To search, Click below search items.


All Published Papers Search Service


iBanana: Intelligent Method for Banana Ripeness Detection and Analysis using Convolutional Neural Network


Andi Bese Firdausiah Mansur, Arwa Abdulwahab Mashat, Nouf Al-mohammadi


Vol. 22  No. 11  pp. 493-502


Researchers have demonstrated that teaching children could be improved by using technology to teach them rather than by following traditional methods to instruct them about detecting fruit ripeness, which is one of the challenging problems in harvesting fruit for farmers. Most farmers still rely on manual inspection to check the ripeness of fruits. An innovative solution using computer vision and artificial intelligence might help people select fruit based on its color intensity in order to harvest the best quality fruit. This project detects banana fruit quantity and ripeness using computer vision based on seeing, recognizing and analyzing an image. To capture fruit from a photo, the system must go through phases to process each layer of the given image. The system recognizes the quantity and ripeness of fruit using image-based computer vision and deep learning. This system uses a convolutional neural network (CNN) to analyze fruit images after a person (user) first uploads an image. The system compares the classifier image with a stored image in the dataset from the disk. Using the pretrained model VGG16, the system achieves more than 95% accuracy in detecting fruit ripeness. This system is expected to be helpful in the hands of the people who collect fruit based on their knowledge and reliability, to make sure they buy a good grade of fruit.


Fruit ripeness, Artificial Intelligence, Convolutional neural network