Title :
Non-rigid Object Matching Using Hypergraph Method
Author :
Deyuan Li ; Yue Zhou
Author_Institution :
Inst. of Image Process. & Pattern Recognition, Shanghai Jiao Tong Univ., Shanghai, China
Abstract :
We present a non-rigid object matching algorithm based on hyper graph method. Previous work has achieved good performance for rigid object matching. However, because of deformation and wrinkle, existing algorithms cannot solve non-rigid object matching problem effectively. This paper mainly focuses on matching patterns on cloth which often deforms greatly. First, we extract stable regions from the given image. Second, we combine several features in region as bundled feature. In addition, we describe the characteristic of region based on bundled feature and the relationship among regions based on star topology. Finally, we establish the problem model and get the matching result by mathematical programming technique and refinement. Experimental results on both synthetic data and real image show the good performance of our algorithm.
Keywords :
graph theory; image matching; mathematical programming; bundled feature; hypergraph method; mathematical programming technique; nonrigid object matching; pattern matching; star topology; Algorithm design and analysis; Computational modeling; Feature extraction; Mathematical model; Noise; Pattern matching; Topology; bundled feature; hypergraph method; non-rigid object matching; result refinement; star topology;
Conference_Titel :
Image and Graphics (ICIG), 2013 Seventh International Conference on
Conference_Location :
Qingdao
DOI :
10.1109/ICIG.2013.117