Grading of Cashew Nuts on the Bases of Texture, Color and Size

Abstract

This paper presents a novel defect of cashew nuts based on color and texture features with K-Nearest Neighbor algorithm. The Support Vector Machine (SVM) is used for background removal and color classification. Physical recognition of defected cashew nuts is very time overwhelming. These days, most existing cashew nuts superiority detecting and grading system have the drawback of low efficiency, high cost, complex and low speed of grading. Although color is not commonly used for defect segmentation, it produces a high discriminative power for different regions of image. This approach thus provides a feasible robust solution for defect segmentation of cashew nuts. Image processing gives solution for the automated cashew nuts size grading to give precise, dependable, unfailing and relative information apart from handling large volumes, which may not be achieved by employing the human graders. This will have a good aspect of application in fruit quality detecting industries.