ABSTRACT

Agriculture has a vital role in human life. Almost 60% of the population is involved in agriculture in some way, either directly or indirectly. Farmers are not interested in expanding their agricultural production day by day because there are no technologies in the old system to identify diseases in diverse crops in an agricultural setting. Crop diseases have an impact on their particular species' growth, hence early detection is essential. Many Machine Learning (ML) models have been used to detect and classify crop illnesses, but recent breakthroughs in a subset of ML known as Deep Learning (DL) look to hold a lot of promise in terms of enhanced accuracy. To effectively and precisely identify and characterize crop disease signs, the suggested method employs a convolutional neural network and a Deep Neural Network. These solutions are also evaluated using a variety of efficiency indicators. This article goes through the DL models that are used to depict crop diseases in detail. Furthermore, various research gaps have been found, allowing for increased transparency in detecting plant illnesses even before symptoms appear. The suggested methodology seeks to create a plant leaf disease detection strategy based on convolutional neural networks.

Keywords: OpenCV, Plant Disease Detection, Convolution Neural Network, Deep Learning