Research Article
Plant Disease Detection Using CNN
@INPROCEEDINGS{10.4108/eai.28-4-2025.2357865, author={Manisha More and Sharvari Awadhane and Avni Ingalgi and Krushna Aware and Ayush Kirange and Ayan Jaiswal}, title={Plant Disease Detection Using CNN}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part I}, publisher={EAI}, proceedings_a={ICITSM PART I}, year={2025}, month={10}, keywords={convolutional neural network data augmentation disease detection deep learning feature extraction}, doi={10.4108/eai.28-4-2025.2357865} }- Manisha More
Sharvari Awadhane
Avni Ingalgi
Krushna Aware
Ayush Kirange
Ayan Jaiswal
Year: 2025
Plant Disease Detection Using CNN
ICITSM PART I
EAI
DOI: 10.4108/eai.28-4-2025.2357865
Abstract
Plants constitute one of the major sources of human foodstuffs. Farmers in countries across the globe are struggling to repel an array of destructive organisms. In this work, we propose a Convolutional Neural Network (CNN) architecture for image-based plant leaf disease detection based on deep learning with a total of 20 layers including convolutional layers, max pooling layers, dropout layers, flatten layer, and dense layers. The CNN classifier model was trained with a dataset of nearly 87,000 images of different healthy and disease crop leaves and background images. The spatial patterns were discovered by feature extraction mechanisms. The model displayed 95-98% accuracy on the test set and proved to be a promising tool in plant disease detection.
