东北大学学报:自然科学版 ›› 2016, Vol. 37 ›› Issue (2): 157-161.DOI: 10.12068/j.issn.1005-3026.2016.02.002

• 信息与控制 • 上一篇    下一篇

基于投票策略的特征点提取

陈红1,2, 吴成东1, 陈东岳1,卢紫微1   

  1. (1.东北大学 信息科学与工程学院, 辽宁 沈阳110819; 2.鞍山师范学院 物理科学与技术学院, 辽宁 鞍山 114005)
  • 收稿日期:2014-12-22 修回日期:2014-12-22 出版日期:2016-02-15 发布日期:2016-02-18
  • 通讯作者: 陈红
  • 作者简介:陈红(1978-),女,辽宁沈阳人,东北大学博士研究生,鞍山师范学院讲师; 吴成东(1960-),男,辽宁大连人,东北大学教授,博士生导师.
  • 基金资助:
    国家自然科学基金资助项目(61273078,61471110).

Key Point Extraction Based on Voting Strategy

CHEN Hong1, 2, WU Cheng-dong1, CHEN Dong-yue1, LU Zi-wei1   

  1. 1. School of Information Science & Engineering, Northeastern University, Shenyang 110819, China; 2. School of Physics Science and Technology, Anshan Normal University, Anshan 114005, China.
  • Received:2014-12-22 Revised:2014-12-22 Online:2016-02-15 Published:2016-02-18
  • Contact: CHEN Hong
  • About author:-
  • Supported by:
    -

摘要: 特征点提取算法中存在伪角点和定位不准确的问题,导致特征点匹配率低,并且影响图像配准精度和速度.针对这一问题,提出基于投票策略的特征点提取算法.算法通过选举人投票选举出最强特征性点集,有效去除伪角点.点集中的特征点满足多重准则,特征性强度高.依据坐标选举,保证了特征点定位的准确性.在发生相似变换、亮度变化和加噪的情况下对大量图像进行了特征点提取和匹配实验,并与传统的特征点提取方法进行比较.实验结果表明,该算法提取的特征点具有更好的有效性,算法具有较强的适应性和抗噪性.

关键词: 特征点提取, 点匹配, 投票策略, 图像配准, 伪角点

Abstract: False corners and inaccurate orientation in key point extraction algorithms will result in low matching rate and low image registration accuracy and speed. A new method is proposed to solve the problem. A set of strongest interest points is worked out in the algorithm to eliminate false corners. Interest points in the set have high characteristic strength and meet several criteria. The same coordinate is applied to ensure orientation accuracy. With similarity transformation, brightness change and noise, a series of images are tested with the new algorithm proposed and traditional algorithms, respectively. The results show that the new algorithm has better adaptability and anti-noise performance, and is more effective in feature points extraction.

Key words: key point extraction, point matching, voting strategy, image registration, false corner

中图分类号: