Plant Nursery Management and Disease Detection Using Artificial Intelligence

Mrunal Rajesh Omanna , Dr. Shrenik Suresh Sarade

Although buying a plant is easy to do online today, knowing how to keep that plant alive afterward is not, and diagnosing what has gone wrong with it later is harder still. This study presents an Android application that combines both problems into one tool. On the retail side, it allows a buyer to shop for plants, seeds, fertilizers, and pots without a nursery visit, with care notes attached to each listing so that the guesswork of watering, light, and feeding schedules is removed. On the health side, it adds a camera-driven diagnosis feature: when a leaf starts showing symptoms, a photo of it is run through a Support Vector Machine (SVM) classifier trained to recognize common plant diseases, and the app responds with a likely diagnosis plus a practical remedy. The system was built iteratively under an agile process, with Android Studio driving the client, PHP and MySQL handling storage and business logic, and a Python/Flask service hosting the classifier. Unit, integration, and acceptance testing across these pieces confirmed that the combined shopping plus diagnosis workflow holds together end-to-end.

Although buying a plant is easy to do online today, knowing how to keep that plant alive afterward is not, and diagnosing what has gone wrong with it later is harder still. This study presents an Android application that combines both problems into one tool. On the retail side, it allows a buyer to shop for plants, seeds, fertilizers, and pots without a nursery visit, with care notes attached to each listing so that the guesswork of watering, light, and feeding schedules is removed. On the health side, it adds a camera-driven diagnosis feature: when a leaf starts showing symptoms, a photo of it is run through a Support Vector Machine (SVM) classifier trained to recognize common plant diseases, and the app responds with a likely diagnosis plus a practical remedy. The system was built iteratively under an agile process, with Android Studio driving the client, PHP and MySQL handling storage and business logic, and a Python/Flask service hosting the classifier. Unit, integration, and acceptance testing across these pieces confirmed that the combined shopping plus diagnosis workflow holds together end-to-end.

Published Paper   E-Certificate

"Plant Nursery Management and Disease Detection Using Artificial Intelligence", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.11, Issue 7, page no.a435-a437, July-2026, Available :https://ijsdr.org/papers/IJSDR2607046.pdf

Volume 11 Issue 7, July-2026

Pages : a435-a437

Paper Reg. ID: IJSDR_310865

Published Paper Id: IJSDR2607046

Downloads: 000116

Research Area: Science and Technology

Country: Kolhapur , maharashtra , India

Published Paper PDF: https://ijsdr.org/papers/IJSDR2607046

Published Paper URL: https://ijsdr.org/viewpaperforall?paper=IJSDR2607046

ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJSDR(IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition