Presentation 2011-10-24
Toward Machine Vision Technology Overcoming the Pixel Resolution Limit : From 3D Vision to Biometric Authentication
Takafumi AOKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents fundamentals of Phase-Only Correlation (POC) -- a technique for high-accuracy registration of 1D, 2D and 3D signals using phase information of discrete Fourier transform. Since 1990s, our research group has developed a novel technique of phase-based image matching for fingerprint verification and industrial machine vision. We have recently proposed an efficient image correspondence algorithm using POC, which can find pairs of corresponding points between the given two images with sub-pixel accuracy. This allows us to apply the POC technique to a wide range of applications, including smart image sensors, microscope image analysis, passive 3D vision, automotive image processing, image-based human interface, biometric authentication, and medical image analysis.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Computer Vision / Image Matching / Image Registration / 3D Measurement / Biometric Authentication
Paper # SIP2011-62,ICD2011-65,IE2011-61
Date of Issue

Conference Information
Committee ICD
Conference Date 2011/10/17(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 Integrated Circuits and Devices (ICD)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Toward Machine Vision Technology Overcoming the Pixel Resolution Limit : From 3D Vision to Biometric Authentication
Sub Title (in English)
Keyword(1) Computer Vision
Keyword(2) Image Matching
Keyword(3) Image Registration
Keyword(4) 3D Measurement
Keyword(5) Biometric Authentication
1st Author's Name Takafumi AOKI
1st Author's Affiliation Graduate School of Information Sciences, Tohoku University()
Date 2011-10-24
Paper # SIP2011-62,ICD2011-65,IE2011-61
Volume (vol) vol.111
Number (no) 258
Page pp.pp.-
#Pages 6
Date of Issue