Rice is one of the most widely cultivated crops globally and has been developed into numerous varieties. The quality of rice during cultivation is primarily determined by its cultivar and characteristics. Traditionally, rice classification and quality assessment rely on manual visual inspection, a process that is both time-consuming and prone to errors. However, with advancements in machine vision technology, automating rice classification and quality evaluation based on its cultivar and characteristics has become increasingly feasible, enhancing both accuracy and efficiency. This study proposes a real-time evaluation mechanism for comprehensive rice grain assessment, integrating a one-stage object detection approach, a deep convolutional neural network, and traditional machine learning techniques. The proposed framework enables rice variety identification, grain completeness grading, and grain chalkiness evaluation. The rice grain dataset used in this study comprises approximately 20,000 images from six widely cultivated rice varieties in China. Experimental results demonstrate that the proposed mechanism achieves a mean average precision (mAP) of 99.14% in the object detection task and an accuracy of 97.89% in the classification task. Furthermore, the framework attains an average accuracy of 97.56% in grain completeness grading within the same rice variety, contributing to an effective quality evaluation system.

Rice stands as a foundational agricultural product and staple food, instrumental in feeding more than half of the global population. It is a significant source of sustenance for approximately 3.5 billion individuals worldwide and represents a crucial element of food security, with an annual production surpassing 500 million tons. Beyond its role as a dietary staple, rice cultivation is a vital economic activity, offering substantial income for countless farmers across various regions. The emphasis on sophisticated and accurate methodologies for rice quality and classification has become increasingly prominent. This urgency is driven by the potential to enhance market acceptability, minimize rejection rates, and elevate the economic gains for producers through reliable quality assurance practices [1]. In the realm of agricultural quality assessment, traditional methods often depend on manual inspection based on visual appearance and smell, which, despite their widespread use, suffer from limitations in speed, accuracy, and reliability, particularly for those without extensive experience. Recent advancements in technology have paved the way for the application of data mining and machine learning techniques, marking a significant leap in enhancing the efficiency and precision of rice classification processes. These innovative approaches utilize detailed feature extraction from images, analyzing color, shape, and textural characteristics to differentiate rice varieties and ascertain their quality with unprecedented accuracy [2, 3, 4, 5, 6]. Sumaryanti et al. present a system designed for the identification of rice varieties using image processing techniques and a LVQ neural network algorithm.