Comparative Analysis of Machine Learning Models for Potato Leaf Disease Detection
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This research analyses the performance of three algorithms: SVM, K-means Clustering, and CNN to diagnose diseases on potato leaves from images. The research implemented the dataset of Plant Village which contained images for potato leaves both as healthy and diseased. Accuracy, precision, recall, and F1 score were the parameters that were selected to be measured for the algorithms considered. The results indicate that CNN is the best fit for this problem as it performs better than SVM and K-means, achieving an accuracy of 97%, significantly higher than SVM (93%) and K-means (43%). The proposed approach may well end up as a reliable and efficient way to identify potato plant diseases and enable farmers to decide and act fast about infection once an outbreak occurs, thereby enabling the improvement of food security and the general sustainability of the agriculture industry.
Fields of Study & Subjects
Smart Agriculture and AI
Advanced Neural Network Applications
Industrial Vision Systems and Defect Detection
Publication details
- Journal / source
- International Conference on Emerging Trends and Innovations in ICT (ICEI)
- Pages
- 1–6
- Publication date
- 9 January 2026
- Language
- EN