Product brand recognition using YOLOv8 achieves 99.86% precision in GroZi datasets, suggesting improved payment accuracy.
This paper presents a product brand recognition method based on the YOLOv8 algorithm. The performance evaluation of the proposed method is conducted on two datasets consisting of GroZi-120 and GroZi-3.2K. The results show that the proposed method can achieve high accuracy. The precision and F1-score on the GroZi-120 and GroZi-3.2K datasets reach of {74.77%, 80%} and {99.86%, 100%}, respectively. The comparison with previous studies shows that the precision and F1-score obtained by the YOLOv8 method outperform some previous studies. Additionally, the effectiveness of the proposed method is also evaluated on a dataset of 6,170 images for twelve real products collected from supermarkets for use in order payment. The results show that the proposed method can be applied in single-order payment as well as multiple simultaneous orders with high accuracy in product recognition ranging from 94% to 98%. Therefore, the proposed method can be applied in order quick payment at supermarkets.
No takes yet. Share an insight, caveat, or question.
Huynh et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: