Agriculture Leaf Disease Detection and Classification Using Deep Learning

Abstract

In this modern world, agriculture is the backbone of our economy. As we all know that the crop diseases lead to great loss of yield in the crops. Therefore, early and exact diagnosis of leaf diseases plays an important role in the management of diseases and for the sake of agriculture production. In this paper, an Agriculture Leaf Disease Scanner system is proposed. It utilizes the technique of deep learning with the help of Convolutional Neural Networks (CNN) to identify and classify the leaf diseases of plants by using the images of leaves. The proposed system has given an accuracy of 97.4% on Plant Village dataset that contains 38 different disease classes of 14 different crops. The proposed system includes Image preprocessing, feature extraction and a mobile application interface that provides real time detection of diseases using the smartphone cameras. The results of the proposed system are compared with other machine learning algorithms which shows that the proposed method gives better results and helps in taking the necessary actions in time for the sake of farmers.

Introduction

The text describes the Agriculture Leaf Disease Scanner, an AI-based web application designed to detect plant leaf diseases using deep learning.

The project aims to help farmers by replacing traditional manual disease identification with an automated system powered by a Convolutional Neural Network (CNN). Users upload leaf images through a web interface, which are processed by a Flask backend, preprocessed (resized and normalized), and then analyzed by the CNN model to predict the disease along with a confidence score. The system also provides disease details and treatment suggestions.

It includes features such as user authentication, scan history storage using SQLite, and an easy-to-use interface for farmers and agricultural workers. The literature review shows that CNN-based models achieve high accuracy but may struggle in real-world conditions, which this system addresses using preprocessing and improved training strategies.

Technically, the system uses Python, Flask, TensorFlow/Keras, NumPy, and Werkzeug to support image processing, model prediction, and secure web operations.

Conclusion

The Agriculture Leaf ailment Scanner mission successfully demonstrates using artificial Intelligence in agriculture for early ailment detection. The system uses a Convolutional Neural network (CNN) model to accurately become aware of plant leaf sicknesses from pics. through integrating a user-friendly internet interface with a Flask backend, the gadget permits users to effortlessly add leaf photographs and receive instantaneous predictions. The project also provides extra capabilities which includes sickness description, treatment guidelines, and scan records garage the use of an SQLite database. these functions assist users take well timed motion and song plant fitness over the years.

References

[1] S. P. Mohanty, D. P. Hughes, and M. Salathé, \"Using deep learning for image-based plant disease detection,\" Frontiers in Plant Science, vol. 7, p. 1419, 2016. [2] K. P. Ferentinos, \"Deep learning models for plant disease detection and diagnosis,\" Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018. [3] A. Ramcharan, K. Baranowski, P. McCloskey, B. Ahmed, J. Legg, and D. P. Hughes, \"Deep learning for image-based cassava disease detection,\" Frontiers in Plant Science, vol. 8, p. 1852, 2017. [4] P. Srivastava and R. Shukla, \"A survey of image processing techniques for plant leaf disease detection,\" International Journal of Computer Applications, vol. 139, no. 12, pp. 10–16, 2016. [5] D. P. Hughes and M. Salathé, \"An open access repository of images for training deep learning algorithms,\" arXiv preprint arXiv:1511.08060, 2015. [6] M. Islam, A. Dinh, K. Wahid, and P. Bhowmik, \"Detection of potato diseases using image segmentation and multiclass support vector machine,\" IEEE 30th Canadian Conference on Electrical and Computer Engineering, 2017, pp. 1–4. [7] F. Chollet, Deep Learning with Python. Manning Publications, 2018

Copyright

Copyright © 2026 Ms. Sharvari B. Kale, Ms. Pratima A. Kamble, Ms. Sakshi N. Satpute, Mrs. Nazmin N. Shaikh, Prof. Hiremath A. G.. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.