|Feature Correspondence Based on Directed Structural Model Matching|
|Yang X(杨旭); Qiao, Hong; Liu, Zhiyong; Zhi-Yong Liu
|Source Publication||Image and Vision Computing
|Abstract||Feature correspondence lays the foundation for many tasks in computer vision and pattern recognition. In this paper the directed structural model is utilized to represent the feature set, and the correspondence problem is then formulated as the structural model matching. Compared with the undirected structural model, the proposed directed model provides more discriminating ability and invariance against rotation and scale transformations. Finally, the recently proposed convex–concave relaxation procedure (CCRP) is generalized to approximately solve the problem. Extensive experiments on synthetic and real data witness the effectiveness of the proposed method.|
Directed Structural Model
|Corresponding Author||Zhi-Yong Liu|
|First Author Affilication||中国科学院自动化研究所
Yang X,Qiao, Hong,Liu, Zhiyong,et al. Feature Correspondence Based on Directed Structural Model Matching[J]. Image and Vision Computing,2015(33):57-67.
Yang X,Qiao, Hong,Liu, Zhiyong,&Zhi-Yong Liu.(2015).Feature Correspondence Based on Directed Structural Model Matching.Image and Vision Computing(33),57-67.
Yang X,et al."Feature Correspondence Based on Directed Structural Model Matching".Image and Vision Computing .33(2015):57-67.
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.