Potato Disease Detection by using Deep Learning
Divyanshi Parashar, Anshika Agarwal, Akshat Agarwal, Rahul Singh
Abstract
One crop that is commonly grown is the potato. In order to create a robust food security system that would facilitate efficient potato growing, potatoes - a staple item that is high in carbohydrates are given top priority. However, a number of diseases that affect potatoes hinder their development and cause problems for our entire agricultural supply chain. Therefore, a more efficient method of ensuring crop cultivation performance may be early disease identification. Our primary goal is to create a deep learning system that uses K-means clustering segmentation to identify and categorize potato leaf diseases. The VGG16, 2-D CNN, and ResNet50 network models are the ones we have chosen. Of these chosen models, we were able to obtain exceptional accuracy using VGG16, yielding the best result out of three networks. For improved accuracy when working on a huge dataset created from multiple sources, the model's performance is contrasted with the state-of-the-art techniques currently in use.