Pest Identification and Control in Paddy Plants using Ml with an Optimised Activation Function

The rice plant, one of the most extensively cultivated crops in India, suffers from a number of diseases at various stages of its growth. Farmers find it incredibly difficult to manually diagnose these diseases properly because of their lack awareness. Caused by many types, Such as; Fungi, Bacteria and Viruses and Pest. In Image processing technology many algorithms are used to classify rice leaf diseases. In the southern regions of India, paddy is the primary source of food. It has an impact on the nation's infrastructure. Its main illnesses were found in paddy field crops, which also significantly impair its profitability. In this research study, the automatic diagnosis and classification of different paddy leaf diseases using an image processing system was demonstrated. Deep Learning can be used for pest identification in paddy plants. Using a collection of pictures of paddy plants with and without pests, a Convolutional Neural Network (CNN) can be trained in this application. The network can learn to identify the characteristic features of pests in the images, such as shape, color, size, and texture. Once the network is trained, it can be used to classify new images of paddy plants as containing pests or not. By using deep learning, it is possible to automate the process of pest identification in paddy plants, reducing the time and effort required for manual inspection and increasing the accuracy of the results. So this paper, Classify the normal leaf and disease affected leaf using CNN algorithm. Software has been developed as part of the proposed system to automatically reduce the paddy leaf disease. The proposed system is based on the Deep Learning method. All the process is done by using python Programming language. In the proposed system tkinter is the front end and Python is back end.

I. Introduction

The diagnosis of paddy diseases is a major problem for the agricultural industry. On some Rice leaves, there are apparent signs. Different diseases can be recognized using these leaf patterns, and quick action can be taken to stop the spread of those diseases. The majority of these plant diseases are challenging to identify with the naked eye, and even knowledgeable people frequently make mistakes. Using deep learning and machine learning models, disease classification is done. This study suggests using deep learning to classify plant diseases. Deep learning models have the advantage of being able to swiftly and accurately analyse vast volumes of data, which makes them perfect for application in large-scale agricultural situations. Using an image, the object is identified. The elimination of image noise would likely be the initial stage in this process, followed by (low-level) feature extraction to identify the lines, regions, and possibly the areas with the particular textures. This application uses a collection of photos of paddy plants with and without pests to train a convolutional neural network. The network can learn to recognise the distinctive shapes, colours, sizes, and textures of pests in the photos. Once trained, the network may be used to identify whether or not new photos of paddy plants contain pests.