摘要
针对数字化档案处理过程中,印章多、印痕浅、印章识别准确度较低的问题,提出了一种改进的YOLOv5印章识别算法。算法改进分为两个方面,首先引入CBAM注意力模块,以提高模型的特征提取能力,其次引入EIoU Loss,以替换算法中的CIOU Loss边界框回归损失函数,有效解决了纵横比描述为相对值,存在一定模糊的问题。实验表明,改进算法的印章识别F1分数达到了0.95,相较于原算法提高了2%。最后为验证模型的有效性,在数字化档案处理系统中调用改进后的YOLOv5模型对印章进行处理,结果表明本文改进算法能在系统中稳定运行。
Aiming at the problems of many seals,shallow impressions and low accuracy of seal identification,a modified YOLOv5 seal identification algorithm is proposed.The algorithm improvement is divided into two aspects.First,CBAM attention module is introduced to improve the feature extraction ability of the model.Secondly,and EIoU Loss is introduced to replace the CIOU Loss boundary box regression loss function in the algorithm,which effectively solves the aspect ratio described as the relative value,which is a certain fuzzy problem.Experiments show that the improved algorithm′s seal recognition F1score has reached 0.95,which is a 2%improvement compared to the original algorithm.Finally,to use the seal to verify the effectiveness of the model,the improved YOLOv5 model is called in the digital archive processing system,and the results show that the improved algorithm can run stably in the system.
作者
闫新庆
贾营
赵丽
李雅琪
张晨曦
Yan Xinqing;Jia Ying;Zhao Li;Li Yaqi;Zhang Chenxi(School of Information Engineering,North China University of Water Resources and Electronic Power,Zhengzhou 450046,China)
出处
《电子测量技术》
北大核心
2023年第2期169-174,共6页
Electronic Measurement Technology
作者简介
闫新庆,博士,副教授,主要研究方向为仪器与测试技术、图像处理与模式识别等。E-mail:yanxq@ncwu.edu.cn;通信作者:贾营,硕士研究生,主要研究方向为图像处理与模式识别。E-mail:984025264@qq.com
