计算机应用 ›› 2013, Vol. 33 ›› Issue (04): 1096-1099.DOI: 10.3724/SP.J.1087.2013.01096

• 多媒体处理技术 • 上一篇    下一篇

图像局部映射二进制串描述符

汤培楷,陈玮,麦毅成   

  1. 广东工业大学 自动化学院,广州 510006
  • 收稿日期:2012-10-09 修回日期:2012-11-29 出版日期:2013-04-01 发布日期:2013-04-23
  • 通讯作者: 汤培楷
  • 作者简介:汤培楷(1988-),男,广东汕头人,硕士研究生,主要研究方向:机器视觉;陈玮(1963-),女,浙江温州人,教授,博士,主要研究方向:智能控制、离散事件动态系统;麦毅成(1989-),男,广东佛山人,硕士研究生,主要研究方向:机器视觉。

Binary projection for image local descriptor

TANG Peikai,CHEN Wei,MAI Yicheng   

  1. College of Automation, Guangdong University of Technology, Guangzhou Guangdong 510006, China
  • Received:2012-10-09 Revised:2012-11-29 Online:2013-04-01 Published:2013-04-23
  • Contact: TANG Peikai

摘要: 为了提高图像局部特征算法的计算速率与匹配速度,并保持其准确率,提出了一种局部映射二进制串描述符算法。它通过映射的方法将图像局部区域转化成二进制串,从而提高其计算效率与匹配速度,并通过机器学习的方法寻找最佳映射矩阵,保持其准确率。从实验结果表明,只需32比特的二进制串就可以在准确率上媲美现有的局部描述符算法,并在匹配速度上有较大的优势。

关键词: 二进制串, 局部特征, 描述符, 图像匹配, 特征提取

Abstract: In order to reduce the computational burden and maintain the recognition rate of the image local descriptor, a binary projection method for image local descriptor was proposed. The image patch was projected and transformed into a binary string for boosting the performance as well as speeding up the matching speed. The projection matrix was optimized by machine learning method to maintain its recognition rate and robustness. The experimental result indicates that only a 32-bit binary string is needed to perform as well as the state-of-art descriptors and it shows significantly faster matching speed.

Key words: binary string, local feature, descriptor, image matching, feature extraction

中图分类号: