An Artificial Intelligence - Based System For Automated Detection of Rice Leaf Diseases

SOLOMON ANAB; RICHARD BADASU; MUSTAPHA ADAMU MOHAMMED; GODBLESS MENSAH

doi:10.36948/ijfmr.2026.v08i02.71969

An Artificial Intelligence - Based System For Automated Detection of Rice Leaf Diseases

Author(s)	Mr. SOLOMON ANAB, Mr. RICHARD BADASU, Dr. MUSTAPHA ADAMU MOHAMMED, Mr. GODBLESS MENSAH
Country	Ghana
Abstract	Food security and sustainable agriculture have placed an increasing strain on the need to detect crop disease in a methodical and dependable way. Rice (Oryza sativa), one of the main food sources of over half the world population, is very susceptible to diseases like brown spot, leaf smut, and bacterial blight, which have great impact on production and grain quality. Conventional disease detection techniques are most often based on manual identification by specialists that is time consuming, subjective and in many cases unavailable to the smallholder farmers in rural regions. In order to overcome these difficulties, this paper proposes the design and implementation of an automated rice disease detection system based on deep learning and image processing. The system uses a Convolutional Neural Network (CNN), which has been trained using a variety of rice leaf images using the ResNet50 architecture. This model had a training accuracy of 90% and a loss value of 0.45 which indicates high learning and generalization ability. It is based on a user-friendly web interface built using Flask that enables farmers and researchers to upload rice leaf images to predict disease in real-time. The system involves processing the image and labelling it as either healthy or diseased, and giving it a confidence score and the anticipated disease category. Evaluation outcomes reveal an equal amount of average confidence of 76.65% and a processing time of 2.67 seconds, which is efficient and reliable. The suggested system shows how artificial intelligence has the potential to revolutionize the agricultural diagnostics market through offering a low-cost scalable solution to early detection of rice diseases. It helps to enhance yield, decrease the use of pesticides, and to make wise decisions among farmers. The addition of mobile applications and the scale of the disease dataset, as well as the implementation of the model on drones to monitor large-scale fields, can be considered future improvement points that will assist in the digital transformation of precision agriculture.
Keywords	Accuracy, Confidence score, Disease, ResNet50, Rice
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-04-03
DOI	https://doi.org/10.36948/ijfmr.2026.v08i02.71969

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

An Artificial Intelligence - Based System For Automated Detection of Rice Leaf Diseases

Share this