Data Embedding into Characters

Koichi KISE; Shinichiro OMACHI; Seiichi UCHIDA; Masakazu IWAMURA; Marcus LIWICKI

doi:10.1587/transinf.2014MUI0002

Open Access
Data Embedding into Characters

Koichi KISE, Shinichiro OMACHI, Seiichi UCHIDA, Masakazu IWAMURA, Marcus LIWICKI

Full Text Views

143

Share
Cite this

Free PDF (1.6MB)

Summary :

This paper reviews several trials of re-designing conventional communication medium, i.e., characters, for enriching their functions by using data-embedding techniques. For example, characters are re-designed to have better machine-readability even under various geometric distortions by embedding a geometric invariant into each character image to represent class label of the character. Another example is to embed various information into handwriting trajectory by using a new pen device, called a data-embedding pen. An experimental result showed that we can embed 32-bit information into a handwritten line of 5 cm length by using the pen device. In addition to those applications, we also discuss the relationship between data-embedding and pattern recognition in a theoretical point of view. Several theories tell that if we have appropriate supplementary information by data-embedding, we can enhance pattern recognition performance up to 100%.

Publication: IEICE TRANSACTIONS on Information Vol.E98-D No.1 pp.10-20

Publication Date: 2015/01/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014MUI0002

Type of Manuscript: Special Section INVITED PAPER (Special Section on Enriched Multimedia)

Category

Authors

Koichi KISE
  Osaka Prefecture University
Shinichiro OMACHI
  Tohoku University
Seiichi UCHIDA
  Kyushu University
Masakazu IWAMURA
  Osaka Prefecture University
Marcus LIWICKI
  DFKI

Keyword

data embedding, character recognition, handwriting, supplementary information, character design, geometric invariant, pen device

Cite this

Copy

Koichi KISE, Shinichiro OMACHI, Seiichi UCHIDA, Masakazu IWAMURA, Marcus LIWICKI, "Data Embedding into Characters" in IEICE TRANSACTIONS on Information, vol. E98-D, no. 1, pp. 10-20, January 2015, doi: 10.1587/transinf.2014MUI0002.
Abstract: This paper reviews several trials of re-designing conventional communication medium, i.e., characters, for enriching their functions by using data-embedding techniques. For example, characters are re-designed to have better machine-readability even under various geometric distortions by embedding a geometric invariant into each character image to represent class label of the character. Another example is to embed various information into handwriting trajectory by using a new pen device, called a data-embedding pen. An experimental result showed that we can embed 32-bit information into a handwritten line of 5 cm length by using the pen device. In addition to those applications, we also discuss the relationship between data-embedding and pattern recognition in a theoretical point of view. Several theories tell that if we have appropriate supplementary information by data-embedding, we can enhance pattern recognition performance up to 100%.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2014MUI0002/_p

Copy

@ARTICLE{e98-d_1_10,
author={Koichi KISE, Shinichiro OMACHI, Seiichi UCHIDA, Masakazu IWAMURA, Marcus LIWICKI, },
journal={IEICE TRANSACTIONS on Information},
title={Data Embedding into Characters},
year={2015},
volume={E98-D},
number={1},
pages={10-20},
abstract={This paper reviews several trials of re-designing conventional communication medium, i.e., characters, for enriching their functions by using data-embedding techniques. For example, characters are re-designed to have better machine-readability even under various geometric distortions by embedding a geometric invariant into each character image to represent class label of the character. Another example is to embed various information into handwriting trajectory by using a new pen device, called a data-embedding pen. An experimental result showed that we can embed 32-bit information into a handwritten line of 5 cm length by using the pen device. In addition to those applications, we also discuss the relationship between data-embedding and pattern recognition in a theoretical point of view. Several theories tell that if we have appropriate supplementary information by data-embedding, we can enhance pattern recognition performance up to 100%.},
keywords={},
doi={10.1587/transinf.2014MUI0002},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - Data Embedding into Characters
T2 - IEICE TRANSACTIONS on Information
SP - 10
EP - 20
AU - Koichi KISE
AU - Shinichiro OMACHI
AU - Seiichi UCHIDA
AU - Masakazu IWAMURA
AU - Marcus LIWICKI
PY - 2015
DO - 10.1587/transinf.2014MUI0002
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2015
AB - This paper reviews several trials of re-designing conventional communication medium, i.e., characters, for enriching their functions by using data-embedding techniques. For example, characters are re-designed to have better machine-readability even under various geometric distortions by embedding a geometric invariant into each character image to represent class label of the character. Another example is to embed various information into handwriting trajectory by using a new pen device, called a data-embedding pen. An experimental result showed that we can embed 32-bit information into a handwritten line of 5 cm length by using the pen device. In addition to those applications, we also discuss the relationship between data-embedding and pattern recognition in a theoretical point of view. Several theories tell that if we have appropriate supplementary information by data-embedding, we can enhance pattern recognition performance up to 100%.
ER -