A Systematic Literature Review on CNN-Based Deep Learning Models for Plant Disease Detection and Classification to Enhance Agricultural Productivity

DOI

10.2991/978-94-6463-718-2_100How to use a DOI?

Keywords

Artificial Intelligence; Computer Vision; Convolutional Neural Networks; Deep Learning; Image Recognition; Image Segmentation; Image Classification

Abstract

Deep Learning is a specialized subset of computer vision and artificial intelligence and is applicable to the domain of automatic learning process. Deep learning deals with the high-dimensional data processing like text, image, and video. More Over CNN or Convolutional neural networks, one of the deep learning techniques become a mainstream in Agriculture domain while identifying the plant diseases and also segmenting the disease spots. This will help to maximize the production and minimize the yield loss because the diseases can be identified early on the plant images. By using CNN, identification, segmentation and classification of different disease classes was performed more efficiently. In this study, we have suggested a novel nn architecture that we used to accomplish the classification problem. The proposed approach is constructed from scratch and enhanced the learning procedure to create more precise classification applications. The new model recognizes and classifies several diseases in 10 diverse plants, including potato, soybean, tomato, peach, corn, grape, orange, pawpaw, custard apple, and banana, and it is trained and tested from the scratch. The initial step is the feed-forwarding learning process of the model using the datasets extracted through such online repositories as Plant Village. Secondly, the performance of the proposed model is verified over the plant images captured in the agriculture fields. These classification accuracies are then improved by a fine-tuning process such as back propagation. Then the performance of the suggested model is compared by according to validation and verification with the current and pre-trained models. The Results of the research where by using this work, we can eliminate the manual way of identifying the disease and traditional way of selecting the disease spots.

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)

TY  - CONF
AU  - G. Prathibha Priyadarshini
AU  - S. Zahoor-Ul-Huq
PY  - 2025
DA  - 2025/05/23
TI  - A Systematic Literature Review on CNN-Based Deep Learning Models for Plant Disease Detection and Classification to Enhance Agricultural Productivity
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 1207
EP  - 1218
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_100
DO  - 10.2991/978-94-6463-718-2_100
ID  - Priyadarshini2025
ER  -