Deteksi Tingkat Kematangan Buah Pisang Berdasarkan Citra Digital Menggunakan Metode Convolutional Neural Network (CNN)

Faidatul Hanafiyah (Universitas Ibrahimy)
Farihin Lazim (Universitas Ibrahimy)
Firman Santoso (Universitas Ibrahimy)

Jurnal Ilmiah Teknik Informatika (TEKINFO)
Vol. 27 No. 2 (2026): TEKINFO Vol 27 No 2 Oktober 2026

color of the fruit's skin. This method often produces different assessment results dueto the influence of subjective human factors. This research aims to create a system thatcan recognize banana ripeness using digital images using a convolutional neuralnetwork (CNN) method. Data were collected by photographing bananas using a mobilephone camera, and the bananas were categorized into four categories: unripe, ripe,overripe, and rotten. The research process consisted of several steps: data collection,data labeling, image processing by resizing the images to 224x224 pixels, normalizingpixel values, converting the color format to RGB, data augmentation, training the CNNmodel, and evaluating model performance. The CNN architecture used consisted ofthree convolutional layers, three max-pooling layers, a flatten layer, a dropout layer, anda dense layer. Tests demonstrated the model's ability to classify banana ripeness with up to 96% accuracy. Good precision, recall, and F1-score values indicate the CNNmethod's success in recognizing banana ripeness from digital images.