A Hybrid Framework Combining CNN, LSTM, and BiLSTM for Early and Reliable Detection of Tomato Leaf Diseases in Real-World Environments

Manasvi Nanjurao Shinde; Payal Dadabhau Patil; Krushna Dilip Pathak; Hemant Pramod Mande

doi:10.36948/ijfmr.2026.v08i03.77756

A Hybrid Framework Combining CNN, LSTM, and BiLSTM for Early and Reliable Detection of Tomato Leaf Diseases in Real-World Environments

Author(s)	Ms. Manasvi Nanjurao Shinde, Ms. Payal Dadabhau Patil, Ms. Krushna Dilip Pathak, Prof. Hemant Pramod Mande
Country	India
Abstract	Tomato crop yields are greatly impacted by leaf diseases, which pose a serious threat to agricultural productivity. Traditional methods for identifying these diseases rely heavily on manual inspection, a process that is often slow, subjective, and not easily accessible to many farmers. While deep learning techniques have shown promise with high accuracy, their success is generally limited to controlled settings and struggles to handle real-world challenges such as changing lighting, complex backgrounds, and leaf occlusions. To address these issues, this study introduces a hybrid deep learning approach that combines Convolutional Neural Networks (CNN) for extracting detailed spatial features from leaf images with Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) networks to capture important contextual information, thereby enhancing classification accuracy. The model is trained and tested on a publicly available tomato leaf dataset, utilizing preprocessing and data augmentation to boost performance. Results from the experiments reveal that this integrated framework not only achieves higher accuracy but also generalizes better than traditional methods. Moreover, it is computationally efficient and designed for real-time use, offering a practical solution for precision agriculture and early detection of tomato leaf diseases to help farmers manage crop health more effectively.
Keywords	Tomato Leaf Disease, CNN, LSTM, BiLSTM, Deep learning, Image Classification, Precision Agriculture
Field	Computer Applications
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-11
DOI	https://doi.org/10.36948/ijfmr.2026.v08i03.77756

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

A Hybrid Framework Combining CNN, LSTM, and BiLSTM for Early and Reliable Detection of Tomato Leaf Diseases in Real-World Environments

Share this