Presentation 2015-02-19
Probabilistic Interpolation for Improving Three Dimensional Rotation Angle Estimation of Camera-captured Characters
Kanta KURAMOTO, Wataru OHYAMA, Tetsushi WAKABAYASHI, Fumitaka KIMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is necessary to recognize various accompanying information other than the character type in Camera-Based Optical Character Recognition. In this paper, we propose an efficient implementation of 3D rotation estimation for camera-captured characters. The proposed implementation requires small memory load and short computational time. We employ Linear Discriminant Function (LDF) instead of Modified Quadratic Discriminant Function (MQDF) for further memory reduction. The results of experimental evaluation using a alphanumeric character dataset showed that small number of dimensionality of original feature vector is sufficient for keeping accuracy of 3D rotation estimation and total amount of memory required for 3D rotation estimation is reduced from 1.7 GB to 6.6 MB. Moreover, we proposed probabilistic rotation angle estimation and achieved improvement of estimation accuray without increase of memory size.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) camera-based OCR / rotation angle estimation / gray-scale gradient feature / MQDF / probabilistic interpolation
Paper # PRMU2014-116,CNR2014-31
Date of Issue

Conference Information
Committee PRMU
Conference Date 2015/2/12(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Probabilistic Interpolation for Improving Three Dimensional Rotation Angle Estimation of Camera-captured Characters
Sub Title (in English)
Keyword(1) camera-based OCR
Keyword(2) rotation angle estimation
Keyword(3) gray-scale gradient feature
Keyword(4) MQDF
Keyword(5) probabilistic interpolation
1st Author's Name Kanta KURAMOTO
1st Author's Affiliation Graduate School of Engineering, Mie University()
2nd Author's Name Wataru OHYAMA
2nd Author's Affiliation Graduate School of Engineering, Mie University
3rd Author's Name Tetsushi WAKABAYASHI
3rd Author's Affiliation Graduate School of Engineering, Mie University
4th Author's Name Fumitaka KIMURA
4th Author's Affiliation Graduate School of Engineering, Mie University
Date 2015-02-19
Paper # PRMU2014-116,CNR2014-31
Volume (vol) vol.114
Number (no) 454
Page pp.pp.-
#Pages 6
Date of Issue