An Efficient CNN Architecture for Automated Plant Disease Classification using Plant Village Benchmark

Author(s)	Ms. Zoha Ali, Mr. Mohd Raiyyan Ali, Mr. Imran Raza Khan
Country	India
Abstract	Crop cultivation is a global lifeline, covering roughly 4.8 billion hectares, but it faces a constant threat from diseases that destroy yields and can even impact human health. To tackle this, we developed a specialized AI model designed to "see" and diagnose plant diseases as accurately as a trained expert. Using the PlantVillage dataset—which covers 38 different plant conditions—we built a Convolutional Neural Network (CNN) that processes images of leaves to identify specific infections. By resizing images to 128x128 pixels and training the model with the Adam optimizer, we achieved a strong 92.3% validation accuracy in just 10 epochs. The results show a steady improvement in accuracy without signs of overfitting, proving that even a straightforward CNN can be a powerful tool for farmers. This research serves as a foundation for future smart-farming tech, helping harvesters catch and treat diseases before they have a chance to spread.
Keywords	plant disease, CNN, TensorFlow, Keras, PlantVillage, image classification, deep learning, leaf photo.
Field	Engineering
Published In	Volume 7, Issue 2, March-April 2026
Published On	2026-04-21
DOI	https://doi.org/10.63363/aijfr.2026.v07i02.4996

About AIJFR 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		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research