Classification of Cashew kernels into Wholes and Splits using Machine Vision Approach

Abstract

Cashew kernels play a vital role in the food industry, where accurate classification into wholes and splits is essential for quality control and pricing. This paper presents a machine learning-based approach for automating the classification process. A dataset of cashew kernel images is collected and preprocessed, followed by feature extraction to capture discriminative characteristics. Support Vector Machines (SVM) is employed as the classification algorithm due to its ability to handle high- dimensional data and binary classification tasks. Out of several features derived from grayscale-intensity-profile values, the “length of curve” best classified the split-up cashews from others. Experimental results demonstrate the effectiveness of the proposed method, achieving an accuracy of 93% on the test set. The developed model offers a reliable and efficient solution for cashew kernel classification, enabling improved efficiency and accuracy in the food industry. Further research could explore the extension of the classification to include additional categories or investigate the integration of deep learning techniques for enhanced performance.