Thai Hom Mali rice grading using machine learning and deep learning approaches

Abstract

Thai Jasmine rice or Thai Hom Mali rice is a well-known rice type that originated in Thailand. Rice grain qualities are important in determining market pricing and are used in grading systems. The purpose of this research is to use machine learning and deep learning to improve the grading of Thai Hom Mali rice following standardized grading criteria. The appearance of grains and foreign items will determine the grade of rice. The experiment has two parts: grain categorization and rice grading. Multi-class support vector machine (SVM) and convolutional neural network (CNN) are proposed. There are 15 features used as input for multi-class SVM, including morphology and color features. With ImageNet pre-trained weights, CNN with DenseNet201 architecture is implemented. The experiment also tested into how CNN worked with both original and preprocessed images. The results are then compared to a neural network (NN) baseline approach. The CNN approach, which identified each rice variety using preprocessed images, archieved the greatest accuracy rate of 98.25%, with an average accuracy of 94.52% across six categories of rice grading.