Presentation 1998/9/11
Recognition of Blurred Images Based on Phase Invariants
Jianyin Lu, Yasuo Yoshida,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recognition of a blurred image against an image database plays an important role in many application areas. Classical methods try to estimate the blur parameters and to restore the image before recognition. In this paper, we propose an alternative approach that need no image restoration. We show that the FFT phase of an image is invariant with respect to blur if the PSF of the blur system is symmetric and the FFT of PSF is positive. Then, we derive a phase cross-correlation function between two images which becomes a delta function if one of the image is a blurred version of another. An recognition algorithm based on the function is introduced. Numerical experiments using number images of a car license plate are presented to illustrate the utilization of the algorithm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) phase invariant / blurred image / symmetric blur / correlation / image recognition
Paper # DSP98-81,SP98-60
Date of Issue

Conference Information
Committee DSP
Conference Date 1998/9/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Digital Signal Processing (DSP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Recognition of Blurred Images Based on Phase Invariants
Sub Title (in English)
Keyword(1) phase invariant
Keyword(2) blurred image
Keyword(3) symmetric blur
Keyword(4) correlation
Keyword(5) image recognition
1st Author's Name Jianyin Lu
1st Author's Affiliation Faculty of Engineering and Design, Kyoto Institute of Technology()
2nd Author's Name Yasuo Yoshida
2nd Author's Affiliation Faculty of Engineering and Design, Kyoto Institute of Technology
Date 1998/9/11
Paper # DSP98-81,SP98-60
Volume (vol) vol.98
Number (no) 262
Page pp.pp.-
#Pages 8
Date of Issue