Grape Leaf Disease Detection Using CNN
Keywords:
CNN, Grape leaf disease, Image processing, Pesticides, Pre-processingAbstract
Diseases found in agricultural crops are a major threat that causes production and economic losses as well as reduction in both the quality and quantity of agricultural products. In India, 70% of the population depends on agriculture and contributes 17% towards the GDP of the country. Farmers experience great difficulties in switching from one disease control policy to another. The naked eye observation of experts is the traditional approach; this method can be time-consuming, expensive and inaccurate. The crop losses can be minimized by applying pesticides or their equivalent to combat the effect of specific pathogens if diseases are correctly diagnosed and identified early. Grape yield can be decreased by the presence of leaf diseases, costing growers money. Bacteria, fungi, viruses, etc. are the principal culprits behind leaf diseases. To properly implement control measures, a plant disease diagnosis must be made. The purpose of this publication is to aid in the diagnosis and categorization of grape leaf diseases. In essence, CNN is an artificial neural network design that needs to be repeatedly trained to achieve high accuracy. Three phases make up CNN: classification, feature learning, and data input. Python programming is used in this study's CNN implementation, which makes use of the Keras packages. The Keras framework was developed to aid with computer learning.