Potato Leaf Disease Detection Using Convolutional Neural Network

Potato cultivation in India has faced challenges in recent years due to diseases such as early blight and late blight. These diseases have increased production costs and negatively affected potato yields. To address this issue and enhance potato production, a research paper proposes an automated and rapid disease detection system using image processing and machine learning techniques, specifically a CNN algorithm. The paper suggests that image processing is an effective approach for detecting and analyzing potato leaf diseases. The study utilizes a dataset of over 2000 images of healthy and unhealthy potato leaves, sourced from platforms like Kaggle. To detect and classify the health status of leaves, pre-trained CNN models are employed. The results indicate that the proposed system achieves an impressive accuracy of 99.01% during testing, employing a training-to-testing data split of 80% and 20% respectively. These outcomes demonstrate that the CNN algorithm outperforms existing methods in potato disease detection. The development of an automated and accurate disease detection process for potato cultivation holds great promise. By enabling early detection and intervention, farmers can take prompt measures to mitigate the impact of diseases, leading to improved crop yields and reduced production costs. Furthermore, the digitization of this system facilitates efficient monitoring and management of potato crops, enhancing overall agricultural practices.