Development Of Tensorflow Based Mobile Application and Support Vector Machine Based System for Detecting Hevea Brasiliensis Leaf Disease

Plant diseases are a major source of tragedy in today's horticulture industry. Plant illness severity is a significant threshold to assess infection level and may therefore be used to predict yield and recommend therapy. Quick, precise analysis of sickness severity can help reduce yield losses. Plant disease severity is often determined by a visual examination of plant tissue by trained professionals. The high cost and low productivity of human sickness evaluation impede the rapid development of contemporary farming. With the number of inhabitants in cutting-edge cameras and the advancements in PC vision, the robotized disease detection models are considerably discussed by exactness agriculture, high-throughput plant total, sagacious greenhouse, and so on. Inspired by the major learning advancement in imagebased plant disease confirmation, this study suggests significant learning models for imagebased customized assurance of plant disease seriousness. The agricultural industry was founded on Hevea brasiliensis (rubber), which is now an important source of both financial gain and energy. Many-level plantations are also employed to solve the problem of global warming. Nowadays, agriculture employs a major section of the population. There is an abundance of plants, but due to environmental factors and climate change, various non-native diseases plague them, bringing harm to the economy, society, and ecology. Many farmers are unable to identify this new disease. This may not always be visible to the naked eye, which might reduce the amount and quality of plants. As a result, a farmer will want an expert who can identify the illness and its signs on plant leaves.