{"title":"Palmprint recognition using Palm-line direction field texture feature","authors":"Yan-Xia Wang, Guangling Sun","doi":"10.1109/ICMLC.2012.6359513","DOIUrl":null,"url":null,"abstract":"Compared with the Palm line structure features, extraction and description of palm print texture features are easier. But, with the increase in the number of palmprint samples, these features are not powerful enough. In order to solve the problem, the paper proposes a new approach to enhance the distinguishing capability of texture features for palm print recognition. It uses classical results on Riemannian geometry to obtain the information of palm lines and construct direction fields of palm lines. The direction fields become a part of the textures of the palmprint image to enhance the distinguishing capability of texture features. Finally, the dual-tree complex wavelet transform-based local binary pattern weighted histogram method (DT -CWT based LBPWH) is used to extract enhanced texture features. The experimental results validate the effectiveness of the method.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"71 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 International Conference on Machine Learning and Cybernetics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMLC.2012.6359513","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
Compared with the Palm line structure features, extraction and description of palm print texture features are easier. But, with the increase in the number of palmprint samples, these features are not powerful enough. In order to solve the problem, the paper proposes a new approach to enhance the distinguishing capability of texture features for palm print recognition. It uses classical results on Riemannian geometry to obtain the information of palm lines and construct direction fields of palm lines. The direction fields become a part of the textures of the palmprint image to enhance the distinguishing capability of texture features. Finally, the dual-tree complex wavelet transform-based local binary pattern weighted histogram method (DT -CWT based LBPWH) is used to extract enhanced texture features. The experimental results validate the effectiveness of the method.
与掌纹结构特征相比,掌纹纹理特征的提取和描述更为简单。但是,随着掌纹样本数量的增加,这些功能不够强大。为了解决这一问题,本文提出了一种增强纹理特征识别能力的新方法。利用经典黎曼几何结果获取掌线信息,构造掌线方向场。方向场成为掌纹图像纹理的一部分,增强了纹理特征的识别能力。最后,采用基于双树复小波变换的局部二值模式加权直方图方法(DT -CWT based LBPWH)提取增强纹理特征。实验结果验证了该方法的有效性。