Multispectral Imaging and CNN Architectures for Cotton Leaf Disease Classification: A Comprehensive Review

Gajanan Ankatwar; Chitra Dhawale

doi:10.36948/ijfmr.2025.v07i03.47769

Multispectral Imaging and CNN Architectures for Cotton Leaf Disease Classification: A Comprehensive Review

Author(s)	Mr. Gajanan Ankatwar, Dr. Chitra Dhawale
Country	India
Abstract	This review paper presents a comprehensive cotton leaf disease dataset designed to enhance detection and classification models using deep learning. The dataset comprises over 50,000 high-resolution images across seven classes: Bacterial Blight, Curl Virus, Herbicide Growth Damage, Leaf Hopper Jassids, Leaf Reddening, Leaf Variegation, and Healthy Leaves. Images were captured in diverse environments and growth stages to facilitate the development of robust, scalable convolutional neural network (CNN) models. We review prior datasets, highlighting limitations in class diversity, environmental inconsistency, and image quality, and demonstrate how our dataset addresses these challenges. The dataset construction methodology is detailed, from multi-modal data acquisition and expert labeling to augmentation and preprocessing techniques. We explore the biological basis and visual patterns of each disease class, enabling both human and algorithmic recognition. State-of-the-art CNN architectures like ResNet, DenseNet, and MobileNet are benchmarked, with a focus on explainable AI techniques like Grad-CAM for decision transparency. The integration of multispectral and hyperspectral imaging is shown to enhance classification performance. Deployment strategies for mobile and edge AI systems are discussed, along with challenges in rural connectivity and user adoption. Future research directions include addressing dataset biases, cross-regional validation, and extending to pest and weed detection. This work establishes a new standard for data-driven plant pathology, empowering farmers with timely, accurate, and scalable disease diagnostics.
Keywords	Cotton leaf disease, Dataset, Deep learning, Classification, Convolutional neural network (CNN), Bacterial Blight, Leaf Curl Virus, hyperspectral imaging.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 7, Issue 3, May-June 2025
Published On	2025-06-11
DOI	https://doi.org/10.36948/ijfmr.2025.v07i03.47769
Short DOI	https://doi.org/g9pz4k

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 7 Isu 3 Cover Page Vol 7 Isu 2 Cover Page Vol 7 Isu 1

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

Multispectral Imaging and CNN Architectures for Cotton Leaf Disease Classification: A Comprehensive Review

Share this