EP1918104A2 - Procédé destiné à la vérification d'une impression et dispositif de vérification d'impression - Google Patents

Procédé destiné à la vérification d'une impression et dispositif de vérification d'impression Download PDF

Info

Publication number
EP1918104A2
EP1918104A2 EP07118691A EP07118691A EP1918104A2 EP 1918104 A2 EP1918104 A2 EP 1918104A2 EP 07118691 A EP07118691 A EP 07118691A EP 07118691 A EP07118691 A EP 07118691A EP 1918104 A2 EP1918104 A2 EP 1918104A2
Authority
EP
European Patent Office
Prior art keywords
data code
data
imprint
acceptable
record
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP07118691A
Other languages
German (de)
English (en)
Other versions
EP1918104A3 (fr
Inventor
Udo Miletzki
Ingolf Rauh
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Original Assignee
Siemens AG
Siemens Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens AG, Siemens Corp filed Critical Siemens AG
Publication of EP1918104A2 publication Critical patent/EP1918104A2/fr
Publication of EP1918104A3 publication Critical patent/EP1918104A3/fr
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B41—PRINTING; LINING MACHINES; TYPEWRITERS; STAMPS
    • B41F—PRINTING MACHINES OR PRESSES
    • B41F33/00—Indicating, counting, warning, control or safety devices
    • B41F33/0036—Devices for scanning or checking the printed matter for quality control

Definitions

  • the invention relates to a method for checking an imprint, in which an imprint is read and from which a data code is formed and the data code is compared with a number of check data codes in a stored data record.
  • the invention relates to a Aufticianprüfvorraum with a reader for scanning an imprint, a memory with at least one stored record with a number of educables and a computing unit for forming a data code from the imprint and comparing the data code with at least one educable.
  • the object of the method is solved by a method of checking an input of the type mentioned in which, when the data code is found in the data set, it is decided whether the data code is classified as acceptable or unacceptably defective. Acceptable faulty printouts can be handled without rejection, and rejection can be restricted to content-falsifying errors and unknown bugs.
  • the invention is based on the consideration that a content-based error detection can be performed reliably if known, concrete errors are already classified as acceptable or unacceptable. These known errors can be written as individual test data codes in the data set and the data code can be compared with these known test data codes in terms of content. If a match of a data code with one of the test data codes is detected, it can be decided based on the error thus identified whether the error in the data code is acceptable or not. Any error considered acceptable therefore no longer needs to be rejected or submitted to a decision maker, such as an examiner. A rejection rate can thereby be kept low, while the test result is not affected, since only known acceptable errors pass through the test system and unknown and unacceptable known errors continue to be rejected or rejected.
  • An imprint can be any character-like information applied to an article, in particular a label, wherein the character-like information preferably comprises characters to be read by persons, in particular alphanumeric characters, that is to say letters and numbers.
  • the data code and check data code may be any machine-readable code representing the character-like information.
  • the data code comprises a string of characters.
  • the data format of the test data codes is expediently that of the data code to be tested.
  • the finding of the data code in the data record can be done by finding a test data code in the data record which matches the data code or is similar to it to a predetermined extent.
  • the data record has a list with acceptable and a list of unacceptably incorrect test data codes, wherein the decision is made depending on in which of the lists the data code is found.
  • the list of acceptable check data codes may include a template code or target data code that represents the print template.
  • a further advantageous embodiment of the invention provides that a predetermined deviation of the data code from a test data code of the data record is permitted for finding the data code in the data record.
  • a deviation of the data code from the next check data code can be quantitatively detected, e.g. as Levenshtein distance, and in case of falling below a predetermined limit deviation, the assignment of the data code to the strigskycode done. If in this way a variant of a character set of the imprint is found in the list of acceptable test data codes with very high reliability according to the deviation algorithm used, the imprint is deemed to be acceptable. In this way, a rate of tolerable errors can be further reduced.
  • the deviation may be a distance between data codes.
  • the data record has a list with at least one test data code which contains a placeholder, that is to say a character which allows any character. If any character in the place of the wildcard would lead to a rejection or acceptance of the data code, then the corresponding list can be kept short and a comparison process fast.
  • the permitted deviation depends on whether the test data code is classified as acceptable or unacceptable. It is possible to differentiate between important and unimportant information, or between easily understandable and easily understandable information, and to adjust the deviation accordingly. For example, while an important and slightly ambiguous text may have some acceptable variations, further deviations from the variations must be rejected as unacceptable despite high similarity to the acceptable variations. In this case, the deviation can be set very small, so that the risk of erroneous assignment of a data code to a sensitive acceptable test data code is low.
  • the data set can be created simply and comprehensively if the data code is not output for checking by a decision maker if no matching test data code is found in the data record.
  • a check of a type of labels without test data codes or only with the desired data code, which corresponds exactly to the print original can begin in the data record.
  • the decider for example to a person, by optical output, eg on a screen.
  • the decision maker decides whether the information which the data record reproduces, for example a character string, is understandable in the sense of the print template and classifies the data code accordingly.
  • a decision of the decider recorded in the record can be stored accordingly as a test data code, for example in one of the two lists.
  • the record can be maintained, so that an issue of unknown data codes to the decision maker is becoming increasingly rare.
  • the decision maker is expediently a person, wherein a calculation unit is also conceivable which checks the sense of the print according to predetermined semantic algorithms.
  • the error rate of the proof test can be further reduced if the imprint is divided into tolerance-tolerant and intolerant information and the data code is treated differently depending on its affiliation to the tolerant or intolerant information. Affiliation can be determined from the location of a string within the expression without having to read the string character by character. In this way, e.g. for fault-tolerant information greater deviations than for important or easily misunderstood information are allowed.
  • a data code associated with the intolerant information must completely match a target data code to be classified as accepted.
  • the target data code preferably corresponds to the print template. Data that does not permit any deviations, such as patient numbers or expiration dates, can be checked very critically, without minor errors in the remaining print leading to a large number of rejections. For this purpose, deviations from a desired data code are advantageously permitted for a data code which has been assigned to the tolerant information in order to classify the data code as accepted.
  • the object directed to the Aufdruckprüfvortechnisch is achieved by a Auftikprüfvortechnisch of the type mentioned, in which the arithmetic unit is prepared according to the invention, in finding the data code in the record to decide if the data code is classified as acceptable or unacceptably flawed.
  • a rejection rate can be kept low and unacceptable errors can be detected with high reliability.
  • FIG. 1 shows, in addition to a printing inspection device 2, a schematically illustrated design system 4 for labels, for example for such a label 6, as shown in FIG.
  • a print 8 is designed and written coded into a description file.
  • the description file is transmitted to a printer 10, which prints the label 6.
  • the label 6 is fed to the printing inspection device 2, which moves the label 6 with a transport device 12 into a receiving region of a reading device 14.
  • the arithmetic unit 20 has access to a data memory 22 in which a print template 24 with a number of desired data codes 26 in the form of a description file 28 is stored by the design system 4.
  • the data memory 22 comprises two lists 30, 32 with check data codes to which the arithmetic unit 20 also has access.
  • An output unit 34 in the form of a screen is used to output by data codes 38, 40 (FIG 3) reproduced parts of the imprint 8 to a test person.
  • the imprint 8 shown in FIG. 2 on the label 6 has a number of character strings which, together with the positions of the character strings, are respectively stored in the description file 28 as a setpoint data code 26.
  • a character string here consists of an entire line, one or more words or a number of the imprint 8.
  • Each of the setpoint data codes 26 also represents a checkdata code 44, 46, 48, 50, of which only four checkdata codes 44 are shown in FIG. 2 for the sake of clarity. 46, 48, 50 are marked as such.
  • the test data code 48 is data representing the character string "For clinical evaluation.”
  • the imprint 8 is divided into tolerant, medium tolerant and intolerant information such that each of the desired data codes 26 is associated with one of these pieces of information. This classification is also included in the description file 28.
  • the test data code 48 is associated, for example, with medium-tolerant information.
  • FIG. 3 shows an imprint 52 which has smaller and larger imperfections.
  • the imprint 52 is read by the reading device 14, and from the image 16 of the arithmetic unit 20 many data codes 36-42 obtained, of which for clarity, only four are marked.
  • Each data code 36-42 is then compared by the arithmetic unit 20 with the corresponding test data code 44-50. This is first clarified on the basis of the data code 40.
  • the arithmetic unit 20 comprises an OCR component which reads the text from the image 16 of the imprint 52 character by character and forms the data code 40 from the character string thus read.
  • the string is "Intended for Clinical Examination, where the first word was incorrectly deciphered because of a small spot of ink and the last two characters of the last word could be recognized but not deciphered.”
  • This data code 40 becomes test data code 48 compared, for example word by word. First, the word “clinch” is not equal to the word “clinical” in the test data code 48.
  • the arithmetic unit 20 now checks whether there is the string “clinch” in one of the lists 30, 32 as a variation of the character string "clinical". This is initially not the case.
  • the arithmetic unit 20 therefore outputs either the entire text corresponding to the data code 40 or only "ripples" on the output unit 34.
  • the test person now decides into which of the lists 30, 32 a new test data code is to be inserted as a variation of the test data code 48 "For clinical examination” with the word “clinch”. Since the correct word “clinical” results readily from the context of the sentence, a new check data code 54 is inserted into the positive list 30, which is shown schematically in FIG. This list 30 now contains, in addition to the correct sentence entry "clinical", the additional entry "clinch” or in each case the entire sentence.
  • the arithmetic unit 20 proceeds with the word "determin ..”, which the decider also classified as recognizable and thus acceptable. Since he considers the last two letters unnecessary, he gives the word “determinate?” with a wildcard for a character and "bestim *" with a wildcard for indefinitely many characters in the 30 list.
  • the arithmetic unit 20 finds, for example, the test data code 54 which identifies "clinically” as acceptable and classifies it the corresponding erroneous data code as acceptable.
  • the arithmetic unit 20 again moves accordingly, whereby the decider considers the character string, which the OCR unit has deciphered as "Oiaio ingestion according to the test plan", incomprehensible and the word "Oiaio" - or the whole sentence which is not comprehensible - in the negative list 32 inserts.
  • the corresponding new test data code 56 can now are found by the arithmetic unit 20 and assigned to the data code 38, which is thereby classified as unacceptably defective. The label 6 is therefore rejected solely because of this error.
  • the check data code 44 is classified in the description file 28 as intolerant information and therefore does not allow errors. However, the corresponding information of the imprint 52 was erroneously read as "12346" and the data code 36 was created accordingly. In the positive list 30 only "12345” is noted, whereas in the negative list it is noted that any other character string is unacceptable. The label 6 is therefore rejected as unacceptable, also because of this error in the imprint 52.
  • the text "PHARMA" of the data set 42 can not be deciphered because of an incomplete pressure. however, the check data code 50 is marked as tolerant information, and in the list 30 it is noted that any characters are acceptable. Therefore, the record 42 is classified as acceptable.
  • the information on the imprint 52 is also treated differently with respect to character recognition.
  • intolerant information to which test data code 44 belongs a character must be deciphered with a very high probability to be considered decoded. Here are therefore high demands on the pressure.
  • moderately tolerant and intolerant information an average or even lower probability of deciphering is sufficient, so that the pressure requirements are lower or lower.
  • the probability also depends on whether the deciphered data code 36-42 is acceptable or not. If a deciphered data code 40, 42 classified as acceptable, for example, it can be checked whether the deciphering probability is above a predetermined value, the is higher than an unacceptable data code 36, 38. If not, the data code 40, 42 can still be rejected.
  • FIG. 1 A flowchart of a method for checking the imprint 52 is shown in FIG.
  • the imprint 52 is read 58 by the reader, deciphered as a string, and formed into a data code 36-42.
  • a comparison 60 of the data code 36-42 with the lists 30, 32 is made on the basis of the prescribed positions in the description file 28.
  • the positive list 30 is searched. If this test 62 is successful, ie if the data code 42 is found in the positive list 30, the data code 42 is classified as acceptable. It is then checked 64 whether all the data codes 36-42 of the imprint 52 have been checked. If this is not the case, a next data code 36-42 is compared 60.
  • an imprint comprises only a single data code, so that the test 64 is omitted.
  • the next label, document, receipt or the like is transported 66 to the reading device 14 and read 58.
  • the test 68 If it is determined in the test 62 that the data code 36-40 can not be found in the positive list 30, it is now checked 68 whether it can be found in the negative list 32. If this is the case, the label 6 is rejected for an exchange 70 and the next label is transported to the reading device 14 66 and read 58. If the test 68 also fails, the data code 38, 40 is therefore not in any of the lists 30, 32, it is issued to the decider 72. It decides 74 whether the data code 38, 40 is classified as acceptable or unacceptable. If the data code 40 is acceptable, it is written 76 into the positive list 30 and the check 64 is made to see if all the data codes 36-42 have been checked. If the data code 38 is unacceptable, it is written 78 into the negative list 32 and the tag 6 is discarded 70.

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Character Discrimination (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Techniques For Improving Reliability Of Storages (AREA)
  • Accessory Devices And Overall Control Thereof (AREA)
EP07118691A 2006-10-25 2007-10-17 Procédé destiné à la vérification d'une impression et dispositif de vérification d'impression Withdrawn EP1918104A3 (fr)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
DE102006050347A DE102006050347A1 (de) 2006-10-25 2006-10-25 Verfahren zum Prüfen eines Aufdrucks und Aufdruckprüfvorrichtung

Publications (2)

Publication Number Publication Date
EP1918104A2 true EP1918104A2 (fr) 2008-05-07
EP1918104A3 EP1918104A3 (fr) 2010-06-23

Family

ID=39203137

Family Applications (1)

Application Number Title Priority Date Filing Date
EP07118691A Withdrawn EP1918104A3 (fr) 2006-10-25 2007-10-17 Procédé destiné à la vérification d'une impression et dispositif de vérification d'impression

Country Status (3)

Country Link
US (1) US8170290B2 (fr)
EP (1) EP1918104A3 (fr)
DE (1) DE102006050347A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102020109152A1 (de) 2020-04-02 2021-10-07 Koenig & Bauer Ag Verfahren zum Ermitteln eines von einem Farbregelsystem einer Druckmaschine zur Farbregelung zu verwendenden Druckkontrollstreifens

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6162085B2 (ja) 2014-08-27 2017-07-12 富士フイルム株式会社 印刷物の検査装置、検査方法及びプログラム
US10606536B2 (en) 2018-08-17 2020-03-31 Bank Of America Corporation Intelligent systematic physical document fulfillment system
US11087323B2 (en) 2018-08-21 2021-08-10 Bank Of America Corporation Exposure based secure access system
US11025641B2 (en) 2018-08-21 2021-06-01 Bank Of America Corporation System for optimizing access control for server privilege
US11361330B2 (en) 2018-08-22 2022-06-14 Bank Of America Corporation Pattern analytics system for document presentment and fulfillment
US10929076B2 (en) 2019-06-20 2021-02-23 International Business Machines Corporation Automatic scaling for legibility

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0981114A1 (fr) 1998-07-24 2000-02-23 G. D Societa per Azioni Procédé et dispositif pour valider des billets de banque
DE10157959A1 (de) 2000-11-27 2002-10-24 Omron Tateisi Electronics Co Vorrichtung und Verfahren zur Prüfung von Bildern
WO2005025872A1 (fr) 2003-09-12 2005-03-24 Eyec Gmbh Procede et dispositif pour controler des resultats d'impression

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0916598A (ja) * 1995-07-03 1997-01-17 Fujitsu Ltd エラー・パターンを用いた文字列修正システムおよび方法
JP3689455B2 (ja) 1995-07-03 2005-08-31 キヤノン株式会社 情報処理方法及び装置
US6272245B1 (en) * 1998-01-23 2001-08-07 Seiko Epson Corporation Apparatus and method for pattern recognition
DE19820353C2 (de) * 1998-05-07 2001-06-13 Ibm Verfahren und Vorrichtung zur Erkennung eines Musters auf einer Vorlage
JP3541731B2 (ja) * 1999-06-18 2004-07-14 株式会社デンソー 偽造判定方法、偽造判定装置及び記録媒体
US6778684B1 (en) * 2000-01-20 2004-08-17 Xerox Corporation Systems and methods for checking image/document quality
GB0313002D0 (en) * 2003-06-06 2003-07-09 Ncr Int Inc Currency validation
DE10361543A1 (de) * 2003-09-12 2005-04-14 Eyec Gmbh Verfahren und Vorrichtung zum Prüfen von Druckergebnissen
DE102006012513A1 (de) 2006-03-18 2007-09-20 Man Roland Druckmaschinen Ag Bildverarbeitungssystem für eine Druckmaschine
US7920714B2 (en) * 2006-07-31 2011-04-05 Canadian Bank Note Company, Limited Method and apparatus for comparing document features using texture analysis

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0981114A1 (fr) 1998-07-24 2000-02-23 G. D Societa per Azioni Procédé et dispositif pour valider des billets de banque
DE10157959A1 (de) 2000-11-27 2002-10-24 Omron Tateisi Electronics Co Vorrichtung und Verfahren zur Prüfung von Bildern
WO2005025872A1 (fr) 2003-09-12 2005-03-24 Eyec Gmbh Procede et dispositif pour controler des resultats d'impression

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102020109152A1 (de) 2020-04-02 2021-10-07 Koenig & Bauer Ag Verfahren zum Ermitteln eines von einem Farbregelsystem einer Druckmaschine zur Farbregelung zu verwendenden Druckkontrollstreifens

Also Published As

Publication number Publication date
US20080101679A1 (en) 2008-05-01
EP1918104A3 (fr) 2010-06-23
US8170290B2 (en) 2012-05-01
DE102006050347A1 (de) 2008-04-30

Similar Documents

Publication Publication Date Title
DE10342594B4 (de) Verfahren und System zum Erfassen von Daten aus mehreren maschinell lesbaren Dokumenten
DE69421255T2 (de) Dokumentkopierabwehrverfahren
DE69331456T2 (de) Überprüfbare optische Zeichenerkennung
EP0980293B1 (fr) Procede et dispositif de reconnaissance d'information de distribution de courrier
EP2463101B1 (fr) Système et procédé de production et d'inspection d'impressions dotés de contenus statiques et variables
EP1918104A2 (fr) Procédé destiné à la vérification d'une impression et dispositif de vérification d'impression
EP3205411B1 (fr) Procede de tri de bagages et systeme de tri de bagages
EP4258160A1 (fr) Lecture de codes optiques
DE10224749B4 (de) Verfahren und Vorrichtung zum Handhaben von Kunststoffkarten
DE2435889B2 (de) Verfahren und einrichtung zur unterscheidung von zeichengruppen
EP1502233B1 (fr) Procede et dispositif pour preparer un support de carte pour une jonction avec une carte
EP1844865B1 (fr) Marquage électronique pour le tri d'objets individuels, fabriqués et vérifiés en groupement d'objets
DE4407998C2 (de) Verfahren und Vorrichtung zur Erkennung eines Musters auf einem Beleg
EP2259210A2 (fr) Procédé et dispositif destinés à l'analyse d'une base de données
DE102004030415A1 (de) Verfahren zur automatischen Ermittlung operativer Leistungsdaten von Lesesystemen
EP4070294B1 (fr) Dispositif et procédé pour traiter des documents de valeur, plus particulièrement des billets de banque, et système de traitement de documents de valeur
DE2333202A1 (de) Zeichenerkennungsanordnung
EP0618544B1 (fr) Méthode et appareil pour acquérir et reconnaítre automatiquement des écritures
EP1229483B1 (fr) Méthode et appareil pour lire des adresses d'envoi avec codes postaux
DE102020120962B4 (de) Erkennungsverfahren und Erkennungssystem zum eindeutigen Erkennen eines Objekts
DE102005040662A1 (de) Verfahren zur Identifizierung von zu sortierenden Sendungen
DE102024115141A1 (de) Computerimplementiertes Verfahren, Vorrichtung und Anlage zum Verifizieren mindestens einer auf mindestens einem Objekt angebrachten Zeichenfolge
EP4726673A1 (fr) Procédé d'anonymisation de données relatives à des personnes
DE102004053562B4 (de) Verfahren und Vorrichtung zur Bereitstellung von Kartenrohlingen
DE102023131723A1 (de) Verfahren zum automatischen Ermitteln, Erstellen, Ausdrucken und Nachweisen von Umweltplaketten

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU LV MC MT NL PL PT RO SE SI SK TR

AX Request for extension of the european patent

Extension state: AL BA HR MK RS

PUAL Search report despatched

Free format text: ORIGINAL CODE: 0009013

AK Designated contracting states

Kind code of ref document: A3

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU LV MC MT NL PL PT RO SE SI SK TR

AX Request for extension of the european patent

Extension state: AL BA HR MK RS

17P Request for examination filed

Effective date: 20101018

AKX Designation fees paid

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU LV MC MT NL PL PT RO SE SI SK TR

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: SIEMENS AKTIENGESELLSCHAFT

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20130503