Journal of South China University of Technology (Natural Science Edition) ›› 2011, Vol. 39 ›› Issue (2): 118-124.doi: 10.3969/j.issn.1000-565X.2011.02.020

• Electronics, Communication & Automation Technology • Previous Articles     Next Articles

Object Recognition Approach Based on Local Type-Consistent k-Means Clustering

Liang Peng  Li Shao-fa Qin  Jiang-wei   

  1. School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, Guangdong, China
  • Received:2010-04-28 Online:2011-02-25 Published:2011-01-02
  • Contact: 梁鹏(1981-)，男，博士生，主要从事计算机视觉、机器学习和模式识别研究 E-mail:cs_phoenix_liang@163.com
  • About author:梁鹏(1981-)，男，博士生，主要从事计算机视觉、机器学习和模式识别研究
  • Supported by:

    国家自然科学基金资助项目(60273064)；广东省工业攻关计划项目(2004B10101032)

PDF

1656

Abstract:

Aiming at the object recognition in complex background,a recognition method,which simultaneously detects object location and classifies object types,is proposed.In this method,first,a large number of interest points are selected from the image and are filtered to obtain exactly-fitted outliers via the epipolar geometric constraint between images.Then,feature codebooks in the interest point space are formed via the local type consistent k-means clustering.Finally,for the given test interest points,the local features are voted to represent the object type,and the foreground object is obtained by maximizing the joint probability of object type and location.Experimental results on standard dataset Caltech-101 and real scene images demonstrate that the proposed method improves the recognition accuracy by about 8%.

Key words: Object Recognition, Local Type Consistent Kmeans Clustering, Epipolar Geometric Constraint, Interest Point