Performance Enhancement in Agriculture Sector Based on Image Processing

Abstract

In the realm of agriculture and horticulture, machine vision and soft computing approaches have shown promise in overcoming the limitations of traditional methods for identifying plant illnesses utilizing various plant components. In all relevant studies such as fruit grading, leaf lesion area identification, and so on, image segmentation is the first and most important step. In order to diagnose the illness more effectively, a robust approach for numerous crops employing diverse plant components such as Fruit, Flower, and Leaf has been suggested in this study. Before segmentation, the acquired real-time pictures are pre-processed for illumination normalization and color space conversion. To enhance the segmentation outcomes, the conventional ML, image processing and deep learning approaches scheme has been made adaptable, and edge detection transformations have been implemented. To separate the sick regions from photos, the aim function of the Machine Learning approach has been adjusted, and cluster centers have also been upgraded. The many classes of plant illnesses noticed by shooting various types of images of diseases in plants, including many popular plants such as grapes, apple, and tomato. In terms of both broad human observation and computing time, the results achieved are superior.