Fruit Disease Detection Utilizing Colour, Surface and Deep Learning Methods

TITLE	Fruit Disease Detection Utilizing Colour, Surface and Deep Learning Methods
ABSTRACT	To improve crop quality and support agriculturalists with timely disease control, this research proposes an automated system for mango fruit disease identification. Traditional inspection methods are manual, time-consuming, and error-prone, often leading to low productivity and financial losses. To address this, a Convolutional Neural Network (CNN) trained on a custom dataset of healthy and diseased mango images is used to classify fruit diseases with confidence scores. K-means clustering is applied for image segmentation to highlight infected regions and enhance interpretability. The system is deployed as a Django-based web application, enabling users to upload fruit images and instantly receive predictions along with disease-specific management recommendations. This approach ensures faster, more accurate, and cost-effective disease detection, improving agricultural quality control.
AUTHOR	Chirag, Dr Raghavendra S P
PUBLICATION DATE	2025-09-01 19:31:21
VOLUME	13
ISSUE	3
DOI	DOI: 10.15662/IJMSERH.2025.1303062
PDF	pdf/2025/7/62_Fruit Disease Detection Utilizing Colour, Surface and Deep Learning Methods.pdf
KEYWORDS

Article