Title :
Robust irregular region matching based on inner product and exterior product
Author :
Liu, Hongmin ; Wang, Zhiheng
Author_Institution :
Sch. of Comput. Sci. & Tech., Henan Polytech. Univ., Jiaozuo, China
Abstract :
A great deal of descriptors for region matching have been proposed in last years. However, an extra step, fitting the irregular regions into fixed shapes, must be implemented in advance when constructing these descriptors on irregular regions. This fitting step can cause great errors, and thus will result in poor matching. Base on inner product and exterior product, this paper develops a method for constructing descriptors on irregular regions without any extra fitting steps. Experimental results prove that descriptors proposed in this paper can perform great and robust for irregular region matching.
Keywords :
gradient methods; image matching; vectors; Gaussian gradients; descriptor construction; exterior product; inner product; robust irregular region matching; Automation; Computational complexity; Computer science; Filters; Histograms; Matrix decomposition; Principal component analysis; Quantization; Robustness; Shape; Exterior product; Inner product; Irregular region matching; Region descriptor;
Conference_Titel :
Information and Automation (ICIA), 2010 IEEE International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-5701-4
DOI :
10.1109/ICINFA.2010.5512191