基于图像匹配的古陶瓷身份自动认证方法  

Ancient Ceramics Verification Based on Image Matching

作　　者：唐云祁[1] 丁建伟[2] 陈蕊丽[1] 田华伟[3] 郭威[1] 

机构地区：[1]中国人民公安大学刑事科学技术学院,北京100038 [2]中国人民公安大学信息技术与网络安全学院,北京100038 [3]中国人民公安大学侦查与反恐怖学院,北京100038

出　　处：《数据采集与处理》2016年第4期728-736,共9页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61503387)资助项目;中央高校基本科研业务费项目(2016JKF01203)资助项目

摘　　要：针对古陶瓷鉴定证书安全性低和公信度有限的问题,利用古陶瓷表面细节信息的独特性,基于图像识别技术,研究安全性高的古陶瓷身份自动认证方法。登记注册时将古陶瓷表面若干点位的细节信息以图像的形式录入系统;认证时,系统在线采集古陶瓷细节信息,与对应点位注册图像作匹配,并依据所有点位细节信息图像间的匹配结果来对古陶瓷进行认证。为验证方法性能,本文构建了一个古陶瓷细节信息数据库。实验结果表明,本文提出的方法能够实现古陶瓷身份的高精度认证。Ceramics appraisal is a hot topic in field of cultural relic collection. Traditionally, there are mainly two types of ceramics appraisal methods, which are experience-based and technology-based meth- ods. In practice, both methods will cause high cost and time-consuming. A novel vision-based method, which is mainly inspired by the idea of biometrics recognition techniques, is proposed to achieve efficiently verification of the identity of a ceramics. In this method, the microscopic information of a ceramics cap- tured by a digital microscope camera is used as the characteristics for verification. In technical detail, speeded up robust features（SURF） is first employed to align the probe image to the gallery images. Local binary patterns（LBP） features are then extracted from the two aligned images. Finally, Chi-square dis- tance is calculated to measure the similarity between probe and gallery. Experiments on the dataset con- structed by this paper demonstrate the state-of-the-art performance of proposed method.

关 键 词：图像匹配 古陶瓷鉴定 加速稳健特征 二值判别模式 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]