International Journal of Advances in Engineering & Scientific Research
Print ISSN : 2349 –4824
Online ISSN : 2349 –3607
Frequency : Continuous
Current Issue : Volume 12 , Issue 1
2025
Mrs.Y.Vahidhabanu, Harshumathi P, Mahalakshmi G, Srika S
Mrs.Y.Vahidhabanu, Harshumathi P, Mahalakshmi G, Srika S, Department of Computer Science and Engineering, Kongunadu College of Engineering and Technology, Tamilnadu, India
DOI : https://doi.org/ 10.5281/zenodo.14921991 Page No : 24-33
Published Online : 2025-02-25
Download Full Article : PDF Check for Updates
Automatic plant disease detection is a crucial research area aimed at addressing challenges in sustainable agriculture by minimizing pesticide usage, reducing costs, and enhancing crop quality. India, being a predominantly agricultural nation, faces significant economic impacts due to plant diseases caused by fungi, bacteria, and viruses. Climatic changes further exacerbate these challenges. This project leverages convolutional neural network (CNN) algorithms to classify multiple leaf diseases and recommend fertilizers based on disease severity. High-level properties such as color, shape, and texture features are extracted using image processing techniques. Pretrained models like VGG16 and X ception are utilized to construct an efficient model, ensuring high classification accuracy. Automated segmentation and feature extraction enable the identification of diverse leaf diseases with precision. The software infrastructure includes Python (server-side), Flask IDE, and MySQL for database management. The client-side interface is built using HTML, CSS, and Bootstrap. This system aims to analyze extensive agricultural crops, ensuring accurate disease detection and fertilizer recommendations, thus supporting sustainable agricultural practices and boosting productivity.
Keywords: CNN, Plant Disease Detection, Image Processing, Sustainable Agriculture, Fertilizer Recommendation and Deep Learning.
