Optimal object matching via convexification and composition

Hongsheng Li, Junzhou Huang, Shaoting Zhang, Xiaolei Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Scopus citations


In this paper, we propose a novel object matching method to match an object to its instance in an input scene image, where both the object template and the input scene image are represented by groups of feature points. We relax each template point's discrete feature cost function to create a convex function that can be optimized efficiently. Such continuous and convex functions with different regularization terms are able to create different convex optimization models handling objects undergoing (i) global transformation, (ii) locally affine transformation, and (iii) articulated transformation. These models can better constrain each template point's transformation and therefore generate more robust matching results. Unlike traditional object or feature matching methods with "hard" node-to-node results, our proposed method allows template points to be transformed to any location in the image plane. Such a property makes our method robust to feature point occlusion or mis-detection. Our extensive experiments demonstrate the robustness and flexibility of our method.

Original languageEnglish (US)
Title of host publication2011 International Conference on Computer Vision, ICCV 2011
Number of pages8
StatePublished - 2011
Event2011 IEEE International Conference on Computer Vision, ICCV 2011 - Barcelona, Spain
Duration: Nov 6 2011Nov 13 2011

Publication series

NameProceedings of the IEEE International Conference on Computer Vision


Conference2011 IEEE International Conference on Computer Vision, ICCV 2011

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Optimal object matching via convexification and composition'. Together they form a unique fingerprint.

Cite this