Datasets
Standard Dataset
Banana Dataset
- Citation Author(s):
-
Md. AtaurRahman
Fab Lab IUB, Independent University, Bangladesh - Submitted by:
- Md. Ataur Rahman
- Last updated:
- Sun, 03/09/2025 - 15:30
- DOI:
- 10.21227/dn9b-9y70
- License:
31 Views- Categories:
- Keywords:
Abstract
Bananas are widely farmed and consumed, offering essential nutrients like manganese, vitamin B6, vitamin C, and magnesium. They come in various breeds with distinct visual traits, including size, shape, color, texture, and skin patterns. To classify these varieties, five deep learning models—VGG16, ResNet50, MobileNet, Inception-v3, and a customized CNN—were trained on banana images. These models enhance quality control and supply chain management by accurately identifying banana breeds. Performance evaluation showed that the customized CNN model achieved the highest accuracy of 99.37%, making it the most effective for precise banana classification in agricultural and food industries using machine learning and computer vision.
Bananas are widely farmed and consumed, offering essential nutrients like manganese, vitamin B6, vitamin C, and magnesium. They come in various breeds with distinct visual traits, including size, shape, color, texture, and skin patterns. To classify these varieties, five deep learning models—VGG16, ResNet50, MobileNet, Inception-v3, and a customized CNN—were trained on banana images. These models enhance quality control and supply chain management by accurately identifying banana breeds. The dataset used for training and evaluation consisted of 5,100 banana images, ensuring a diverse representation of different breeds. Performance evaluation showed that the customized CNN model achieved the highest accuracy of 99.37%, making it the most effective for precise banana classification in agricultural and food industries using machine learning and computer vision.
