An affine invariant feature detection method based on SIFT and MSER

Author

Zhuping Wang ; Huiyu Mo ; Han Wang ; Danwei Wang

Author_Institution

Coll. of Electron. & Inf. Eng., Tongji Univ., Shanghai, China

fYear

2012

fDate

18-20 July 2012

Firstpage

69

Lastpage

72

Abstract

In this paper, an affine invariance feature detection method based on Scale Invariant Feature Transform (SIFT) and Maximally Stable Extremal Regions (MSER) is proposed. Classical SIFT algorithm is not robust to affine deformations, because it is based on DOG detector which extracts circle regions for keypoint location. In order to overcome this disadvantage, DOG detector in conventional SIFT algorithm is replaced by MSER detector which is robust to affine deformation. Then these regions are normalized and extracted using SIFT. Simulation studies are carried out to show the effectiveness of the proposed method to affine transform in comparison to traditional SIFT algorithm.

Keywords

computer vision; feature extraction; image matching; image restoration; transforms; DOG detector; MSER detector; SIFT algorithm; affine invariant feature detection method; affine transform; circle region extraction; computer vision; image matching; image restoration; image understanding; keypoint location; maximally stable extremal regions; object identification; scale invariant feature transform; Computer vision; Covariance matrix; Detectors; Feature extraction; Robustness; Transforms; Vectors; MSER; SIFT; features extract; image normalization;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics and Applications (ICIEA), 2012 7th IEEE Conference on

Conference_Location

Singapore

Print_ISBN

978-1-4577-2118-2

Type

conf

DOI

10.1109/ICIEA.2012.6360699

Filename

6360699