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

Abstrak

color of the fruit's skin. This method often produces different assessment results due
to the influence of subjective human factors. This research aims to create a system that
can recognize banana ripeness using digital images using a convolutional neural
network (CNN) method. Data were collected by photographing bananas using a mobile
phone 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, normalizing
pixel values, converting the color format to RGB, data augmentation, training the CNN
model, and evaluating model performance. The CNN architecture used consisted of
three convolutional layers, three max-pooling layers, a flatten layer, a dropout layer, and
a 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 CNN
method's success in recognizing banana ripeness from digital images.