A rapid identification technique for rice adulteration based on improved YOLOV8 model

Abstract Rice classification and quality testing are essential to ensure its safety and quality, and can effectively reduce food economic losses associated with rice, which is currently the subject of repeated reports of rice adulteration. For this reason, according to the experimental requirements, we selected the smallest and lightest version of YOLOv8n in the YOLOv8 series, and optimised and proposed the lightweight and efficient Faster-YOLO algorithm, which is more suitable for rice adulteration classification and recognition tasks, on the basis of the YOLOv8n algorithm. Firstly, this paper introduces the Group Convolutional Hybrid Attention Mechanism, which combines channel information and spatial information, and embeds it in the last layer of the Backbone network, which enhances the feature representation capability of the model by focusing on the key information to suppress the noise. Secondly, the C2F module in the Backbone part adopts the design of combining Faster and C2F to enhance the feature fusion capability and reduce the number of parameters and computational complexity of the model. Finally, the collected data are augmented with multiple aspects to simulate different environments and compared with multiple attention mechanisms and deep learning models. The experimental results show that the method proposed in this paper is superior in classification and recognition performance, with recognition accuracy of 93.4%, precision of 96.5%, recall of 96%, and F1 score of 96.2%. In this paper, the accuracy is improved by 1.1%, 2.4%, 6.9%, 7.5%, 13.1%, 7.9%, 7.1%, and 7.1% compared to yolov8n, yolo11, yolov5, EfficientNetV2, MobileNetV3, Restnet18, and VGG19 image classification methods, respectively. It is demonstrated that Faster-YOLO provides a strong basis for the rapid identification of rice adulteration by reducing the weight of the model while improving the detection and identification capabilities.