Home > Engineering > Computer Engineering > Special Issue > Smart Innovations in Computer Science and Applications > A Computer Vision Method for Plant Leaf Disease Early Detection

A Computer Vision Method for Plant Leaf Disease Early Detection

Call for Papers

Volume-10 | Issue-5

Last date : 27-Oct-2026

Best International Journal
Open Access | Peer Reviewed | Best International Journal | Indexing & IF | 24*7 Support | Dedicated Qualified Team | Rapid Publication Process | International Editor, Reviewer Board | Attractive User Interface with Easy Navigation

Journal Type : Open Access

First Update : Within 7 Days after submittion

Submit Paper Online

For Author

Research Area


A Computer Vision Method for Plant Leaf Disease Early Detection


Manasvi Gajbhiye



Manasvi Gajbhiye "A Computer Vision Method for Plant Leaf Disease Early Detection" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Special Issue | Smart Innovations in Computer Science and Applications, March 2026, pp.283-301, URL: https://www.ijtsrd.com/papers/ijtsrd101624.pdf

Crop diseases are a serious worldwide concern because they cause yield losses of 20–40% per year and have a substantial effect on the food security of expanding populations. In order to minimize excessive pesticide use, minimize crop damage, and stop the spread of disease, early and precise disease identification is crucial. Traditional techniques of detection, however, rely on the human visual inspection of skilled agricultural professionals, which is subjective, time-consuming, and frequently unavailable to farmers in remote or rural locations. The lack of plant pathologists causes additional delays in diagnosis and treatment, which leads to avoidable financial losses. Plant disease identification can be automated with the help of breakthroughs in deep learning and computer vision. This will allow for quick, scalable, and expert-level diagnosis using smartphone apps that farmers may use anywhere in the world. The comprehensive AI-based leaf disease detection system presented in this study makes use of cutting-edge Convolutional Neural Networks (CNNs) with transfer learning strategies. Pre-trained architectures such as ResNet-50, VGG-16, and MobileNetV2 were refined using a dataset of 87,000 leaf pictures from 14 crop species, including tomato, potato, corn, grape, apple, cherry, peach, pepper, and strawberry, that represented 38 disease categories. The dataset contains leaves in good health as well as those with bacterial, viral, fungal, and nutritional deficiencies. In order to improve resilience and generalization in real-world imaging scenarios, the effective dataset was enlarged to over 200,000 photos with intensive data augmentation, including flipping, zooming, rotation, brightness and contrast correction, and color jittering. Multi-class classification, deep feature extraction, semantic segmentation-based background removal, picture preprocessing, disease severity estimation based on impacted leaf area, and a treatment recommendation engine linked to agricultural knowledge bases are all integrated into the system architecture. The entire framework is made available as an intuitive mobile application with multilingual support, offline capabilities, and integration with agricultural extension agencies for professional advice as needed. During a four-month growing season, 150 farmers from Maharashtra, Punjab, and Karnataka participated in field validation, which showed excellent real-world performance. The technology produced results in an average of 8.3 seconds from image collection and achieved 93.7% practical diagnostic accuracy when compared to expert pathologist ratings. 89% of users were satisfied, and 67% of the time the system was able to identify ailments in their early stages, before they were obvious to untrained observers. Due to focused treatment suggestions, quicker treatment commencement than with standard expert consultation delays, and projected crop loss reductions of 15–25%, farmers reported a 32% decrease in pesticide usage. According to economic research, yield preservation and optimized input costs resulted in a 340% return on investment in a single growing season. Additionally, by enhancing agricultural extension databases through crowdsourcing validation, enabling regional disease monitoring, and increasing farmer awareness of disease indicators and management strategies, the system exhibited its promise as a scalable solution.

Transfer Learning, Plant Disease Detection ResNet, MobileNet, Precision Agriculture, Computer Vision, Agricultural Technology, Mobile Applications, Image Categorization, Smart Farming, Crop Health Tracking, Deep Learning, and Convolutional Neural Networks


IJTSRD101624
Special Issue | Smart Innovations in Computer Science and Applications, March 2026
283-301
IJTSRD | www.ijtsrd.com | E-ISSN 2456-6470
Copyright © 2019 by author(s) and International Journal of Trend in Scientific Research and Development Journal. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0) (http://creativecommons.org/licenses/by/4.0)

International Journal of Trend in Scientific Research and Development - IJTSRD having online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International Journal which provides rapid publication of your research articles and aims to promote the theory and practice along with knowledge sharing between researchers, developers, engineers, students, and practitioners working in and around the world in many areas like Sciences, Technology, Innovation, Engineering, Agriculture, Management and many more and it is recommended by all Universities, review articles and short communications in all subjects. IJTSRD running an International Journal who are proving quality publication of peer reviewed and refereed international journals from diverse fields that emphasizes new research, development and their applications. IJTSRD provides an online access to exchange your research work, technical notes & surveying results among professionals throughout the world in e-journals. IJTSRD is a fastest growing and dynamic professional organization. The aim of this organization is to provide access not only to world class research resources, but through its professionals aim to bring in a significant transformation in the real of open access journals and online publishing.

Thomson Reuters
Google Scholer
Academia.edu

ResearchBib
Scribd.com
archive

PdfSR
issuu
Slideshare

WorldJournalAlerts
Twitter
Linkedin