Abstract: The identification of plant diseases is a quite difficult process in the field of agriculture. If the identification process is incorrect, then there will be a huge loss. The identification of Leaf diseases requires knowledge about plant diseases, a big amount of research study, research work, and more processing time. Vegetable and fruit plant supports the lives of approximately 7.5 billion people worldwide and plays a crucial role in the survival of the planet. The economic development of any nation depends on agricultural productivity. The livelihood of around 58 percent of India's population depends on agriculture which is the primary income source. A plant disease is an abnormal condition that alters the appearance and performance of the plant. It is a physiological process that affects some or all plant functions.
In this paper, a convolutional neural network (CNN) model is used to distinguish between healthy and diseased Citrus fruits and leaves. If the image is diseased then the proposed CNN-based model can identify the type of leaf or fruit disease. In the proposed method, we have tried to classify diseases from images of citrus fruit and leaves using the CNN model. Common citrus fruit and leaf diseases are black spot, canker, scab, greening, and melanose. The CNN Model performs better than the several traditional methods used for identifying citrus fruit and plant disease. This method is accurate and gives the results quickly. For farmers wishing to categorize citrus plant leaf or fruit diseases, the CNN Model is a helpful tool for decision-making with a test accuracy of 98.61 percent. This CNN model was checked on the Citrus dataset.
Keywords: deep learning, plant disease recognition, CNN, computer vision.
|
DOI:
10.17148/IJARCCE.2022.11808
