GreenScan:IntelligentPaddyLeafDiseaseDetectionUsing Deep CNN Architectures

Thara K L; Zuber Khan; Faizan Ahmed Khan; Aafiya Arfain; Ayeena Marziya

doi:10.36948/ijfmr.2025.v07i06.64138

GreenScan:IntelligentPaddyLeafDiseaseDetectionUsing Deep CNN Architectures

Author(s)	Prof. Thara K L, Mr. Zuber Khan, Mr. Faizan Ahmed Khan, Ms. Aafiya Arfain, Ms. Ayeena Marziya
Country	India
Abstract	Paddy leaf diseases pose major challenges to world yield, food security, and economic stability in agricultural regions. Timely and correct identification of diseases is of utmost importance for farmers and policymakers in order to follow effective disease management strategies before the infection spreads across large cultivation areas. The traditional method of manual inspection is labor-intensive, subjective, and limited by expert availability. On the contrary, this research contributes to an automated and intelligent rice leaf disease recognition system based on Deep Convolutional Neural Networks (DCNNs) with inclusion of transfer learning. Domain-specific, custom-curated, and visually diverse rice leaf disease images were acquired for a dataset and subjected to robust preprocessing including resizing, normalizing, and removal of noise. Extensive data augmentation techniques, like rotation, flipping, shifting, and altering light intensity, were adopted to address class imbalance and improve model generalization. Advanced DCNN architectures, including InceptionV3, ResNet50, and VGG16, which were pre-trained on the large-scale ImageNet database, were fine-tuned on the augmented dataset. In that respect, deep feature extraction layers have been frozen to retain generic representation capabilities, and the final fully connected layers are replaced with domain-specific classifiers customized for four major Paddy diseases, namely, Blast, Brown Spot, Leaf Blight, and Tungro. Hence, systematic division of the dataset into training, validation, and testing subsets has been performed with multiple split ratios. Each model's effectiveness analysis has been done by calculating performance metrics: Accuracy, Precision, Recall, and F1-Score. Experimental results show that the proposed DCNN-based system offers superior detection performance and reliable classification accuracy compared to the previous machine learning-based approaches. Its high scalability and robustness provide a suitable real-time smart farming application toward sustainable agriculture,improving productivity, and early disease prevention.
Keywords	Rice Leaf Disease ,Deep Learning , Transfer Learning, DCNN, Smart Agriculture, Plant Disease Detection, Image Classification.
Field	Engineering
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-12-21
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.64138

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

GreenScan:IntelligentPaddyLeafDiseaseDetectionUsing Deep CNN Architectures

Share this