On-line recognition handwritten mathematical symbols

Xuejin Zhao; Xinyu Liu; Shengling Zheng; Baochang Pan; Yuan Y. Tang

doi:10.1109/ICDAR.1997.620585

On-line recognition handwritten mathematical symbols

Xuejin Zhao, Xinyu Liu, Shengling Zheng, Baochang Pan, Yuan Y. Tang

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

Abstract

The paper aims at online recognition of handwritten mathematical symbols. It analyses the structures of 94 opt used mathematical symbols and concludes that all of them consist of 10 basic elements. It proposes a new method of basic element ordering and reduces the number of standard symbols by extracting three primary features of mathematical symbols, namely, basic element vector, relative positions between basic elements and basic element length vector. The traditional dynamic programming method is improved by means of classifying roughly 94 mathematical symbols, considering matching and unmatching value, adding geometric restraints and solving matching problem, through improved Kohn-Munkres algorithm. Correctness rate reaches 90.52%, incorrectness rate 5.03% and refusal rate 4.45%.

Original language	English
Title of host publication	Proceedings of the Fourth International Conference on Document Analysis and Recognition
Editors	Bob Werner
Publisher	IEEE
Pages	645-648
Number of pages	4
Volume	2
ISBN (Print)	0818678984
DOIs	https://doi.org/10.1109/ICDAR.1997.620585
Publication status	Published - 18 Aug 1997
Externally published	Yes
Event	4th International Conference on Document Analysis and Recognition, ICDAR 1997 - Ulm, Germany Duration: 18 Aug 1997 → 20 Aug 1997 https://ieeexplore.ieee.org/xpl/conhome/4891/proceeding (Conference proceedings)

Conference

Conference	4th International Conference on Document Analysis and Recognition, ICDAR 1997
Country/Territory	Germany
City	Ulm
Period	18/08/97 → 20/08/97
Internet address	https://ieeexplore.ieee.org/xpl/conhome/4891/proceeding (Conference proceedings)

User-Defined Keywords

Handwriting recognition
Joining processes
Keyboards
Pattern recognition
Writing
Feature extraction
Machine intelligence
Dynamic programming
Mathematics
Tail

Access to Document

10.1109/ICDAR.1997.620585

Cite this

@inproceedings{10387cc8ce7946c981b3dbdc62822e17,

title = "On-line recognition handwritten mathematical symbols",

abstract = "The paper aims at online recognition of handwritten mathematical symbols. It analyses the structures of 94 opt used mathematical symbols and concludes that all of them consist of 10 basic elements. It proposes a new method of basic element ordering and reduces the number of standard symbols by extracting three primary features of mathematical symbols, namely, basic element vector, relative positions between basic elements and basic element length vector. The traditional dynamic programming method is improved by means of classifying roughly 94 mathematical symbols, considering matching and unmatching value, adding geometric restraints and solving matching problem, through improved Kohn-Munkres algorithm. Correctness rate reaches 90.52%, incorrectness rate 5.03% and refusal rate 4.45%.",

keywords = "Handwriting recognition, Joining processes, Keyboards, Pattern recognition, Writing, Feature extraction, Machine intelligence, Dynamic programming, Mathematics, Tail",

author = "Xuejin Zhao and Xinyu Liu and Shengling Zheng and Baochang Pan and Tang, {Yuan Y.}",

note = "Publisher copyright: {\textcopyright} 1997 by The Institute of Electrical and Electronics Engineers, Inc. All rights reserved; 4th International Conference on Document Analysis and Recognition, ICDAR 1997 ; Conference date: 18-08-1997 Through 20-08-1997",

year = "1997",

month = aug,

day = "18",

doi = "10.1109/ICDAR.1997.620585",

language = "English",

isbn = "0818678984",

volume = "2",

pages = "645--648",

editor = "Bob Werner",

booktitle = "Proceedings of the Fourth International Conference on Document Analysis and Recognition",

publisher = "IEEE",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/4891/proceeding",

}

Zhao, X, Liu, X, Zheng, S, Pan, B & Tang, YY 1997, On-line recognition handwritten mathematical symbols. in B Werner (ed.), Proceedings of the Fourth International Conference on Document Analysis and Recognition. vol. 2, 620585, IEEE, pp. 645-648, 4th International Conference on Document Analysis and Recognition, ICDAR 1997, Ulm, Germany, 18/08/97. https://doi.org/10.1109/ICDAR.1997.620585

TY - GEN

T1 - On-line recognition handwritten mathematical symbols

AU - Zhao, Xuejin

AU - Liu, Xinyu

AU - Zheng, Shengling

AU - Pan, Baochang

AU - Tang, Yuan Y.

PY - 1997/8/18

Y1 - 1997/8/18

N2 - The paper aims at online recognition of handwritten mathematical symbols. It analyses the structures of 94 opt used mathematical symbols and concludes that all of them consist of 10 basic elements. It proposes a new method of basic element ordering and reduces the number of standard symbols by extracting three primary features of mathematical symbols, namely, basic element vector, relative positions between basic elements and basic element length vector. The traditional dynamic programming method is improved by means of classifying roughly 94 mathematical symbols, considering matching and unmatching value, adding geometric restraints and solving matching problem, through improved Kohn-Munkres algorithm. Correctness rate reaches 90.52%, incorrectness rate 5.03% and refusal rate 4.45%.

AB - The paper aims at online recognition of handwritten mathematical symbols. It analyses the structures of 94 opt used mathematical symbols and concludes that all of them consist of 10 basic elements. It proposes a new method of basic element ordering and reduces the number of standard symbols by extracting three primary features of mathematical symbols, namely, basic element vector, relative positions between basic elements and basic element length vector. The traditional dynamic programming method is improved by means of classifying roughly 94 mathematical symbols, considering matching and unmatching value, adding geometric restraints and solving matching problem, through improved Kohn-Munkres algorithm. Correctness rate reaches 90.52%, incorrectness rate 5.03% and refusal rate 4.45%.

KW - Handwriting recognition

KW - Joining processes

KW - Keyboards

KW - Pattern recognition

KW - Writing

KW - Feature extraction

KW - Machine intelligence

KW - Dynamic programming

KW - Mathematics

KW - Tail

U2 - 10.1109/ICDAR.1997.620585

DO - 10.1109/ICDAR.1997.620585

M3 - Conference proceeding

SN - 0818678984

VL - 2

SP - 645

EP - 648

BT - Proceedings of the Fourth International Conference on Document Analysis and Recognition

A2 - Werner, Bob

PB - IEEE

T2 - 4th International Conference on Document Analysis and Recognition, ICDAR 1997

Y2 - 18 August 1997 through 20 August 1997

ER -

On-line recognition handwritten mathematical symbols

Abstract

Conference

User-Defined Keywords

Access to Document

Fingerprint

Cite this