EN 14603:2004

SLOVENSKI STANDARD
01-april-2005
,QIRUPDFLMVNDWHKQRORJLMD±$OIDQXPHULþQLQDERUVOLNRYQLK]QDNRY]DRSWLþQR
UD]SR]QDYR]QDNRY2&5%±2EOLNHLQPHUHWLVNDQHVOLNH
Information technology - Alphanumeric glyph image set for optical character recognition
OCR-B - Shapes and dimensions of the printed image
Informationstechnik - Alphanumerischer Bildzeichensatz für optische Zeichenerkennung
OCR-B - Formen und Abmessungen des gedruckten Bildes
Technologies de l'information - Jeu d'images de glyphe alphanumérique pour la
reconnaissance optique de caracteres OCR-B - Formes et dimensions de l'image
imprimée
Ta slovenski standard je istoveten z: EN 14603:2004
ICS:
35.040 Nabori znakov in kodiranje Character sets and
informacij information coding
2003-01.Slovenski inštitut za standardizacijo. Razmnoževanje celote ali delov tega standarda ni dovoljeno.

EUROPEAN STANDARD
EN 14603
NORME EUROPÉENNE
EUROPÄISCHE NORM
December 2004
ICS
English version
Information technology - Alphanumeric glyph image set for
optical character recognition OCR-B - Shapes and dimensions
of the printed image
Technologies de l'information - Jeu d'images de glyphe
alphanumérique pour la reconnaissance optique de
caractères OCR-B - Formes et dimensions de l'image
imprimée
This European Standard was approved by CEN on 17 June 2004.
CEN members are bound to comply with the CEN/CENELEC Internal Regulations which stipulate the conditions for giving this European
Standard the status of a national standard without any alteration. Up-to-date lists and bibliographical references concerning such national
standards may be obtained on application to the Central Secretariat or to any CEN member.
This European Standard exists in three official versions (English, French, German). A version in any other language made by translation
under the responsibility of a CEN member into its own language and notified to the Central Secretariat has the same status as the official
versions.
CEN members are the national standards bodies of Austria, Belgium, Cyprus, Czech Republic, Denmark, Estonia, Finland, France,
Germany, Greece, Hungary, Iceland, Ireland, Italy, Latvia, Lithuania, Luxembourg, Malta, Netherlands, Norway, Poland, Portugal, Slovakia,
Slovenia, Spain, Sweden, Switzerland and United Kingdom.
EUROPEAN COMMITTEE FOR STANDARDIZATION
COMITÉ EUROPÉEN DE NORMALISATION
EUROPÄISCHES KOMITEE FÜR NORMUNG
Management Centre: rue de Stassart, 36  B-1050 Brussels
© 2004 CEN All rights of exploitation in any form and by any means reserved Ref. No. EN 14603:2004: E
worldwide for CEN national Members.

Foreword
This document (EN 14603:2004) has been prepared by Technical Committee CEN/TC 304,
"Information and communication technologies – European localization requirements”, the
secretariat of which is held by SIS.

This European Standard shall be given the status of a national standard, either by publication of
an identical text or by endorsement, at the latest by June 2005, and conflicting national standards
shall be withdrawn at the latest by June 2005.

The document is based on the International Standard ISO 1073/ll, “Alphanumeric character set
for optical recognition – Part ll: Character set OCR-B – Shapes and dimensions of the printed
image”.
According to the CEN/CENELEC Internal Regulations, the national standards organizations of the
following countries are bound to implement this European Standard: Austria, Belgium, Cyprus,
Czech Republic, Denmark, Estonia, Finland, France, Germany, Greece, Hungary, Iceland,
Ireland, Italy, Latvia, Lithuania, Luxembourg, Malta, Netherlands, Norway, Poland, Portugal,
Slovakia, Slovenia, Spain, Sweden, Switzerland and United Kingdom.
Contents
1 Scope .5
2 Conformance.5
3 Normative references.5
4 Terms and definitions .5
5 Coding in OCR applications.6
6 OCR-B styles.6
7 OCR-B sizes .6
8 Typical dimensions of the nominal printed image.7
9 OCR-B glyph image set.8
9.1 Subset 1: Minimal alphanumeric subset.8
9.2 Subset 2: Basic alphanumeric subset.8
9.3 Subset 3: Extended alphanumeric subset .9
9.4 Subset 4: Options subset .9
10 Index table.10
10.1 Availability of glyph images .10
10.2 Identification of drawings .10
10.3 Application considerations .10
11 Use of diacritical marks .18
11.1 Diacritical mark repertoire.18
11.2 Composite glyph images .18
11.3 Rules for glyph image combinations .18
12 Use of the LOW LINE glyph .19
13 SPACE .19
14 Glyph image shape definitions .19
14.1 Reference drawings .19
14.2 Availability of duplicates .19
14.3 Type dimensions .19
14.4 Constant-strokewidth font, size I.19
14.5 Constant-strokewidth font, size III.20
14.6 Constant-strokewidth font, size IV.20
14.7 Letterpress font, size I .20
15 Printing the letterpress and constant-strokewidth fonts .20
16 Illustration of OCR-B .20
Annex A (normative) Definition of Euro sign glyph image (ISO/IEC 9541-3 syntax) .22
Annex B (informative) Main differences between ISO 1073/II-1976 and this European Standard .23
Annex C (informative) Notes on the implementation of OCR-B .24
Annex D (informative) Glyph-repertoire extension needs identified in JTC 1/SC 2 revision process .25
Annex E (informative) Illustrations of reference drawings .29
Annex F (informative) Availability of reference drawings.32
Bibliography.33
Introduction
Optical Character Recognition technology, OCR, came into use in the 1960s, and some specialized OCR fonts
were designed at the time. In 1976 two such fonts were formally standardized by ISO, designated OCR-A and
OCR-B, in the standard ISO 1073 parts I and II, respectively.
ISO 1073 was developed by the ISO Technical Committee ISO/TC97, Computers and information processing. At
the creation of ISO/IEC JTC 1, responsibility for ISO 1073 was transferred to JTC 1/SC 2, Coded character sets.
In order to enlarge the set of characters covered by the standard, especially with special letters used in European-
origin languages, a revision of the standard was initiated in 1994 by JTC 1/SC 2, and progressed through three
consecutive Committee Drafts. Since however testing of the proposed character set extensions could not be ac-
complished, the JTC 1/SC 2 revision was discontinued in 1999.
With the introduction of the Euro sign a need – primarily European – to add that character to the OCR-B set was
recognized. CEN/TC304 therefore decided to develop an OCR-B glyph image shape for the character, verify its
recognition properties, and include it in a European version of the OCR-B standard; see CEN/TC304 reports refer-
enced in the Bibliography. The decided-on glyph image shape is specified in Annex A.
For reasons of continuity, and also to facilitate possible future CEN – ISO/IEC cooperation on OCR-B, it was de-
cided to use the current ISO text with only the necessary minimum of changes as a basis for the CEN standard,
even though the ISO text was developed in an OCR-technology situation rather different from the one existing
when this CEN standard is published. In particular, the ISO standard text's division into clauses was kept as far as
possible, although some restructuring might have been desirable.
A description of the main differences between this European Standard and ISO 1073/II is given in Annex B. Gen-
eral information on the implementation of the OCR-B shapes, taken from ISO 1073/II, has been included in An-
nex C.
In connection with the verification of the recognition properties of the Euro sign, some limited verification was also
done on special letters identified during the JTC 1/SC 2 revision work as needed in OCR-B. The extent of this veri-
fication is not sufficient for the inclusion of the letters in the OCR-B repertoire at present, but the issue is described
in Annex D, as a basis for possible future inclusion work.
Printed images produced by an OCR-B printing device
1 Scope
are in conformance with this standard if their nominal
shapes and dimensions are in accordance with their
This European Standard defines a set of glyph im-
respective reference drawing(s) and, in the case of the
ages designated OCR-B, intended primarily for use
Euro sign glyph image, with Annex A (see clause 14);
in Optical Character Recognition (OCR) appli-
with the claimed conformance to tolerances and printing
cations, but suitable also for visual, i.e. human,
quality factors specified in standard ISO 1831 consid-
reading. It does not relate any coding scheme with
ered.
these images (see clause 5).
This European Standard is based on the ISO stan-
dard 1073 part II. It differs from that standard in
3 Normative references
extending normatively the set of glyph images with
the Euro currency sign; but also in deleting some
This European Standard incorporates by dated or un-
glyphs not relevant in present-day OCR processing.
dated reference, provisions from other publications.
It further adds information on a number of glyph im-
These normative references are cited at the appropriate
ages corresponding to characters specific to some
places in the text and the publications are listed here-
European-origin languages.
after. For dated references, subsequent amendments to
or revisions of any of these publications apply to this
NOTE In ISO 1073 Part II the term "character" is
European Standard only when incorporated in it by
used not only in its strict sense, but also to mean the
amendment or revision. For undated references the lat-
printed images used for their visual, i.e. printed, repre-
est edition of the publication referred to applies.
sentations. In this European Standard the term "glyph
image" is used in the latter sense.
ISO 1831-1980, Printing specifications for optical char-
acter recognition.
This European Standard contains information on
nominal dimensions for the glyph images. Toler-
ISO/IEC 9541-3:1994, Information technology — Font
ances, printing quality and other characteristics of
information interchange — Part 3: Glyph shape
...