Presentation 2015-02-19
Extraction of Dot Matrix Text for Factory Automation OCR
Koshi SUZUKI, Wataru OHYAMA, Tetsushi WAKABAYASHI, Fumitaka KIMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we propose a method extracts dot matrix text used for showing expiration date and manufacturing symbol. The problems of dot matrix text extraction are deformation and rotation by curved surface printing, the difference of the dot arrangement and size of each product and unnecessary characters that are not subject of extraction on the product. In this paper, as a part of the dot matrix text recognition and extraction process, we propose a method for extraction of candidate region of dot matrix text by selecting extracted FAST points using dot characteristics and by clustering of brightness of candidate points. We evaluated performance of the proposed method by experiment with 250 product images. The result shows that recall and precision of text extraction are 94.4% and 40.1%, respectively.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) dot matrix character / text extraction / FAST points
Paper # PRMU2014-129,CNR2014-44
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) Extraction of Dot Matrix Text for Factory Automation OCR
Sub Title (in English)
Keyword(1) dot matrix character
Keyword(2) text extraction
Keyword(3) FAST points
1st Author's Name Koshi SUZUKI
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 # PRMU2014-129,CNR2014-44
Volume (vol) vol.114
Number (no) 454
Page pp.pp.-
#Pages 2
Date of Issue