Crop Disease Detection Using Deep Learning and Transfer Learning Techniques

Amrut Shailesh Nikam

doi:10.36948/ijfmr.2025.v07i06.63503

Crop Disease Detection Using Deep Learning and Transfer Learning Techniques

Author(s)	Mr. Amrut Shailesh Nikam
Country	India
Abstract	It's hard for farmers to identify whether a crop is healthy or diseased at an early stage, as symptoms often appear subtle or look similar to nutritional deficiencies. The aim of the present research is to construct a computer-based system that will observe leaf images and classify disease types with high reliability. In this paper, authors employ the PlantVillage dataset and five deep learning architectures: CNN, ResNet50, VGG16, EfficientNet, and Vision Transformer (ViT). All these models have undergone identical trainings so that their strengths and weaknesses can be compared effectively. Images were first enhanced through the augmentation method to simulate varied lighting and background situations during the experiment. Later, each model was evaluated through accuracy, precision, recall, and F1 score. According to the results, ViT produced the strongest performance, followed closely by EfficientNet and ResNet50. CNN and VGG16 also provided meaningful outcomes but seemed to be affected more by the similarity among the disease classes. These observations indicate that transformer-based models handle fine-grained texture differences better than conventional CNN approaches. Overall, this study shows that deep learning tools can support agricultural monitoring systems and reduce dependence on expert field inspection. With minor enhancements and real-time integration, the proposed approach may support farmers in preventing large-scale losses and preserving crop quality.
Keywords	Crop Disease Detection , PlantVillage Dataset , Deep Learning in Agriculture ,Vision Transformer (ViT) , Convolutional Neural Network (CNN) , ResNet50 , VGG16 , EfficientNet
Field	Biology > Agriculture / Botany
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-12-17
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.63503

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

Crop Disease Detection Using Deep Learning and Transfer Learning Techniques

Share this