作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 人工智能及识别技术 • 上一篇    下一篇

基于方向信息的随机蕨特征匹配算法

孙博文a,邱子鉴b,沈 斌b,张艳鹏a   

  1. (哈尔滨理工大学 a. 计算中心;b. 计算机科学与技术学院,哈尔滨 150080)
  • 收稿日期:2013-04-23 出版日期:2014-05-15 发布日期:2014-05-14
  • 作者简介:孙博文(1963-),男,副教授,主研方向:模式识别,虚拟现实,增强现实;邱子鉴、沈 斌,硕士研究生;张艳鹏,硕士。

Random Fern Feature Matching Algorithm Based on Orientation Information

SUN Bo-wen a, QIU Zi-jian b, SHEN Bin b, ZHANG Yan-peng a   

  1. (a. Compute Center; b. School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China)
  • Received:2013-04-23 Online:2014-05-15 Published:2014-05-14

摘要: 特征点匹配是计算机视觉领域研究的核心问题之一。现有的随机蕨算法具有简单、高速的优点,但随机蕨算法训练得到的分类器体积过大,低内存的移动设备难以承受,严重限制了该算法的应用范围。针对该问题,提出一种基于方向信息的随机蕨特征匹配算法,对用于训练的小图块进行“归零化”处理,提取特征属性构造特征向量,建立朴素贝叶斯模型训练分类器。实验结果表明,经过该方法处理后,在相近识别精度下,得到的分类器体积减小到原始算法的1/8~1/16,满足实时性要求。

关键词: 随机蕨, 特征匹配, 增强现实, 模式识别, 贝叶斯模型, 方向蕨

Abstract: Feature point matching is a key base of many computer vision problems. A large advantage of fern algorithm, simple and fast, is noticed among the existing algorithms, but classifier trained by fern is too large to low memory device, such as cellphones. For cutting down the size of a classifier, this paper proposes an improved version of fern, named Oriented Fern(OFern), which “normal” patches are done that training for a classifier, and features are extracted, a Naive Bayesian model is built to train a classifier. Experimental results show that compared with the traditional fern, OFern can save memory to 1/8~1/16 at the similar recognition rate, while it still keeps high speed for real-time applications.

Key words: Random Fern(RF), feature matching, augmented reality, pattern recognition, Bayes model, Oriented Fern(OFern)

中图分类号: