About this document

Mango Breed Detection Using CNNs by usm4nmusic is a document available to read on EtoBox.

This conference paper presents a computer vision system utilizing Convolutional Neural Network (CNN) models for detecting five local mango breeds in Bangladesh. The study involved analyzing 15,000 images and comparing three different CNN models, with the best model achieving an accuracy of 92.80%. The paper discusses various methodologies, including image acquisition, noise removal, and overfitting elimination techniques to enhance the classification performance.

Author

usm4nmusic

Language

EN