Recognition of isolated handprinted characters

Bo Martins

doi:10.1109/ICSMC.1996.565504

Recognition of isolated handprinted characters

Bo Martins

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

364 Downloads (Orbit)

Abstract

Handprinted characters are of unequal complexity and a common description of all alphabet symbols seems therefore unobtainable. However, letters which confuse human beings and man-made OCR systems usually have approximately the same appearance and may therefore be modeled jointly. We part the set of bitmaps into types, where each type has its unique feature space. The bitmaps belonging to some types are modeled independently from bitmaps belonging to other types. The feature vector of a bitmap initially constitutes a lossy representation of the contour(s) of the bitmap. The initial feature space is usually too large but can be reduced automatically by the use of a predictive code length or predictive error criterion

Original language	English
Title of host publication	Proceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume	Volume 3
Publisher	IEEE
Publication date	1996
Pages	2238-2243
ISBN (Print)	07-80-33280-6
DOIs	https://doi.org/10.1109/ICSMC.1996.565504
Publication status	Published - 1996
Event	1996 IEEE International Conference on Systems, Man and Cybernetics - Beijing, China Duration: 14 Oct 1996 → 17 Oct 1996 https://ieeexplore.ieee.org/xpl/conhome/4232/proceeding

Conference

Conference	1996 IEEE International Conference on Systems, Man and Cybernetics
Country/Territory	China
City	Beijing
Period	14/10/1996 → 17/10/1996
Internet address	https://ieeexplore.ieee.org/xpl/conhome/4232/proceeding

Bibliographical note

Copyright 1996 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Access to Document

10.1109/ICSMC.1996.565504

BoFinal published version, 934 KB

OpenUrl availability

Full text

Cite this

@inproceedings{d0babb88b9504fab9231303e4550db1c,

title = "Recognition of isolated handprinted characters",

abstract = "Handprinted characters are of unequal complexity and a common description of all alphabet symbols seems therefore unobtainable. However, letters which confuse human beings and man-made OCR systems usually have approximately the same appearance and may therefore be modeled jointly. We part the set of bitmaps into types, where each type has its unique feature space. The bitmaps belonging to some types are modeled independently from bitmaps belonging to other types. The feature vector of a bitmap initially constitutes a lossy representation of the contour(s) of the bitmap. The initial feature space is usually too large but can be reduced automatically by the use of a predictive code length or predictive error criterion",

author = "Bo Martins",

note = "Copyright 1996 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.; 1996 IEEE International Conference on Systems, Man and Cybernetics ; Conference date: 14-10-1996 Through 17-10-1996",

year = "1996",

doi = "10.1109/ICSMC.1996.565504",

language = "English",

isbn = "07-80-33280-6",

volume = "Volume 3",

pages = "2238--2243",

booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",

publisher = "IEEE",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/4232/proceeding",

}

TY - GEN

T1 - Recognition of isolated handprinted characters

AU - Martins, Bo

N1 - Copyright 1996 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 1996

Y1 - 1996

N2 - Handprinted characters are of unequal complexity and a common description of all alphabet symbols seems therefore unobtainable. However, letters which confuse human beings and man-made OCR systems usually have approximately the same appearance and may therefore be modeled jointly. We part the set of bitmaps into types, where each type has its unique feature space. The bitmaps belonging to some types are modeled independently from bitmaps belonging to other types. The feature vector of a bitmap initially constitutes a lossy representation of the contour(s) of the bitmap. The initial feature space is usually too large but can be reduced automatically by the use of a predictive code length or predictive error criterion

AB - Handprinted characters are of unequal complexity and a common description of all alphabet symbols seems therefore unobtainable. However, letters which confuse human beings and man-made OCR systems usually have approximately the same appearance and may therefore be modeled jointly. We part the set of bitmaps into types, where each type has its unique feature space. The bitmaps belonging to some types are modeled independently from bitmaps belonging to other types. The feature vector of a bitmap initially constitutes a lossy representation of the contour(s) of the bitmap. The initial feature space is usually too large but can be reduced automatically by the use of a predictive code length or predictive error criterion

U2 - 10.1109/ICSMC.1996.565504

DO - 10.1109/ICSMC.1996.565504

M3 - Article in proceedings

SN - 07-80-33280-6

VL - Volume 3

SP - 2238

EP - 2243

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

PB - IEEE

T2 - 1996 IEEE International Conference on Systems, Man and Cybernetics

Y2 - 14 October 1996 through 17 October 1996

ER -

Recognition of isolated handprinted characters

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this