Improved YoloV5 for the Authenticity Identification of Silver Coins in Modern China

• Published in: 2022 6th Asian Conference on Artificial Intelligence Technology (ACAIT) pp. 1 - 5
• Main Authors: Wang, Xin, Ren, Jiale, Shi, Wei, Wang, Tao, Guo, Xuhui, Han, Yiyuan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 09.12.2022
• Subjects: Attention Mechanism; Authenticity of Silver Coins; Correlation; Deep learning; Feature extraction; Image edge detection; Image Features; Neural networks; Object detection; Silver; YoloV5
• DOI: 10.1109/ACAIT56212.2022.10138006

Silver coin is an important circulating currency in modern China, and the edge teeth of silver coins are the key factor to identify its authenticity. However it is difficult for some hobbyists to distinguish the authenticity. So we propose an improved yoloV5 neural network algorithm, which can distinguish the authenticity of silver coin through its edge tooth images, and the value of mAP is more than 0.8. The algorithm in this paper adopts the Self-Attention mechanism, which can make full use of the correlation between image pixels and fully focus on the key details in the image, so that the network model can capture the global features of the image when learning a few parameters. Compared with yoloV5, the improved network model in this paper performs better on the public data set. No matter the value of mAP, FLOPs or average processing speed all have improved significantly. In addition, this paper also constructs a set of silver coin edge tooth images data set to facilitate relevant research in the future.