AN EFFICIENT ADVANCE ARCHITECTURE ANALYSIS IN DETECT DISEASE OF RICE LEAVES BY DNN
India is an agricultural nation where farming is the principal source of income for the majority of its people, and rice is one of the crops that is grown and used as a staple diet by the majority of its people. As a result, both rice quality and availability must be taken into account, whether the rice is intended for domestic consumption or export. Especially in the field of tasks such as image classification, segmentation, object detection, video processing, analyzing documents, recommender systems, natural language processing, and speech recognition, are just a few of the exciting applications of DCNN. The availability of a significant amount of data, combined with advances made in hardware technology, has accelerated research in CNNs, of recently reported attractive DCNN architectures. Also helpful in optimizing the architectural design are the hyper-parameters Kernel/Filter Size, Padding, Stride, Number of Channels, and Pooling layer Parameters. This research study aims to provide an analysis of diseases in rice plant leaves that may cause a decrease in rice production.
Agriculture, DNN, Deep Learning, Hyper-parameters, Neural Networks, Rice Leaf Diesease Detection