Image Processing Technique on Identification of Leaf Types and Detection of Diseases Portion on Tomato Leaves

Abstract

This study presents novel techniques for leaf type identification, employing color histogram and edge histogram approaches. A color histogram serves as a model to represent color through intensity values, while each image is associated with a descriptive caption. Signatures, encompassing shape, color, and texture, provide a basis for comparing images. The edge histogram, delineating the distribution of five edge types in localized sub-images, further enhances the identification process. To address disease detection on tomato leaves, a color-based segmentation method utilizing the k-means clustering technique is proposed. This iterative approach partitions images into k clusters, facilitating the identification of diseases affecting tomato plants. Beyond environmental factors like rain and temperature, crop diseases emerge as primary influencers on production quality and crop yield. Early detection of diseases is crucial for effective control and mitigation. Leveraging technological advancements, the paper emphasizes the potential of using images of diseased leaves for accurate disease identification. This involves feature extraction from images, which can be subsequently employed in classification algorithms or content-based image retrieval systems.