Paper
29 January 2007 A scale distortion invariant pattern recognition with fractional matching filter correlation
Jun Li, Bin He, Guang-zhi Fu, Chun-hui Wang
Author Affiliations +
Proceedings Volume 6279, 27th International Congress on High-Speed Photography and Photonics; 62797I (2007) https://doi.org/10.1117/12.725957
Event: 27th International congress on High-Speed Photography and Photonics, 2006, Xi'an, China
Abstract
Two optical units who are constructed by one Fresnel transform and one lens can produce a scale fractional Fourier transform. The constraints between the tow units are analyzed. Based on that and fractional correlation theory, a scale distortion invariant pattern recognition method is proposed. Simulation results show that when a scale distortion input image can't be rightly recognized by the conventional correlation, it can be recognized well with the method. Deficiency of the method is that lots of matching filters are needed.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jun Li, Bin He, Guang-zhi Fu, and Chun-hui Wang "A scale distortion invariant pattern recognition with fractional matching filter correlation", Proc. SPIE 6279, 27th International Congress on High-Speed Photography and Photonics, 62797I (29 January 2007); https://doi.org/10.1117/12.725957
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Distortion

Distortion invariant pattern recognition

Fractional fourier transform

Image filtering

Commercial off the shelf technology

Optical correlators

Optical filters

RELATED CONTENT


Back to Top