Rule-based optical character recognition for serial number on Renminbi banknote

Yu Shiuan Tsai; Yi Yu Hsieh; Chih Hui Ho; Ya Ching Chang; Yao Yuan Chang; Heng Jyun Lin; Han Yang Wang; Yu Chen Chou; Jen-Hui Chuang

doi:10.2352/ISSN.2470-1173.2018.13.IPAS-308

Rule-based optical character recognition for serial number on Renminbi banknote

Yu Shiuan Tsai, Yi Yu Hsieh, Chih Hui Ho, Ya Ching Chang, Yao Yuan Chang, Heng Jyun Lin, Han Yang Wang, Yu Chen Chou, Jen-Hui Chuang

Institute of Computer Science and Engineering

Research output: Contribution to journal › Conference article › peer-review

4 Scopus citations

Abstract

A rule-based optical character recognition system for the recognition of serial number on Renminbi (RMB) banknote is presented. It is based on the observation that the characters, including English letters and numbers, can be classified using two hand-crafted features, which are the opening and the loop. Each character has certain characteristics in terms of those two features and classification is achieved following the proposed scheme. The proposed system has been tested on 2245 RMB bills, which contain 22313 characters, and accomplished 99.35% for horizontal characters and 99.84% for vertical characters under 30ms processing time per banknote.

Original language	English
Article number	308
Journal	IS and T International Symposium on Electronic Imaging Science and Technology
DOIs	https://doi.org/10.2352/ISSN.2470-1173.2018.13.IPAS-308
State	Published - 2018
Event	16th Image Processing: Algorithms and Systems Symposium 2018 - Burlingame, United States Duration: 28 Jan 2018 → 1 Feb 2018

Keywords

Character recognition
Feature extraction
Optical character recognition software
Serial number recognition
Text recognition

Access to Document

10.2352/ISSN.2470-1173.2018.13.IPAS-308

Cite this

@article{df41bba1b8dd4b2cb42a5174c9a2a466,

title = "Rule-based optical character recognition for serial number on Renminbi banknote",

abstract = "A rule-based optical character recognition system for the recognition of serial number on Renminbi (RMB) banknote is presented. It is based on the observation that the characters, including English letters and numbers, can be classified using two hand-crafted features, which are the opening and the loop. Each character has certain characteristics in terms of those two features and classification is achieved following the proposed scheme. The proposed system has been tested on 2245 RMB bills, which contain 22313 characters, and accomplished 99.35% for horizontal characters and 99.84% for vertical characters under 30ms processing time per banknote.",

keywords = "Character recognition, Feature extraction, Optical character recognition software, Serial number recognition, Text recognition",

author = "Tsai, {Yu Shiuan} and Hsieh, {Yi Yu} and Ho, {Chih Hui} and Chang, {Ya Ching} and Chang, {Yao Yuan} and Lin, {Heng Jyun} and Wang, {Han Yang} and Chou, {Yu Chen} and Jen-Hui Chuang",

note = "Publisher Copyright: {\textcopyright} 2018 Society for Imaging Science and Technology.; 16th Image Processing: Algorithms and Systems Symposium 2018 ; Conference date: 28-01-2018 Through 01-02-2018",

year = "2018",

doi = "10.2352/ISSN.2470-1173.2018.13.IPAS-308",

language = "English",

journal = "IS and T International Symposium on Electronic Imaging Science and Technology",

issn = "2470-1173",

publisher = "Society for Imaging Science and Technology",

}

TY - JOUR

T1 - Rule-based optical character recognition for serial number on Renminbi banknote

AU - Tsai, Yu Shiuan

AU - Hsieh, Yi Yu

AU - Ho, Chih Hui

AU - Chang, Ya Ching

AU - Chang, Yao Yuan

AU - Lin, Heng Jyun

AU - Wang, Han Yang

AU - Chou, Yu Chen

AU - Chuang, Jen-Hui

PY - 2018

Y1 - 2018

N2 - A rule-based optical character recognition system for the recognition of serial number on Renminbi (RMB) banknote is presented. It is based on the observation that the characters, including English letters and numbers, can be classified using two hand-crafted features, which are the opening and the loop. Each character has certain characteristics in terms of those two features and classification is achieved following the proposed scheme. The proposed system has been tested on 2245 RMB bills, which contain 22313 characters, and accomplished 99.35% for horizontal characters and 99.84% for vertical characters under 30ms processing time per banknote.

AB - A rule-based optical character recognition system for the recognition of serial number on Renminbi (RMB) banknote is presented. It is based on the observation that the characters, including English letters and numbers, can be classified using two hand-crafted features, which are the opening and the loop. Each character has certain characteristics in terms of those two features and classification is achieved following the proposed scheme. The proposed system has been tested on 2245 RMB bills, which contain 22313 characters, and accomplished 99.35% for horizontal characters and 99.84% for vertical characters under 30ms processing time per banknote.

KW - Character recognition

KW - Feature extraction

KW - Optical character recognition software

KW - Serial number recognition

KW - Text recognition

UR - http://www.scopus.com/inward/record.url?scp=85052879210&partnerID=8YFLogxK

U2 - 10.2352/ISSN.2470-1173.2018.13.IPAS-308

DO - 10.2352/ISSN.2470-1173.2018.13.IPAS-308

M3 - Conference article

AN - SCOPUS:85052879210

SN - 2470-1173

JO - IS and T International Symposium on Electronic Imaging Science and Technology

JF - IS and T International Symposium on Electronic Imaging Science and Technology

M1 - 308

T2 - 16th Image Processing: Algorithms and Systems Symposium 2018

Y2 - 28 January 2018 through 1 February 2018

ER -

Rule-based optical character recognition for serial number on Renminbi banknote

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this