A Comparison of SIFT and Harris conner features for correspondence points matching

Author

Le, My-Ha ; Woo, Byung-Seok ; Jo, Kang-Hyun

Author_Institution

Graduated Sch. of Electr. Eng., Univ. of Ulsan, Ulsan, South Korea

fYear

2011

fDate

9-11 Feb. 2011

Firstpage

1

Lastpage

4

Abstract

This paper presents a comparative study of two competing features for the task of finding correspondence points in consecutive image frames. One is the Harris corner feature and the other is the SIFT feature. First, consecutive frames are extracted from video data then two kinds of features are computed. Second, correspondence points matching will be found. The results of SIFT key points matching and Harris key points will be compare and discussed. The comparison based on the result of implementation video data of outdoor with difference condition of intensity and angle of view.

Keywords

feature extraction; image matching; Harris conner features; SIFT feature; angle of view; correspondence points matching; difference condition of intensity; feature extraction; image frames; video data; Equations; Feature extraction; Histograms; Image reconstruction; Mathematical model; Robustness; Three dimensional displays; Harris conner; SIFT; correspondence points matching;

fLanguage

English

Publisher

ieee

Conference_Titel

Frontiers of Computer Vision (FCV), 2011 17th Korea-Japan Joint Workshop on

Conference_Location

Ulsan

Print_ISBN

978-1-61284-677-4

Electronic_ISBN

978-1-61284-676-7

Type

conf

DOI

10.1109/FCV.2011.5739748

Filename

5739748