DocumentCode
2953934
Title
Images´ Similarity Measurement Based on CUDA
Author
Li, Yuhao ; Ke, Yongzhen ; Wang, Zhiyi ; Guan, Ziqi
Author_Institution
Sch. of Comput. Sci. & Software, Tianjin Polytech. Univ., Tianjin, China
fYear
2011
fDate
30-31 July 2011
Firstpage
1
Lastpage
4
Abstract
Hausdorff distance-based image matching method is widely used. But it´s time-consuming to calculate the hausdorff distance of images with many feature points. This paper proposes an algorithm of images´ hasudorff distance based on GPU and CPU to speedup images´s similarity measurement. The experimental results show that the proposed algorithm of hausdorff distance based on CUDA achieves fairly good speedup and can be applied to image´s similarity measurement.
Keywords
computer graphic equipment; coprocessors; image matching; parallel architectures; CPU; CUDA; GPU; Hausdorff distance based image matching method; image similarity measurement; Feature extraction; Graphics processing unit; Image edge detection; Image matching; Kernel; Niobium; Software algorithms;
fLanguage
English
Publisher
ieee
Conference_Titel
Control, Automation and Systems Engineering (CASE), 2011 International Conference on
Conference_Location
Singapore
Print_ISBN
978-1-4577-0859-6
Type
conf
DOI
10.1109/ICCASE.2011.5997659
Filename
5997659
Link To Document