DocumentCode
3342825
Title
Rotation Invariant Shape Contexts based on Feature-space Fourier Transformation
Author
Yang, Su ; Wang, Yuanyuan
Author_Institution
Fudan Univ., Shanghai
fYear
2007
fDate
22-24 Aug. 2007
Firstpage
575
Lastpage
579
Abstract
We propose a new pixel-level shape descriptor. First, shape contexts are computed. Then, 2D FFT is performed on each 2D histogram from shape contexts. Such a scheme solves the rotation-invariance problem of shape contexts based on the shift theorem of Fourier transformation while does not increase the computational complexity. Theoretical proof and experimental validation are provided.
Keywords
Fourier transforms; computational geometry; 2D histogram; feature-space Fourier transformation; pixel-level shape descriptor; rotation invariant shape contexts; Computational complexity; Computer graphics; Computer science; Computer vision; Histograms; Pattern matching; Pattern recognition; Pixel; Robustness; Shape;
fLanguage
English
Publisher
ieee
Conference_Titel
Image and Graphics, 2007. ICIG 2007. Fourth International Conference on
Conference_Location
Sichuan
Print_ISBN
0-7695-2929-1
Type
conf
DOI
10.1109/ICIG.2007.18
Filename
4297150
Link To Document