Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)

<Previous Article In Volume
Next Article In Volume>

Apple Leaf Disease Classification Using SMOTE and Detection Using Convolutional Neural Network Models

Authors
A. Ashwitha1, *, P. Anitha2, Shaleen Bhatnagar3, N. Pavithra4, R. Sapna5
1School of Computer Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India
2School of Computer Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India
3School of Computer Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India
4School of Computer Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India
5School of Computer Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India
*Corresponding author. Email: ashwitha.a@manipal.edu
Corresponding Author
A. Ashwitha
Available Online 31 December 2025.
DOI
10.2991/978-94-6463-978-0_12How to use a DOI?
Keywords
CNN; DenseNet121; InceptionV3; ResNet50; SMOTE; Apple Leaf Disease; Deep Learning
Abstract

Agriculture sustains a large portion of India’s rural economy, where protecting crop health is essential for stable productivity. This study introduces a deep learning framework based on Convolutional Neural Networks (CNNs) for the automatic recognition of apple leaf diseases across four categories: healthy, rust, scab, and multi-diseased. A dataset containing 1821 apple leaf pictures was handled using the Synthetic Minority Oversampling Technique (SMOTE) to improve class imbalance and Singular Value Decomposition (SVD) to reduce high-dimensional feature spaces without losing the data. ResNet50, Inception V3, and DenseNet121 are the three coevolutionary neural network (CNN) architectures were developed and evaluated comparatively. Among them, DenseNet121 gave the finest performance with an accuracy of 99.65%, surpassing Inception V3(96.91%) and ResNet50 (94.00%). The suggested method parades outstanding generalization ability and computational effectiveness, catering a consistent, accessible, and programmed solution for experimental identification of apple leaf diseases. By facilitating sensible crop health estimation this framework influences to data-motivated decision-making and progressed agricultural yield forecast.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
Series
Advances in Engineering Research
Publication Date
31 December 2025
ISBN
978-94-6463-978-0
ISSN
2352-5401
DOI
10.2991/978-94-6463-978-0_12How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - A. Ashwitha
AU  - P. Anitha
AU  - Shaleen Bhatnagar
AU  - N. Pavithra
AU  - R. Sapna
PY  - 2025
DA  - 2025/12/31
TI  - Apple Leaf Disease Classification Using SMOTE and Detection Using Convolutional Neural Network Models
BT  - Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
PB  - Atlantis Press
SP  - 120
EP  - 128
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-978-0_12
DO  - 10.2991/978-94-6463-978-0_12
ID  - Ashwitha2025
ER  -