Automatic Methods for Classification of Plant Diseases Using Convolution Neural Network

ABSTRACT

Agriculture is the primary source of economic development in India. The fertility of the soil, climatic conditions, and crop economic values make farmers select appropriate crops for each season. to fulfil the increasing population requirements, agricultural industries hunt for improved means of food production. Researchers are in search of stories that may reduce investment and significantly improve the yields. The proposed decision-making system utilizes image content characterization and a supervised classifier variety of neural networks. Image processing techniques for this sort of decision analysis involve preprocessing the feature extraction and classification stage. At Processing, an input image is going to be resized and region of interest selection performed if needed. Here, color and texture features are extracted from network training and classification. The system is accustomed to classify the test images automatically to determine leaf characteristics. Precision may be a new technology that helps in improving farming techniques. Thus, this can be one in every of the important and main reasons to be considered for the detection of plant diseases. Plant plant disease detection may be a noteworthy application of precision agriculture. The main aim of this project is to spot the diseased and healthy leaves of distinct plants by extracting features from input images using the CNN algorithm. These features extracted help in identifying the foremost relevant class for images from the datasets. By using the CNN algorithm during this proposed system we will achieve 95% of accuracy.