Abstract: Crop cultivation plays an essential role in the agricultural field. Presently, the loss of food is mainly due to infected crops, which reflexively reduces the production rate. In the field of agricultural information, the automatic identification and diagnosis of diseases in plants is highly desired. To identify the plant leaf diseases at an untimely phase is not yet explored. To improve the identification accuracy of detection Convolutional Neural Network is used. The main challenge is to reduce the usage of pesticides in the agricultural field and to increase the quality and quantity of the production rate. Our paper is used to explore leaf disease prediction at an untimely action. The main aim of this paper is to develop an appropriate and effective method for detection of the disease and its symptoms. A colour-based segmentation model is defined to segment the infected region and place it to its relevant classes. Experimental analyses were done on samples images in terms of time complexity and the area of the infected region. Plant diseases can be detected by image processing technique. Disease detection involves steps like image acquisition, image pre-processing, image segmentation, feature extraction and classification. Our project is used to detect the plant diseases. The detection is done without accessing the internet. It shows the accuracy of detection in percentage. This method will improve the accuracy of disease detection, and also effectively improve the model training and recognition efficiency.
Keywords: Leaf disease detection, Image processing, Image segmentation, machine learning, feature extraction.
|
DOI:
10.17148/IJARCCE.2021.10321
