Fast Computation of Rotation-Invariant Image Features by an Approximate Radial Gradient Transform

Author

Takacs, Gabor ; Chandrasekhar, V. ; Tsai, Shauhyuarn Sean ; Chen, D. ; Grzeszczuk, R. ; Girod, B.

Author_Institution

Microsoft Corp., Sunnyvale, CA, USA

Volume

22

Issue

8

fYear

2013

fDate

Aug. 2013

Firstpage

2970

Lastpage

2982

Abstract

We present the radial gradient transform (RGT) and a fast approximation, the approximate RGT (ARGT). We analyze the effects of the approximation on gradient quantization and histogramming. The ARGT is incorporated into the rotation-invariant fast feature (RIFF) algorithm. We demonstrate that, using the ARGT, RIFF extracts features 16× faster than SURF while achieving a similar performance for image matching and retrieval.

Keywords

approximation theory; feature extraction; gradient methods; image matching; image retrieval; transforms; ARGT; RGT; RIFF feature extraction; SURF; approximate radial gradient transform; gradient quantization approximation; histogramming; image matching; image retrieval; rotation-invariant image features; Approximation methods; Computational modeling; Histograms; Image matching; Quantization; Transforms; Vectors; Computer vision; feature representation; invariants; real-time systems; signal processing; Algorithms; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique;

fLanguage

English

Journal_Title

Image Processing, IEEE Transactions on

Publisher

ieee

ISSN

1057-7149

Type

jour

DOI

10.1109/TIP.2012.2230011

Filename

6363603