Fast rotation-invariant template matching with candidate reduction using CUDA

Author

Seung-ho Kim ; Sang-hyeob Song ; Jong-hak Kim ; Zhongyun Yuan ; Jun-dong Cho

Author_Institution

Coll. of Inf. & Commun. Eng., Sungkyunkwan Univ., Suwon, South Korea

fYear

2015

fDate

24-26 June 2015

Firstpage

1

Lastpage

2

Abstract

This paper presents a Ring Projection Transforms (RPT) for recognizing an object in automation system. Based on the Coarse-fine strategy and Compute Unified Device Architecture (CUDA), we developed a recognition model on GPGPU (General-Purpose computing on Graphics Processing Units) scheme. As experimental validation indicates, our scheme achieved a better performance in terms of processing time compared with the existing method.

Keywords

graphics processing units; image matching; object recognition; parallel architectures; CUDA; GPGPU scheme; RPT; automation system; candidate reduction; coarse-fine strategy; compute unified device architecture; experimental validation; fast rotation-invariant template matching; general-purpose computing on graphics processing units; object recognition; ring projection transforms; Automation; Consumer electronics; Graphics processing units; Industries; Instruction sets; Mathematical model; Transforms; CUDA; GPGPU; RPT; Recognition; Ring Projection Transforms; Template Matching; Vision;

fLanguage

English

Publisher

ieee

Conference_Titel

Consumer Electronics (ISCE), 2015 IEEE International Symposium on

Conference_Location

Madrid

Type

conf

DOI

10.1109/ISCE.2015.7177792

Filename

7177792