Abstract: In agriculture, detecting plant diseases is a difficult task. It is time consuming and require highly knowledgeable individuals to identify diseases. Plants are often at risk of disease that will result in social and economic losses. Many diseases are starting to emerge on plant leaves. If the disease is not recognised in early stage, it might result in serious damages to the plant. The current way of identifying plant disease is an inspection performed by a specialist who must monitor the plants on a constant basis. But costs increase with the size of the farm. In the existing system, Support vector machine algorithm technique is used to predict an infected plant disease with 80 percent of accuracy. In such types of conditions, to achieve a high degree of accuracy and to reduce the difficulty of time, the proposed system contains a comparative study on different machine learning algorithms to predict the disease and build a system that will easy to use by anyone. This system uses computer vision and deep learning strategies. Using the Image Processing technique system will get a picture of the leaf of an infected plant and turn it into a grey scale image. The system will give suggestions on the features and characteristics of various types soils for plant growth without any infection using deep learning techniques. The system uses a different deep learning algorithm to improve its accuracy in diagnosis of plant diseases and offer a suggestion.

Keywords: Computer vision, Gray scale image, Image Processing, Deep learning, Neural networks, Support Vector Machine.

PDF | DOI: 10.17148/IJARCCE.2022.11584

Open chat
Chat with IJARCCE