Isolated character recognition by searching features in scene images

Kazuya Negishi; Masakazu Iwamura; Shinichiro Omachi; Hirotomo Aso

Isolated character recognition by searching features in scene images

Kazuya Negishi, Masakazu Iwamura, Shinichiro Omachi, Hirotomo Aso

ENG - Communications Engineering

Research output: Contribution to conference › Paper › peer-review

5 Citations (Scopus)

Abstract

Conventional segmentation technique cannot extract an isolated character and a touching character. In this paper, to utilize information of such characters, we propose a novel character recognition method based on extracting feature points and voting. The voting algorithm of the proposed method is similar to the generalized Hough transform. This method enables us to extract and recognize such troublesome characters in relatively shorter computational time. The effectiveness of the proposed method is confirmed by experiments.

Original language	English
Pages	140-147
Number of pages	8
Publication status	Published - 2005
Event	1st International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2005 - Seoul, Korea, Republic of Duration: 2005 Aug 29 → 2005 Aug 29

Other

Other	1st International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2005
Country/Territory	Korea, Republic of
City	Seoul
Period	05/8/29 → 05/8/29

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Software

Cite this

@conference{6472ec42c9fe4c53b5743ed1bd07881d,

title = "Isolated character recognition by searching features in scene images",

abstract = "Conventional segmentation technique cannot extract an isolated character and a touching character. In this paper, to utilize information of such characters, we propose a novel character recognition method based on extracting feature points and voting. The voting algorithm of the proposed method is similar to the generalized Hough transform. This method enables us to extract and recognize such troublesome characters in relatively shorter computational time. The effectiveness of the proposed method is confirmed by experiments.",

author = "Kazuya Negishi and Masakazu Iwamura and Shinichiro Omachi and Hirotomo Aso",

year = "2005",

language = "English",

pages = "140--147",

note = "1st International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2005 ; Conference date: 29-08-2005 Through 29-08-2005",

}

TY - CONF

T1 - Isolated character recognition by searching features in scene images

AU - Negishi, Kazuya

AU - Iwamura, Masakazu

AU - Omachi, Shinichiro

AU - Aso, Hirotomo

PY - 2005

Y1 - 2005

N2 - Conventional segmentation technique cannot extract an isolated character and a touching character. In this paper, to utilize information of such characters, we propose a novel character recognition method based on extracting feature points and voting. The voting algorithm of the proposed method is similar to the generalized Hough transform. This method enables us to extract and recognize such troublesome characters in relatively shorter computational time. The effectiveness of the proposed method is confirmed by experiments.

AB - Conventional segmentation technique cannot extract an isolated character and a touching character. In this paper, to utilize information of such characters, we propose a novel character recognition method based on extracting feature points and voting. The voting algorithm of the proposed method is similar to the generalized Hough transform. This method enables us to extract and recognize such troublesome characters in relatively shorter computational time. The effectiveness of the proposed method is confirmed by experiments.

UR - http://www.scopus.com/inward/record.url?scp=34047234664&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34047234664&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:34047234664

SP - 140

EP - 147

T2 - 1st International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2005

Y2 - 29 August 2005 through 29 August 2005

ER -

Isolated character recognition by searching features in scene images

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this