• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2017 International Conference on Security, Pattern Analysis, and Cybernetics >Discriminant orientation and scale features learning with application to palmprint recognition
【24h】

Discriminant orientation and scale features learning with application to palmprint recognition

机译：区分方向和比例尺特征学习及其在掌纹识别中的应用

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Palmprint recognition has now become an important identity recognition technique. Palmprint image contains abundant texture features, especially the orientation and scale features of palm lines. Existing palmprint recognition methods using texture features can be roughly categorized into two classes: coding based and local descriptor based methods. As compared with the latter class, the former one can make full use of the palmprint specific features and acquire fast matching speed. However, most existing coding based methods utilize the competitive coding scheme, which doesn't exploit the scale features of palmprint in their coding schemes. In this paper, we propose a discriminant orientation and scale features learning (DOSFL) for palmprint recognition. By introducing the idea of discriminant analysis into palmprint coding, DOSFL can extract the orientation and scale features with the most favorable discriminability. Then, DOSFL utilizes four code bits to represent both the orientation and scale features of palmprint, and employ the Hamming distance for code matching. Experiments on the commonly-used HK PolyU palmprint database demonstrate that our proposed approach can achieve better recognition results than several representative methods.
机译：掌纹识别现已成为一种重要的身份识别技术。掌纹图像包含丰富的纹理特征，尤其是掌纹的方向和比例特征。现有的使用纹理特征的掌纹识别方法可以大致分为两类：基于编码的方法和基于局部描述符的方法。与后一类相比，前一类可以充分利用掌纹的特定功能并获得快速的匹配速度。但是，大多数现有的基于编码的方法都使用竞争性编码方案，而竞争编码方案并未在其编码方案中利用掌纹的比例尺特征。在本文中，我们提出了用于掌纹识别的判别方向和尺度特征学习（DOSFL）。通过将判别分析的思想引入掌纹编码中，DOSFL可以提取具有最佳判别能力的方向和比例尺特征。然后，DOSFL利用四个代码位来表示掌印的方向和比例特征，并使用汉明距离进行代码匹配。在常用的香港理大掌纹数据库上进行的实验表明，与几种代表性方法相比，我们提出的方法可以获得更好的识别结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号