophyllus) are two different Southeast Asian fruit species from the same genus that quite similar in their external appearance, therefore, sometimes difficult to be recognized visually by humans, especially form of pictures. Convolutional neural networks (CNN) transfer learning can provide an excellent solution recognize fruits, where methods known able classify objects with high accuracy. In this study, several models were proposed constructed using a deep convolutional network (DCNN). We our custom-made own CNN model modify five on pre-trained VGG16, VGG19, Xception, ResNet50, InceptionV3. The experiment used dataset result showed architecture was accuracy between 89% 93.67% compared other learning.