1、I ANSI INCITS 93M-I 981 (R2000) (formerly ANSI X3.93M-1981 (R2000) for Optical Character Recognition (OCR) Character Positioning Developed by Where IT all begins Approval of an American National Standard requires review by ANSI that the requirements for due process, consensus, and other criteria for
2、 approval have been met by the standards developer. Consensus is established when, in the judgment of the ANSI Board of Standards Review, substantial agreement has been reached by directly and materially affected interests. Substantial agreement means much more than a simple majority, but not necess
3、arily unanimity. Consensus requires that all views and objections be considered, and that a concerted effort be made toward their resolution. The use of American National Standards is completely voluntary; their existence does not in any respect preclude anyone, whether he has approved the standards
4、 or not, from manufacturing, marketing, purchasing, or using products, processes, or procedures not conforming to the standards. The American National Standards Institute does not develop standards and will in no circumstances give an interpretation of any American National Standard. Moreover, no pe
5、rson shall have the right or authority to issue an interpretation of an American National Standard in the name of the American National Standards Institute. Requests for interpretations should be addressed to the secretariat or sponsor whose name appears on the title page of this standard. CAUTION N
6、OTICE: This American National Standard may be revised or withdrawn at any time. The procedures of the American National Standards Institute require that action be taken periodically to reaffirm, revise, or withdraw this standard. Purchasers of American National Standards may receive current informat
7、ion on all standards by calling or writing the American National Standards Institute. American National Published by American National Standards Institute 11 West 42nd Street, New York, New York 10036 Copyright O1 981 by Information Technology Industry Council (ITI) All rights reserved. No part of t
8、his publication may be reproduced in any form, in an electronic retrieval system or otherwise, without prior written permission of ITI, 1250 Eye Street NW, Washington, DC 20005. Printed in the United States of America ANSI 63 X3.93M- 198 1 American National Standard for Optical Character Recognition
9、 (OCR) Character Position ng Secretariat -Computer and Business Equipment Manufacturers Association Approved May 29, 1981 American National Standards Institute, Inc (This Foreword is not a part of American National Standard for Optical Character Recognition (OCR) Charac- ter Positioning, ANSI X3.93M
10、- 198 1 .) F0 reword This standard is the result of a recognized need to have separate documents for character shapes, character positioning, print quality, inks, and paper (see Section 5 of this standard). The material contained in this standard is taken from the text and appendix of American Na- t
11、ional Standard Character Set and Print Quality for Optical Character Recognition (OCR-A), ANSI X3.17-1977. This material was omitted from the revised edition, American National Stan- dard Character Set for Optical Character Recognition (OCR-A), ANSI X3.17-198 1, which covers character shapes and siz
12、es only. The character positioning requirements in this standard apply to the constant stroke-width OCR-B characters specified in American National Standard Character Set for Optical Character Recognition (OCR-B), ANSI X3.49-1975, as well as the OCR-A characters. It is recommended that machine-print
13、ed OCR fonts conform to this standard. Fonts with special character positioning requirements shall be treated on an individual basis. Suggestions for improvement of this standard will be welcome. They should be sent to the Ameri- can National Standards Institute, 1430 Broadway, New York, N.Y. 10018.
14、 This standard was processed and approved for submittal to ANSI by American National Standards Committee on Information Processing, X3. Committee approval of the standard does not neces- sarily imply that all committee members voted for its approval. At the time it approved this standard, the X3 Com
15、mittee had the following members. John F. Auwaerter, Chairman J. P. Ancona, Vice-chairman John A. N. Lee, Vice-chairman Catherine A. Kachurik, Administrative Secretary Organization Represented American Bankers Association . American Express Company. American Nuclear Society. . American Society for I
16、nformation Science AMP Incorporated Association for Computing Machinery. Association for Systems Management . Association of American Railroads. Association of Computer Users . Burroughs Corporation. . Computer and Communications Industry Association Control Data Corporation Data General Corporation
17、 Data Processing Management Association . A. B. Dick Company . Name of Representative Andrew Ernst Arthur Miiier (Ait) R. S. Newman Richard Hicks (Ait) Geraldine C. Main D. R. Vondy (Ait) Charles Goldstein Patrick E. Lannan C. Bri (Alt) John A. N. Lee Pat Skeiiy (Ait) Wallace R. McPherson, Jr Richar
18、d Irwin (Ait) R. A. Petrash Hillel Segai Thomas Kurihara (Ait) Michael J. Bedford Jerrold S. Foley (Ait) Norman J. Ream A. G. W. Biddle (Ait) Charles E. Cooper Keith Lucke (Ait) Anthony M. Goschaik Jit Saxena (Ait) Ardyn E. Dubnow Steve Jost (Ait) O. Northstrum Organization Represented Name of Repre
19、sentative Digital Equipment Computer Users Society. . Digital Equipment Corporation. Patricia W. White John R. Ban James Hodges (Ait) Howard Kaikow (Ait) Edison Electric Institute . S. P. Shrivastava General Services Administration William C. Rinehuls Donald J. Page (Ait) GUIDE International. Frank
20、Kirshenbaum Leland Milligan (Ait) Harris Corporation Richard Joyce Ed Younker (Ait) Hewlett-Packard. . Donald C. Loughry Honeywell Information Systems Thomas J. McNamara Eric H. clamons (Ait) Wiiliarn F. McClelland (Ait) IEEE Communications Society . Thomas A. Varetoni Robert S. Stewart (Ait) Lawren
21、ce Berkeley Laboratory . James A. Baker D. F. Stevens (Alt) Life Office Management Association. . Richard E. Ricketts James F. Foley, JI (Ait) Moore Business Forms. . D. H. Oddy National Bureau of Standards. . Robert E. Rountree James H. Bunows (Ait) National Communications System . Marshall L. Cain
22、 George W. White (Alt) National Micrographics Association. William E. Neale Frank Malabaraba (Alt) National Secretaries Association P. E. Pesce Helen Wright (Ait) NCR Corporation. Thomas W. Kern William E. Snyder (Ait) OCR Users Association. . Herbert F. Schantz C. W. Wetze1 Ohio College Library Cen
23、ter, Inc David Colombo David Penniman (Ait) Perkin-Eimer Corporation David Ellis David Saunders (Ait) Prime Computer . Winfried Burke Charles Tinkey (Ait) Printing industries of America . Michael Nolan Norman Scharpf (Ait) Recognition Equipment, Inc. Leonard J. Nunley Larry E. Resch (Ait) SHARE, Inc
24、. . Thomas B. Steel, Jr Daniel Schuster (Alt) Society of Certified Data Processors Thomas M. Kurihara Ardyn E. Dubnow (Ait) Sperryunivac. MaMnW. Bass Charies D. Card (Ait) Standard Register Company. F. V. Parenti R. R. Weeks (Ait) Telephone Group . Robert Mercer S. M. Garland (Ait) R M. Shaw (Ait) U
25、.S. Department of Agriculture. G. Kent Godwin U.S. Department of Defense. William Lht . WaldoM.Wedel Wang Laboratories, Inc. . Carl W. Schwarm Charles McComas Xerox Corporation John L. Wheeler Arthur R. Machell (Ait) IBM Corporation . Muy Anne Gray IEEE Computer Society . Herbert Hecht 3MComPanY . R
26、.C.Sdth Subcommittee X3A1 on Optical Character Recognition, which developed this standard, had the following members: G. K. Godwin, Chairman H. F. Schantz, Vice-chairman C. P. Newman, Secretary R. Aubey T. Bagg W. Billings C. Biss R. Bloss G. Brown J. Brown M. Burris K. Bye L. Cassa F. Cicha B. Dani
27、els W. Davidson J. Desautels R. Easley R. Faulkner J. Forsythe W. Foster J. Freymeyer B. Frost D. Gibson R. Green R Heathcoe E. Henrichon M. Husch W. Holmes J. Hopkins R. Ireland T. Janning W. Kirkner C. Knoedel G. Korzeniewski H. Kruser F. Lewandowski H. Lidkea J. McDonnell S. McIntosh R. Mestler J
28、. MiUer R. Monell D. Newton B. Norlund D. Oddy T. Pealier L. Richards D. Rosenberg J. Rosenblum N. Seike J. Sicard B. Smith R. Smith P. Traglia N. Weiland J. Weus B. Witty Technical responsibility for the development of this standard was assigned to X3A1 Working Group D on Print Quality, which had t
29、he following members: T. Bagg, Chairman K. Bye B. Frost D. Gibson R. Ireland J. McDonneli R. Mestler J. Muer Other persons who made technical contributions are: H. Doefler L. Fiddler M. Hogan A. Holt D. Newton T. Peaiier D. Rosenberg N. Weiland R. Reynolds P. Tragiia SECTION PAGE 6 1.1 Scope 6 Conte
30、nts . 1 . Scope. Purpose. and Application . 1.2 Purpose 6 1.3 Application . 6 . . 2 Character Positioning 6 3 . Definitions 6 3.1 Document Reference Edges . 6 3.2 PrintingArea 6 3.3 ClearArea 6 3.6 LineBoundary . 6 3.8 Characterskew . 8 3.10 Average Baseline 9 3.1 1 Character-Spacing Reference Line
31、. 3.1 2 Character Spacing . 3.13 Character Separation . 9 3.14 Adjacentcharacter Misalignment . 9 3.15 Linecharacter Misalignment 9 3.16 Linespacing . 9 3.17 Line Separation . 9 4.1 ReferenceEdge . 9 4.2 Clear Area, Printing Area, and Margin 9 4.3 Characterskew . 10 4.4 Character Spacing . 10 4.5 Mi
32、nimum Character Separation 10 4.6 Character Misalignment . 10 4.7 Linespacing . 10 4.8 Lineseparation . 11 4.9 Summary of Character Positioning Specifications 11 5 . Revision of American National Standards Referred to in This Document . 11 Tables Table 1 Minimum Margin Requirements 11 Table 2 Charac
33、ter Spacing . 11 Table 3 Maximum AdjacentCharacter Misalignment 11 Table 4 Maximum Line-Character Misalignment . 11 Table 5 Minimum Line Spacing 11 Table 6 Minimum Line Separation 11 Table 7 Summary of Character Positioning Specifications . 12 3.4 Mar.n . 6 3.5 Field 6 3.7 Character Boundary 8 3.9 C
34、haracter Baseline 8 9 9 . 4 . Character Positioning Requirements . 9 Figures Fig . 1 MarginDefinition . Fig . 2 Line Boundary Fig . 3 Character Boundaries and Character Skew Fig . 4 Line Spacing and Definition Fig . 5 Character Separation and Spacing Fig . 6 Character Misalignment . 7 7 8 8 9 10 Ame
35、rican National Standard for Optical Character Recognition (OCR) Character Positioning 1. Scope, Purpose, and Application 1.1 Scope. This standard specifies the location of OCR-A and OCR-B characters in relationship to other characters on a document or page and to reference points of the document or
36、page. 1.2 Purpose. The purpose of this standard is to estab- lish definitions and tolerances for the positioning of OCR-A and OCR-B characters that will ensure satis- factory optical recognition. 1.3 Application. This standard shall be used in con- junction with American National Standards for OCR c
37、haracter shapes and sizes (ANSI X3.17-1981 and ANSI X3.49-1975), OCR paper (ANSI X3.62-1979), and OCR inks (ANSI X3.86-1980). These standards are listed in detail in Section 5 of this standard. For most OCR systems to function reliably, each OCR character should be located and positioned so that oth
38、er OCR characters or non-OCR data cannot interfere with rec- ognition. The values in this standard are chosen on the basis that they are reasonably obtainable. Although each parameter is independently specified, a deterioration in reader performance may occur if the limits of two or more parameters
39、are approached simultaneously. Every _- effort should be made to keep well within the specified limits. It is recognized, however, that in buk printing from any device the limits will occasionally and ran- domly be exceeded. 2. Character Positioning The position of a character is as important as the
40、 shape and quality of the printed character. Character position- ing specifications (format rules) are needed to ensure that each OCR character is seen by the reading device without interference from other OCR characters or from non-OCR matter. The format rules given in this standard are the minimum
41、 requirements and may need to be supplemented by further rules for specific sys- tems, The four general conditions that must be consid- ered are: (1) The position of the character relative to the edge of the document (2) Character separation (3) Character alignment (4) Character skew 3. Definitions
42、3.1 Document Reference Edges. Document reference edges are any edges used to locate the document (see Fig. 1). 3.2 Printing Area. A printing area is a rectangle inside the clear area in which OCR characters are to be printed (see Fig. i). The sides of this rectangle should be paral- lel or perpendic
43、ular to a document reference edge. 3.3 Clear Area. A clear area is the printing area ex- tended by dimensions a, b. c, and d as shown in Fig. 1. A document may contain more than one clear area. The locations and dimensions of clear areas will be determined by individual applications and the require-
44、 ments specified in 4.2.1 and 4.2.2. This does not pre- clude the use of nonread inks. 3.4 Man. A margin is the perpendicular distance between any boundary of the printing area and the nearest document edge (see Fig. 1). 3.5 Field. A field is any group of characters on one or more lines defined as a
45、 unit of information. A line may comprise several fields. 3.6 Line Boundary. A line boundary is the smallest rectangle with sides parallel and perpendicular to the document reference edge and containing all the bound- aries of the component characters of the line (see Fig. 2). 6 7 AMERICAN NATIONAL
46、STANDARD X3.93M-1981 SKEWED CHARACTER CHARACTER OUTLINE CHARACTER BOUNDARY REFERENCE EDGE - I 1 A Fig. 3 Character Boundaries and Character Skew CHARACTER BASELINES Y - - I LOWER LINE BOUNDARY I AVERAGE BASELINE LINE LINE SEPARATION SPACING BA S ELI N E Fig. 4 Line Spacing and Defmition 3.7 Characte
47、r Boundary. A character boundary is the rectangle with sides paraiiel and Perpendicular to a document reference edge, which is drawn tangential to the character outline and contains the character completely. Skewed characters still have boundaries paraiiel or perpendicular to a document reference ed
48、ge (see Fig. 3). The character boundary is used to measure charac- ter and line separation and to determine line boundary. For the purpose of determining the boundary of the Long Vertical Mark, only the portion of the Long Vertical Mark that lies between the extensions of the uppermost and lowermost
49、 horizontal boundaries of the adjacent character(s) will be considered (see Fig. 2). 3.8 Character Skew. Character skew is the rotational deviation (4) of the printed image from its intended orientation relative to a document reference edge (see Fig. 3). 3.9 Character Baseline. The character baseline is a reference line used to specify the nominal vertical posi- tion of all characters relative to the line of type (see Fig. 4). The position of the baseline is indicated on the drawings of all characters (see ANSI X3.17-1981 or 8 AMERICAN NATIONAL STANDARD X3.93M-1981 I il BOUNDARY 8tQ Y C
