Image Based Plant Disease Detection Using Computer Vision

Despite fast population growth, agriculture supplies food for all people. Early detection of plant diseases is advocated as it is essential to making certain the entire population has an abundance of food. However, it is inconvenient to foresee diseases when crops are young due to a lack of necessary infrastructure. The purpose of the paper is to inform farmers about innovative technology that can help to prevent plant diseases. To detect plant conditions, an accurate algorithm for machine learning and imaging sensors is identified. Optical techniques, such as RGB imaging, multi- and hyperspectral sensors, thermography, and chlorophyll fluorescence, have proven effective in computerized, unbiased, repeatable detection systems for locating and measuring plant diseases during the initial phases of outbreaks. The extracts of diseased leaves are taken into account in this investigation. Farmers can quickly identify diseases based on early symptoms by using these disordered leaf samples. By applying machine learning techniques like Support Vector Machine (SVM), Convolutional Neural Network (CNN), and K-Nearest Neighbour (K-NN), the generated characteristics are finally classified. High-end and cutting-edge data processing techniques that produce fresh insights from sensor data for intricate plant-pathogen systems help with the accurate and reliable diagnosis of illnesses.