DocumentCode :
2256959
Title :
Extend point descriptors for line, curve and region matching
Author :
Liu, Hong-Min ; Wang, Zhi-Heng ; Deng, Chao
Author_Institution :
Sch. of Comput. Sci. & Tech., Henan Polytech. Univ., Jiaozuo, China
Volume :
1
fYear :
2010
fDate :
11-14 July 2010
Firstpage :
214
Lastpage :
219
Abstract :
Feature matching plays an important role in many applications, including 3D reconstruction, object recognition and video understanding. Point matching has made great progress recently, while it has made little progress in the fields of line and curve matching. By computing statistics of point descriptors constructed at each edge points, this paper develops a novel method for extending point descriptors to construct descriptors for lines, curves and regions. Experiment results exhibit that our method can perform good and robust on real images.
Keywords :
image matching; statistical analysis; 3D reconstruction; curve matching; edge points; line matching; object recognition; point descriptors; point matching; region feature matching; Computer vision; Detectors; Europe; Image edge detection; Machine learning; Pixel; Shape; Curve matching; Line matching; Region matching;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2010 International Conference on
Conference_Location :
Qingdao
Print_ISBN :
978-1-4244-6526-2
Type :
conf
DOI :
10.1109/ICMLC.2010.5581065
Filename :
5581065
Link To Document :
بازگشت