• Ninad Dhadphale
• Rohini Hanchate
• Shantanu Dhaybhar
• Vedant Pandhare

Detecting plant leaf diseases accurately and promptly is crucial for ensuring global food security and minimizing crop yield losses. In recent years, Convolutional Neural Networks (CNNs) have demonstrated exceptional performance in image classification tasks. This research proposes an innovative plant leaf disease detection system that utilizes CNNs to automate disease identification and enable early intervention. The system leverages a diverse dataset comprising images of healthy leaves as well as leaves affected by various diseases. Pre-processing techniques are applied to enhance image quality and reduce noise, while data augmentation is employed to expand the training dataset and enhance the model's ability to generalize. A custom-designed CNN architecture is trained on the augmented dataset to extract discriminative features for disease classification. The trained CNN model exhibits remarkable accuracy in distinguishing between healthy and diseased plant leaves. Its performance is evaluated using standard evaluation metrics including accuracy, precision, recall, and F1-score. Furthermore, the system's robustness is assessed by testing its performance on previously unseen test images, demonstrating its ability to generalize effectively. The proposed plant leaf disease detection system offers a rapid and automated approach to identify and diagnose plant diseases. Its integration with digital imaging technologies and mobile applications empowers farmers, agronomists, and researchers to detect diseases efficiently in the field. By providing reliable and accurate results, the system facilitates early disease detection and intervention, thus minimizing crop losses and promoting sustainable agricultural practices. Future research may involve expanding the dataset, exploring transfer learning techniques, and deploying the system on low-resource embedded devices for real-time disease detection in resource-constrained environments.

Plant Disease Detection, Deep learning, Computer Vision, CNN

"Diverse Plant Leaf Detection using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.h879-h886, May-2023, Available :http://www.jetir.org/papers/JETIR2305814.pdf

"Diverse Plant Leaf Detection using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. pph879-h886, May-2023, Available at : http://www.jetir.org/papers/JETIR2305814.pdf