检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:段兴钰 陈福仕 韩星周 DUAN Xingyu;CHEN Fushi;HAN Xingzhou(School of Investigation,People's Public Security University of China,Beijing 100038,China;Institute of Forensic Science,Ministry of Public Security,Beijing 100038,China)
机构地区:[1]中国人民公安大学侦查学院,北京100038 [2]公安部鉴定中心,北京100038
出 处:《智能计算机与应用》2025年第2期40-46,共7页Intelligent Computer and Applications
基 金:基本科研业务费项目(2024JB020);法庭科学湖北省重点实验室开放课题(KFKT2023001);文件检验鉴定公安部重点实验室开放课题(2021KFKT01)。
摘 要:印油种类区分是法庭科学文件检验的重要一环,对印油进行种类鉴别在印章印文检验中具有重要意义。为研究无损高效区分光敏印油种类的方法,本文用50种不同品牌光敏印油的原始光谱数据,选择Resnet18、Resnet50、Resnet101这3种模型,以4∶1的比例确定训练集和测试集,对原始数据进行分类。结果表明,Resnet18分类算法对显微分光光谱数据区分的准确率最高,可达到92.81%,为深度学习算法在光敏印油区分领域的应用提供一定参考。The classification of printing oil is an important part in the field of forensic scientific document examination,and the classification of printing oil is of great significance in the examination of seal documents.In order to study the method of non-destructive and efficient classification of photosensitive printing oil types,the original spectral data of 50 different brands of photosensitive printing oil were taken as the control group,and three classification algorithms Resnet18,Resnet50 and Resnet101 were selected to determine the training set and test set at the ratio of 4:l,and the original data were classified.The results show that Resnet18 classification algorithm has the highest accuracy of distinguishing microspectral data,reaching 92.81%,which provides a certain reference for the application of deep learning algorithm in the field of photosensitive printing oil classification.
分 类 号:TP183[自动化与计算机技术—控制理论与控制工程] O657.3[自动化与计算机技术—控制科学与工程] D918.92[理学—分析化学]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.222