A CNN Based Approach For Detection Of Grape Leaf Diseases

DOI

10.2991/978-94-6463-471-6_8How to use a DOI?

Keywords

Agriculture; Grape; Diseased plant; Convolutional Neural Network; Deep Learning; Image Classification; Nadam optimizer

Abstract

Plant leaf disease detection has become increasingly important in ensuring sustainable agriculture and maintaining crop health. Since plant illnesses are quite widespread, finding infections in plants is an important job in the agricultural industry. Manual inspection, which is labour-intensive and subjective, is the basis for traditional plant disease detection. It can be inaccurate and has a limited scope. Faster and more accurate detection is provided by more recent techniques like deep learning and machine learning. They can handle a broader range of diseases, making them an appealing option for large-scale, efficient plant disease management. Every nation must automate its agricultural sector. Plant diseases are typically characterised by visual symptoms, and in recent years, a number of deep learning models have produced exceptional results in the classification of plant diseases. Diseases that affect grape plants, such as leaf blight, black measles, and black rot, lower crop yields Early intervention is essential to address this crop disease. A proper diagnosis is required. This paper uses the Grape Leaf image dataset, which comprises 8845 images with four different classes, and applies a deep learning-based convolutional neural network to perform disease prediction. Additionally, various optimisation strategies and activation functions were employed to bring out the differences in convolutional neural network (CNN) model performance. CNN-Nadam with a sigmoid activation function outperforms other CNN optimizers with 99.45% accuracy, according to an analysis of the experiment results. Therefore, quick action would help minimise losses in plant productivity. Revenue, economic expansion, and agricultural productivity will all increase as a result.

Copyright

© 2024 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  - Smita Rani Sahu
AU  - Bhogi Saikrishna
AU  - Kothakota Priyanka
AU  - Koppala Pavan Sai
AU  - Gujjuru Rohith
PY  - 2024
DA  - 2024/07/30
TI  - A CNN Based Approach For Detection Of Grape Leaf Diseases
BT  - Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
PB  - Atlantis Press
SP  - 76
EP  - 86
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-471-6_8
DO  - 10.2991/978-94-6463-471-6_8
ID  - Sahu2024
ER  -