EP1799359A1 - Method for sorting addressed mailings according to the destination address - Google Patents

Method for sorting addressed mailings according to the destination address

Info

Publication number
EP1799359A1
EP1799359A1 EP05785599A EP05785599A EP1799359A1 EP 1799359 A1 EP1799359 A1 EP 1799359A1 EP 05785599 A EP05785599 A EP 05785599A EP 05785599 A EP05785599 A EP 05785599A EP 1799359 A1 EP1799359 A1 EP 1799359A1
Authority
EP
European Patent Office
Prior art keywords
reading
address
processing step
results
feature
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.)
Granted
Application number
EP05785599A
Other languages
German (de)
French (fr)
Other versions
EP1799359B1 (en
Inventor
Holger Paetsch
Katja Worm
Georg Kinnemann
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
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 filed Critical Siemens AG
Priority to PL05785599T priority Critical patent/PL1799359T3/en
Publication of EP1799359A1 publication Critical patent/EP1799359A1/en
Application granted granted Critical
Publication of EP1799359B1 publication Critical patent/EP1799359B1/en
Not-in-force legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C3/00—Sorting according to destination
    • B07C3/10—Apparatus characterised by the means used for detection ofthe destination
    • B07C3/14—Apparatus characterised by the means used for detection ofthe destination using light-responsive detecting means

Definitions

  • the invention relates to a method according to the preamble of
  • the automatic sorting of postal consignments based on the destination address takes place in several processing steps.
  • the first step is to take a picture of the front of the program.
  • An automatic reading system determines the position of the address block in the image, reads it using OCR techniques and determines the required distribution information therefrom.
  • the pictures of programs that could not be read automatically are connected to a video coding station and manually coded there.
  • the distribution information is either printed directly on the item or it can be assigned from a database via a unique identification which is printed on the item. In both cases, the shipments are marked by machine-readable bar codes. Thus, in the subsequent processing steps, the once determined distribution information can be accessed. The application and reading of these barcodes requires some
  • the invention has for its object to provide a method for sorting addressed broadcasts in several Verarbei ⁇ processing steps, in which even with hardly distinguishable programs their identification without applied identifiers with the help of characteristic features for Verringe ⁇ tion of the necessary reading effort is possible.
  • the respective reading intermediate results are also stored in addition to the read destination addresses / distribution information.
  • the automatic address reader for the respective further processing step is read for reading the address of the currently to be recognized Shipment started.
  • the current intermediate reading results or reading results of the program to be identified are compared with the corresponding stored intermediate reading results or reading results of the programs of the determined feature candidates.
  • the item assigned to this feature candidate with the stored distribution information of the destination address represents the recognized item and the sorting takes place on the basis of this distribution information.
  • the automatic address reader After the start of the automatic address reader and after the determination of the address area of the destination address, this is compared with the address areas to the feature candidates. If there is a match in the required credibility with exactly one of the address areas, the assigned program is identified and the reading process is terminated. If the assignment to only one feature set is not possible, the reading of the individual characters and words and a comparison with the individual characters and words stored for the remaining feature candidates takes place. If there is agreement in the required credibility with the individual characters and words of only one feature candidate, the assigned transmission is identified and the reading process is ended. If the assignment to only one feature set is still not possible, the address interpretation is carried out, the results of which are then compared with those of the remaining feature candidates.
  • the assigned mail item is identified and the reading process is ended.
  • existing primary and secondary readers in the address readers which may be started one after the other, to perform the process described in the previous paragraph with the or the respective secondary readers in the recognition process, if still with the primary reader no automatic identification was achieved.
  • the fingerprint method includes in the first processing step after image acquisition with a camera 1 and a
  • Preprocessing 10 to create defined image ratios the steps feature extraction 2 (determination of the character- ristic features 3), determination of the distribution information in a reading process and storage of these data 3,9 including the intermediate results of the reading process in a database 4.
  • various image normalization steps 10 are performed. These include a rotational position normalization, which eliminates slight deviations in the rotational position of the transmissions, and a standardization for compensating specific camera properties. For gray images this could be a brightness normalization. This area also includes an optional binarization.
  • significant features are extracted from the preprocessed image 2.
  • Structural features histogram-based features derived from transformations (Fourier transform, cosine transform, wavelets) can be used.
  • structural features in particular features derived from the franking and the address block are used, since these are already being processed by machine.
  • For the address block e.g. As stable as possible features such as the number of lines and the decomposition of lines in words and characters are used. In a concrete application, the exact compilation of the feature vectors used will be matched to a significant sample of transmission images in order to achieve optimal detection results.
  • the destination address is then read with a primary reader 5.
  • the area of the destination address (ROI) is first determined 5.1, then the characters of the destination address are read with the OCR section 5.2 and the last step is the address interpretation with the help of an address dictionary 5.3.
  • the result is then either a read verified and unambiguous address or there was no clear result and a second read attempt is made in one second.
  • därleser 7 started with another reading software. In this case, the same processing steps take place, ie, determine ROI 7.1, read destination address 7.2, and perform address interpretation 7.3. If there is still no clear result, then a video coding is carried out. 8.
  • the characteristic feature set / feature vector 3 of the respective mail item is then located and the read results and read intermediate results 9 are assigned to it during the recognition process
  • the preprocessing 20 of the image data, the feature extraction 12.1 and the storage of the feature vector are likewise carried out after the image acquisition by means of a camera 11 for fingerprint recognition 12. Subsequently, this is compared with the feature vectors contained in the database 4 12.2, 12.3.
  • large-scale data systems use space-partitioning techniques to determine the nearest neighbors. These make it possible to quickly find both the candidates adjacent to the feature space and to efficiently manage the set of candidates currently to be considered. This aspect is of particular importance in the fingerprint method, since the reference quantity is determined by newly added broadcasts and completely processed consignments is subject to constant changes.
  • the associated distribution information 9 is assigned to the relevant item and the sorting can take place.
  • the voter 16 can in many cases already clearly select a message from the fingerprint candidates 13.
  • the video coding 18 of the still missing address parts can then be omitted.
  • the voter 16 decides on the basis of the credibility of the result of the fingerprint determination and of the results used and partial results of the reading process, whether the result has been determined sufficiently reliably. 22. If not, the complete destination address must be automatically read or video-coded. In FIG. 3, the sequence has been shown with only one primary reader each for the sake of clarity. If secondary readers are still present, the processes are also carried out accordingly for these readers.

Landscapes

  • Sorting Of Articles (AREA)
  • Character Discrimination (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

In the multistage sorting method, the mail items read in the first step are re-identified in the subsequent steps on the basis of characteristic features determined. If unambiguous assignment to a plurality of candidates is not possible, reading steps are additionally carried out in the subsequent sorting steps and the partial reading results of the candidates are compared with the corresponding partial reading results of the first steps until unambiguous assignment is produced.

Description

Beschreibungdescription
Verfahren zum Sortieren von adressierten Sendungen entspre¬ chend der ZieladresseMethod for sorting addressed broadcasts according to the destination address
Die Erfindung betrifft ein Verfahren nach dem Oberbegriff desThe invention relates to a method according to the preamble of
Anspruches 1.Claim 1.
Die automatische Sortierung von postalischen Sendungen anhand der Zieladresse erfolgt in mehreren Verarbeitungsschritten. Im ersten Schritt wird ein Bild der Vorderseite der Sendung aufgenommen. Ein automatisches Lesesystem ermittelt die Posi¬ tion des Adressblocks im Bild, liest diesen unter Verwendung von OCR-Techniken und ermittelt daraus die benötigte Verteil- information. Die Bilder von Sendungen, die automatisch nicht gelesenen werden konnten, werden an einem Videokodierplatz aufgeschaltet und dort manuell kodiert.The automatic sorting of postal consignments based on the destination address takes place in several processing steps. The first step is to take a picture of the front of the program. An automatic reading system determines the position of the address block in the image, reads it using OCR techniques and determines the required distribution information therefrom. The pictures of programs that could not be read automatically are connected to a video coding station and manually coded there.
In vielen Sortiersystemen wird die Verteilinformation entwe¬ der direkt auf die Sendung aufgedruckt oder sie kann über ei¬ ne eindeutige Identifikation, die auf die Sendung aufgedruckt wird, aus einer Datenbank zugeordnet werden. In beiden Fällen werden die Sendungen mit Hilfe von maschinenlesbaren Barkodes gekennzeichnet. So kann in den nachfolgenden Verarbeitungs- schritten auf die einmal ermittelte Verteilinformation zuge¬ griffen werden. Das Aufbringen und Lesen dieser Barkodes erfordert einigenIn many sorting systems, the distribution information is either printed directly on the item or it can be assigned from a database via a unique identification which is printed on the item. In both cases, the shipments are marked by machine-readable bar codes. Thus, in the subsequent processing steps, the once determined distribution information can be accessed. The application and reading of these barcodes requires some
Hardwareaufwand und ist wartungsintensiv. In einigen Fällen ist das Aufdrucken von Barkodes nicht möglich oder nicht ge¬ wünscht .Hardware expenditure and is maintenance-intensive. In some cases, the printing of bar codes is not possible or not desired.
Um die Sendungen auch ohne aufgebrachte Identifikationen zu erkennen, wurde ein Verfahren bekannt, das es ermöglicht, ei¬ ne Sendung anhand von aus dem Bild gewonnenen charakteristi¬ schen Merkmalen (sogenannten Fingerprints) (DE 40 00 603 C2) zu identifizieren. Um die Anwendung dieser Identifikations- technik in der Praxis zu vereinfachen, wurde ein Verfahren beschrieben, mit dem der Suchraum für die Identifikation von Sendungen deutlich eingeschränkt wird (EP 1 222 037 Bl) .In order to recognize the broadcasts even without applied identifications, a method has been disclosed which makes it possible to identify a program on the basis of characteristic features obtained from the image (so-called fingerprints) (DE 40 00 603 C2). In order to simplify the application of this identification technique in practice, a method has been developed described, with the search space for the identification of broadcasts is significantly restricted (EP 1 222 037 Bl).
Der Erfindung liegt die Aufgabe zugrunde, ein Verfahren zum Sortieren von adressierten Sendungen in mehreren Verarbei¬ tungsschritten zu schaffen, bei dem auch bei schwer unter¬ scheidbaren Sendungen ihre Identifikation ohne aufgebrachte Kennungen mit Hilfe charakteristischer Merkmale zur Verringe¬ rung des notwendigen Leseaufwandes möglich ist.The invention has for its object to provide a method for sorting addressed broadcasts in several Verarbei¬ processing steps, in which even with hardly distinguishable programs their identification without applied identifiers with the help of characteristic features for Verringe¬ tion of the necessary reading effort is possible.
Erfindungsgemäß wird die Aufgabe durch die Merkmale des An¬ spruches 1 gelöst .According to the invention, the object is achieved by the features of claim 1. An¬.
Dabei werden im ersten Verarbeitungsschritt zusammen mit den charakteristischen Merkmalen diesen zugeordnet in der Daten- bank neben den gelesenen Zieladressen/ Verteilinformationen die jeweiligen Lesezwischenergebnisse mit abgespeichert. Im Wiedererkennungsprozess eines weiteren Verarbeitungs- schrittes wird bei keiner eindeutigen Übereinstimmung in festgelegter Glaubwürdigkeit der im jeweiligen Verarbeitungs- schritt ermittelten charakteristischen Merkmale mit mehreren gespeicherten Merkmalssätzen von gefundenen Kandidaten aus dem ersten Verarbeitungsschritt der automatische Adressleser für den jeweiligen weiteren Verarbeitungsschritt zum Lesen der Adresse der aktuell wiederzuerkennenden Sendung gestar- tet.In this case, in the first processing step, together with the characteristic features assigned to them in the database, the respective reading intermediate results are also stored in addition to the read destination addresses / distribution information. In the recognition process of a further processing step, if there is no unambiguous correspondence in defined credibility of the characteristic features having a plurality of stored feature sets of found candidates from the first processing step, the automatic address reader for the respective further processing step is read for reading the address of the currently to be recognized Shipment started.
Dann werden die aktuellen Lesezwischenergebnisse oder Leseer¬ gebnisse der zu identifizierenden Sendung mit den entspre¬ chenden gespeicherten Lesezwischenergebnissen oder Leseergeb¬ nissen der Sendungen der ermittelten Merkmalskandidaten ver- glichen.Then, the current intermediate reading results or reading results of the program to be identified are compared with the corresponding stored intermediate reading results or reading results of the programs of the determined feature candidates.
Bei gefundener Übereinstimmung mit festgelegter Glaubwürdig¬ keit stellt die diesem Merkmalskandidaten zugeordnete Sendung mit der gespeicherten Verteilinformation der Zieladresse die wiedererkannte Sendung dar und die Sortierung erfolgt anhand dieser Verteilinformation.If a match with a defined credibility is found, the item assigned to this feature candidate with the stored distribution information of the destination address represents the recognized item and the sorting takes place on the basis of this distribution information.
Dadurch ist es möglich, bei mehreren möglichen Merkmalskandi- daten, zu denen keine eindeutige Auswahl eines einzigen Kan- didaten nur aufgrund der Merkmalsvergleiche möglich ist und die deshalb bisher erneut manuell kodiert werden mussten, den überwiegenden Teil automatisch zu bearbeiten.This makes it possible, in the case of several possible feature candidates, for which no unambiguous selection of a single channel didaten only because of the feature comparisons and therefore had to be re-coded manually, to process the vast majority automatically.
Vorteilhafte Ausgestaltungen der Erfindung sind in den Unter¬ ansprüchen dargelegt .Advantageous embodiments of the invention are set forth in the dependent claims.
Dabei ist es vorteilhaft, den Lese- und Vergleichsvorgang im Wiedererkennungsprozess eines weiteren Verarbeitungsschrittes stufenweise entsprechend der abfolgenden Leseschritte durch- zuführen, wobei der nachfolgende Lese- und Vergleichsschritt nur erfolgt, wenn der vorherige keine eindeutige Kandidaten¬ zuordnung ergibt. Dadurch erfolgt der Lese- und Ver¬ gleichsaufwand nur im notwendigen Umfang.In this case, it is advantageous to carry out the reading and comparing process in the recognition process of a further processing step in stages according to the subsequent reading steps, the subsequent reading and comparing step taking place only if the preceding does not result in a unique candidate assignment. As a result, the reading and Ver¬ same effort only to the extent necessary.
Hierzu ist es vorteilhaft, in folgender Reihenfolge vorzuge¬ hen:For this purpose, it is advantageous to proceed in the following order:
Nach dem Start des automatischen Adresslesers und nach der Ermittlung des Adressgebietes der Zieladresse wird dieses mit den Adressgebieten zu den Merkmalskandidaten verglichen. Bei Übereinstimmung in geforderter Glaubwürdigkeit mit genau ei¬ nem der Adressgebiete ist die zugeordnete Sendung identifi¬ ziert und der Leseprozess wird beendet. Falls die Zuordnung zu nur einem Merkmalssatz nicht möglich ist, erfolgt das Le¬ sen der Einzelzeichen und Wörter und ein Vergleich mit den zu den verbleibenden Merkmalskandidaten gespeicherten Einzelzei¬ chen und Wörtern. Bei Übereinstimmung in geforderter Glaub¬ würdigkeit mit den Einzelzeichen und Wörtern nur eines Merk¬ malskandidaten ist die zugeordnete Sendung identifiziert und der Leseprozess wird beendet. Falls die Zuordnung zu nur ei- nem Merkmalssatz immer noch nicht möglich ist, wird die Ad¬ ressinterpretation durchgeführt, deren Ergebnisse dann mit denen der verbleibenden Merkmalskandidaten verglichen werden. Bei Übereinstimmung in geforderter Glaubwürdigkeit mit den Ergebnissen der Adressinterpretation zu nur einem Merkmals- kandidaten ist die zugeordnete Sendung identifiziert und der Leseprozess wird beendet . In diesem Zusammenhang ist es vorteilhaft, bei vorhandenen Primär- und Sekundärlesern in den Adresslesern, die bei Be¬ darf nacheinander gestartet werden, beim Wiedererkennungspro- zess den im vorigen Absatz beschriebene Ablauf auch mit dem oder den jeweiligen Sekundärlesern durchzuführen, falls mit dem Primärleser noch keine automatische Identifikation er¬ reicht wurde.After the start of the automatic address reader and after the determination of the address area of the destination address, this is compared with the address areas to the feature candidates. If there is a match in the required credibility with exactly one of the address areas, the assigned program is identified and the reading process is terminated. If the assignment to only one feature set is not possible, the reading of the individual characters and words and a comparison with the individual characters and words stored for the remaining feature candidates takes place. If there is agreement in the required credibility with the individual characters and words of only one feature candidate, the assigned transmission is identified and the reading process is ended. If the assignment to only one feature set is still not possible, the address interpretation is carried out, the results of which are then compared with those of the remaining feature candidates. If the required credibility matches the results of the address interpretation to only one feature candidate, the assigned mail item is identified and the reading process is ended. In this context, it is advantageous for existing primary and secondary readers in the address readers, which may be started one after the other, to perform the process described in the previous paragraph with the or the respective secondary readers in the recognition process, if still with the primary reader no automatic identification was achieved.
Damit der benötigte Speicherbedarf begrenzt werden kann, ist es vorteilhaft, die in der Datenbank gespeicherten charakte¬ ristischen Merkmale mit den Lesezwischenergebnissen und Lese¬ ergebnissen/Verteilkodes zu löschen, wenn eine bestimmte Ver¬ fallszeit überschritten wurde oder wenn der letzte Verarbei¬ tungsschritt durchlaufen wurde.So that the required memory requirement can be limited, it is advantageous to delete the characteristic features stored in the database with the reading intermediate results and reading results / distribution codes if a certain delay time has been exceeded or if the last processing step has been run through ,
Vorteilhaft ist es auch, falls die automatische Identifikati¬ on nicht erfolgreich abgeschlossen wurde, nur die Bilder bzw. Adressalternativen der Sendungskandidaten manuell an Videoko¬ dierplätzen mittels Selektion zu kodieren und damit den Ko- dieraufwand gering zu halten.If the automatic identification has not been successfully completed, it is also advantageous to manually encode only the images or address alternatives of the mailing candidates by means of selection at video coding stations and thus to minimize the coding effort.
Anschließend wird die Erfindung in einem Ausführungsbeispiel anhand der Zeichnung erläutert .Subsequently, the invention will be explained in an embodiment with reference to the drawing.
Dabei zeigenShow
FIG 1 eine schematische Strukturdarstellung für den ersten Verarbeitungsschritt,1 shows a schematic structural representation for the first processing step,
FIG 2 eine schematische Strukturdarstellung für ei- nen weiteren Verarbeitungsschritt,2 shows a schematic structural representation for a further processing step,
FIG 3 ein Flussbild des Verfahrensablaufes.3 shows a flow chart of the procedure.
Das Fingerprint-Verfahren beinhaltet im ersten Verarbeitungs- schritt nach der Bildaufnahme mit einer Kamera 1 und einerThe fingerprint method includes in the first processing step after image acquisition with a camera 1 and a
Vorverarbeitung 10 zur Schaffung definierter Bildverhältnisse die Schritte Merkmalsextraktion 2 (Bestimmung der charakte- ristischen Merkmale 3) , Ermittlung der Verteilinformation in einem Leseprozess und Abspeicherung dieser Daten 3,9 ein¬ schließlich der Zwischenergebnisse des Leseprozesses in einer Datenbank 4. Während der Vorverarbeitung, die in FIG 3 dargestellt ist, werden verschiedene Bildnormierungsschritte 10 durchgeführt. Dazu gehören eine Drehlagenormierung, die geringfügige Abwei¬ chungen in der Drehlage der Sendungen beseitigt, und eine Normierung zum Ausgleich spezifischer Kameraeigenschaften. Bei Graubildern könnte das eine Helligkeitsnormierung sein. In diesen Bereich gehört auch eine gegebenenfalls durchge¬ führte Binarisierung.Preprocessing 10 to create defined image ratios the steps feature extraction 2 (determination of the character- ristic features 3), determination of the distribution information in a reading process and storage of these data 3,9 including the intermediate results of the reading process in a database 4. During the preprocessing, which is shown in FIG. 3, various image normalization steps 10 are performed. These include a rotational position normalization, which eliminates slight deviations in the rotational position of the transmissions, and a standardization for compensating specific camera properties. For gray images this could be a brightness normalization. This area also includes an optional binarization.
Dann werden neben globalen Merkmalen wie der Sendungsgröße signifikante Merkmale aus dem vorverarbeiteten Bild extra- hiert 2. Dabei können strukturelle Merkmale, Histogramm ba¬ sierte und aus Transformationen (Fourier-, Kosinus- Transformation, Wavelets) abgeleitete Merkmale eingesetzt werden. Als strukturelle Merkmale werden insbesondere aus der Freimachung und dem Adressblock abgeleitete Merkmale verwen- det, da diese schon jetzt maschinell verarbeitet werden. Für den Adressblock z.B. werden möglichst stabile Merkmale wie die Anzahl der Zeilen und die Zerlegung der Zeilen in Worte und Zeichen verwendet . Bei einem konkreten Einsatz wird man die exakte Zusammenstel- lung der verwendeten Merkmalsvektoren auf eine signifikante Stichprobe von Sendungsbildern abstimmen, um optimale Erken¬ nungsergebnisse zu erzielen.Then, in addition to global features such as the transmission size, significant features are extracted from the preprocessed image 2. Structural features, histogram-based features derived from transformations (Fourier transform, cosine transform, wavelets) can be used. As structural features, in particular features derived from the franking and the address block are used, since these are already being processed by machine. For the address block e.g. As stable as possible features such as the number of lines and the decomposition of lines in words and characters are used. In a concrete application, the exact compilation of the feature vectors used will be matched to a significant sample of transmission images in order to achieve optimal detection results.
Das Lesen der Zieladresse erfolgt dann mit einem Primärle¬ ser 5. Dabei wird zuerst das Gebiet der Zieladresse (ROI) er- mittelt 5.1, dann werden die Zeichen der Zieladresse mit dem OCR-Teil gelesen 5.2 und als letzter Schritt wird die Adress¬ interpretation mit Hilfe eines Adresswörterbuches durchge¬ führt 5.3. Das Ergebnis ist dann entweder eine gelesene veri¬ fizierte und eindeutige Adresse oder es gab kein eindeutiges Ergebnis und es wird ein zweiter Leseversuch in einem Sekun- därleser 7 mit einer anderen Lesesoftware gestartet . Hierbei laufen die gleichen Verarbeitungsschritte ab, d.h. ROI ermit¬ teln 7.1, Zieladresse lesen 7.2 und Durchführen der Adressin¬ terpretation 7.3. Sollte dann immer noch kein eindeutiges Er- gebnis vorliegen, so wird eine Videokodierung durchgeführt 8. Nach der Abspeicherung in der Datenbank 4 befindet sich dann der charakteristische Merkmalssatz/ Merkmalsvektor 3 der je¬ weiligen Sendung und ihm zugeordnet die Leseergebnisse und Lesezwischenergebnisse 9. Beim Wiedererkennungsprozess erfolgt ebenfalls nach der Bild¬ aufnahme mittels einer Kamera 11 zur Fingerprinterkennung 12 die Vorverarbeitung 20 der Bilddaten, die Merkmalsextrakti¬ on 12.1 und die Abspeicherung des Merkmalsvektors. Anschlie¬ ßend wird dieser mit den in der Datenbank 4 befindlichen Merkmalsvektoren verglichen 12.2,12.3. Um eine Sendung anhand eines ermittelten Merkmalsvektors/Fingerprints effizient i- dentifizieren zu können, werden bei großen Datenmengen Space Partitioning Techniken zur Ermittlung der nächsten Nachbarn eingesetzt. Diese ermöglichen es sowohl die im Merkmalsraum benachbarten Kandidaten schnell zu finden als auch die Menge der aktuell zu betrachtenden Kandidaten effizient zu verwal¬ ten. Diesem Aspekt kommt bei dem Fingerprint-Verfahren eine besondere Bedeutung zu, da die Referenzmenge durch neu hinzu¬ kommende Sendungen und vollständig bearbeitete Sendungen ständigen Änderungen unterworfen ist.The destination address is then read with a primary reader 5. The area of the destination address (ROI) is first determined 5.1, then the characters of the destination address are read with the OCR section 5.2 and the last step is the address interpretation with the help of an address dictionary 5.3. The result is then either a read verified and unambiguous address or there was no clear result and a second read attempt is made in one second. därleser 7 started with another reading software. In this case, the same processing steps take place, ie, determine ROI 7.1, read destination address 7.2, and perform address interpretation 7.3. If there is still no clear result, then a video coding is carried out. 8. After the storage in the database 4, the characteristic feature set / feature vector 3 of the respective mail item is then located and the read results and read intermediate results 9 are assigned to it during the recognition process The preprocessing 20 of the image data, the feature extraction 12.1 and the storage of the feature vector are likewise carried out after the image acquisition by means of a camera 11 for fingerprint recognition 12. Subsequently, this is compared with the feature vectors contained in the database 4 12.2, 12.3. In order to be able to identify a program efficiently on the basis of a determined feature vector / fingerprint, large-scale data systems use space-partitioning techniques to determine the nearest neighbors. These make it possible to quickly find both the candidates adjacent to the feature space and to efficiently manage the set of candidates currently to be considered. This aspect is of particular importance in the fingerprint method, since the reference quantity is determined by newly added broadcasts and completely processed consignments is subject to constant changes.
Wurde bei dem Vergleich/Datenbankabfrage 12.2,12.3 eine zwei¬ felsfreie Übereinstimmung mit einem der gespeicherten Merk¬ malsvektoren festgestellt, so wird die dazugehörende Verteil¬ information 9 der betreffenden Sendung zugeordnet und die Sortierung kann erfolgen.If, in the comparison / database query 12.2, 12.3, a two-tone match was found with one of the stored feature vectors, the associated distribution information 9 is assigned to the relevant item and the sorting can take place.
Konnte überhaupt kein Kandidat von den gespeicherten Merk¬ malsvektoren ermittelt werden, so muss ein ganz normaler und bekannter automatischer Leseprozess durchgeführt werden, ggf. mit zwei Lesern 15,17, d.h. mit den Schritten: ROI- Suche 15.1,17.1, OCR-Zeichenlesen 15.2,17.2 und Adressinter- pretation 15.3,17.3. Falls die Zieladresse so nicht eindeutig identifiziert werden kann, wird das Sendungsbild an einem Vi¬ deokodierplatz manuell kodiert 18, so dass die Sendung ko¬ diert werden kann. Für den Fall, dass auf mehrere in Betracht kommende Kandida¬ ten 13 von Merkmalsvektoren/Fingerprints 3 ermittelt wurden, werden zusätzliche Merkmale von den Adresslesern 15 oder 17 verwendet. Interessant sind dabei die ermittelten Ergebnisse der Region of Interest (ROI) Suche 15.1,17.1, sofern diese Information noch nicht im Fingerprint selbst verwendet wird, die im Zeichenleseprozess 15.2,17.2 ermittelten Einzelzei¬ chenalternativen und natürlich die Ergebnisse der Adressin¬ terpretation 15.3,17.3. Es genügt, wie in dem Flussdiagramm (FIG 3) dargestellt ist, wenn nur die Leseschritte erfolg- reich abgeschlossen werden, die gerade notwendig sind, um den richtigen Fingerprint-Kandidaten auszuwählen. Dabei werden die vom/von den Adresslesern 15,17 erhaltenen Ergebnisse mit den zu den Fingerprint-Kandidaten 13 in der Datenbank 4 abge¬ legten Informationen verglichen und irrelevante Kandidaten werden verworfen, bis nur noch ein Kandidat übrig bleibt. Der Ablauf einschließlich der Vergleichsprozesse wird in einem sogenannten Voter 16 bestimmt.If no candidate could be determined from the stored feature vectors at all, a completely normal and known automatic reading process must be carried out, if necessary with two readers 15, 17, ie with the steps: ROI search 15.1, 7.1, OCR character reading 15.2 , 17.2 and address inter- pretation 15.3,17.3. If the destination address can not be clearly identified in this way, the program picture is manually coded 18 at a video coding station, so that the program can be coded. In the event that 13 of feature vectors / fingerprints 3 have been determined for a plurality of candidate candidates, additional features are used by the address readers 15 or 17. Of particular interest are the results of the Region of Interest (ROI) search 15.1, 17.1, if this information is not yet used in the fingerprint itself, the single-digit alternatives determined in the character reading process 15.2, 17.2 and of course the results of the address interpretation 15.3, 17.3 , It suffices, as shown in the flowchart (FIG. 3), for only the reading steps which are just necessary to select the correct fingerprint candidate to be completed successfully. In this case, the results obtained by / from the address readers 15, 17 are compared with the information filed on the fingerprint candidates 13 in the database 4, and irrelevant candidates are rejected until only one candidate remains. The sequence including the comparison processes is determined in a so-called voter 16.
Z.B. könnte nur die Abgangszeile, d.h. PLZ und Ort vom Leser automatisch erkannt worden sein. Mit dieser Information kann der Voter 16 aber in vielen Fällen schon eindeutig eine Sen¬ dung aus den Fingerprint-Kandidaten 13 auswählen. Die Video¬ kodierung 18 der noch fehlenden Adressteile kann dann entfal¬ len. Zusätzlich entscheidet der Voter 16 anhand der Glaubwürdig- keiten vom Ergebnis der Fingerprint-Ermittlung und von den verwendeten Ergebnissen und Teilergebnissen des Leseprozes¬ ses, ob das Ergebnis genügend sicher ermittelt wurde 22. Wenn nein, muss die komplette Zieladresse automatisch gelesen oder videokodiert werden. In FIG 3 wurde wegen der Übersichtlichkeit der Ablauf mit nur jeweils einem Primärleser dargestellt. Sind noch Sekundärle¬ ser vorhanden, so werden auch für diese Leser die Prozesse entsprechend durchgeführt. For example, only the outgoing line, ie postcode and location, could have been automatically recognized by the reader. With this information, however, the voter 16 can in many cases already clearly select a message from the fingerprint candidates 13. The video coding 18 of the still missing address parts can then be omitted. In addition, the voter 16 decides on the basis of the credibility of the result of the fingerprint determination and of the results used and partial results of the reading process, whether the result has been determined sufficiently reliably. 22. If not, the complete destination address must be automatically read or video-coded. In FIG. 3, the sequence has been shown with only one primary reader each for the sake of clarity. If secondary readers are still present, the processes are also carried out accordingly for these readers.

Claims

Patentansprüche claims
1. Verfahren zum Sortieren von adressierten Sendungen ent¬ sprechend der Zieladresse in mehreren Verarbeitungs- schritten, bei dem im ersten Verarbeitungsschritt ein1. A method for sorting addressed broadcasts corresponding to the destination address in a plurality of processing steps, wherein in the first processing step
Bild der Sendung aufgenommen und daraus die Zieladresse gelesen und die Verteilinformation und zusätzlich charak¬ teristische Merkmale des Bildes (3) ermittelt (2) und der Sendung zugeordnet in einer Datenbank (4) gespeichert werden, und bei dem in den weiteren Verarbeitungsschrit¬ ten ebenfalls die Bilder der Sendungen aufgenommen, dar¬ aus die charakteristischen Merkmale (13) gewonnen (12) , mit den beim ersten Verarbeitungsschritt ermittelten Merkmalen (3) verglichen und bei Übereinstimmung mit festgelegter Glaubwürdigkeit die dazugehörende Sendung mit der gespeicherten Verteilinformation identifiziert wird, d a d u r c h g e k e n n z e i c h n e t , dassImage of the consignment recorded and read from the destination address and the distribution information and additionally charak¬ teristic features of the image (3) determined (2) and associated with the program stored in a database (4), and in the th also processing steps the images of the broadcasts are recorded, the characteristic features (13) are obtained (12), compared with the features (3) determined in the first processing step, and if the corresponding credibility with the stored distribution information is identified in accordance with defined credibility, characterized in that
- im ersten Verarbeitungsschritt zusammen mit den charak¬ teristischen Merkmalen (3) diesen zugeordnet in der Da- tenbank (4) neben den gelesenen Zieladressen/ Verteil-in the first processing step, together with the characteristic features (3) assigned to it in the database (4) in addition to the read target addresses / distribution
Informationen die jeweiligen Lesezwischenergebnisse mit abgespeichert werden (9) ,Information the respective intermediate reading results are stored (9),
- im Wiedererkennungsprozess eines weiteren Verarbei¬ tungsschrittes bei keiner eindeutigen Übereinstimmung in festgelegter Glaubwürdigkeit der im jeweiligen Ver¬ arbeitungsschritt ermittelten charakteristischen Merk¬ male mit mehreren gespeicherten Merkmalssätzen von ge¬ fundenen Kandidaten aus dem ersten Verarbeitungsschritt der automatische Leseprozess für den jeweiligen weite- ren Verarbeitungsschritt zum Lesen der Adresse der ak¬ tuell wiederzuerkennenden Sendung gestartet wird,in the recognition process of a further processing step, if there is no unequivocal agreement in defined credibility of the characteristic features determined in the respective processing step with a plurality of stored feature sets of found candidates from the first processing step, the automatic reading process for the respective further processing step for Reading the address of the current program to be recognized is started,
- die aktuellen Lesezwischenergebnisse oder Leseergebnis¬ se der zu identifizierenden Sendung mit den entspre¬ chenden gespeicherten Lesezwischenergebnissen oder Le- seergebnissen der Sendungen der ermittelten Merkmals¬ kandidaten verglichen werden, - und bei gefundener Übereinstimmung mit festgelegter Glaubwürdigkeit die diesem Merkmalskandidaten zugeord¬ nete Sendung mit der gespeicherten Verteilinformation der Zieldresse die wiedererkannte Sendung darstellt und die Sortierung anhand dieser Verteilinformation er¬ folgt.the actual reading intermediate results or reading results of the mail item to be identified are compared with the corresponding stored intermediate reading results or readings of the mailings of the determined feature candidates, - And found in conformity with a defined credibility, the this feature candidate zugeord¬ ned consignment with the stored distribution information of the target address represents the recognized program and the sorting on the basis of this distribution information er¬ follows.
2. Verfahren nach Anspruch 1, d a d u r c h g e k e n n ¬ z e i c h n e t , dass der Lese- und Vergleichsvorgang im Wiedererkennungsprozess eines weiteren Verarbeitungs- schrittes stufenweise entsprechend der abfolgenden Lese¬ schritte (15.1,15.2,15.3,17.1,17.2,17.3) durchgeführt wird, wobei der nachfolgende Lese- und Vergleichsschritt nur erfolgt, wenn der vorherige keine eindeutige Kandida- tenzuordnung ergibt.2. The method of claim 1, characterized dadurchgekenn ¬ records that the reading and comparing process in the recognition process of a further processing step stepwise according to the subsequent Lese¬ steps (15.1,15.2,15.3,17.1,17.2,17.3) is performed, the following Reading and comparison step only takes place if the previous one does not result in a clear candidate assignment.
3. Verfahren nach Anspruch 2, d a d u r c h g e k e n n ¬ z e i c h n e t , dass nach dem Start des automatischen Leseprozesses und nach der Ermittlung (15.1) des Adress- gebietes der Zieladresse dieses mit den Adressgebieten zu den Merkmalskandidaten verglichen wird, bei eindeutiger Übereinstimmung in geforderter Glaubwürdigkeit (22) mit einem der Adressgebiete die zugeordnete Sendung identifi¬ ziert ist und der Leseprozess beendet wird, falls die Zu- Ordnung zu nur einem Merkmalssatz nicht möglich ist, das Lesen (15.2) der Einzelzeichen und Wörter und ein Ver¬ gleich mit den zu den verbleibenden Merkmalskandidaten gespeicherten Einzelzeichen und Wörtern erfolgt und bei Übereinstimmung in geforderter Glaubwürdigkeit (22) mit den Einzelzeichen und Wörtern nur eines Merkmalskandida¬ ten die zugeordnete Sendung identifiziert ist und der Le¬ seprozess beendet wird, und falls die Zuordnung zu nur einem Merkmalssatz nicht möglich ist, die Adressinterpre¬ tation (15.3) durchgeführt wird, deren Ergebnisse dann mit denen der verbleibenden Merkmalskandidaten verglichen werden, bei Übereinstimmung in geforderter Glaubwürdig¬ keit (22) mit den Ergebnissen der Adressinterpretation zu nur einem Merkmalskandidaten die zugeordnete Sendung identifiziert ist und der Leseprozess beendet wird.3. The method according to claim 2, dadurchgekenn ¬ records that after the start of the automatic reading process and after the determination (15.1) of the address area of the destination address this is compared with the address areas to the feature candidates, with a clear match in required credibility (22) with one of the address areas the assigned program is identifi ed and the reading process is terminated, if the assignment to only one feature set is not possible, reading (15.2) of the individual characters and words and a Ver¬ equal to the remaining feature candidate memorized individual characters and words, and if there is agreement in required credibility (22) with the individual characters and words only one Merkmalskandida¬ th the assigned program is identified and the Le¬ seprozess is terminated, and if the assignment to only one feature set is not possible, the Adressinterpre¬ tion (15.3) is performed, whose Results are then compared with those of the remaining feature candidates, if they agree in the required credibility (22) with the results of the address interpretation only one feature candidate the assigned broadcast is identified and the reading process is terminated.
4. Verfahren nach Anspruch 3, d a d u r c h g e k e n n - z e i c h n e t , dass die Adressleser Primärleser (5,15) und Sekundärleser (7,17) besitzen, die bei Bedarf nach¬ einander gestartet werden und dass beim Wiedererkennungs- prozess der im Anspruch 3 beschriebene Ablauf auch mit dem oder den jeweiligen Sekundärlesern (17) durchgeführt werden, falls mit dem Primärleser (15) noch keine automa¬ tische Identifikation erreicht wurde.4. The method according to claim 3, dadurchgekenn - characterized in that the address reader primary reader (5,15) and secondary readers (7,17) have, which nach¬ each other started if necessary and that in the recognition process of the process described in claim 3 also be performed with the or the respective secondary readers (17) if no automatic identification has been achieved with the primary reader (15).
5. Verfahren nach Anspruch 1, d a d u r c h g e k e n n ¬ z e i c h n e t , dass die in der Datenbank (4) gespei- cherten charakteristischen Merkmale mit den Lesezwischen¬ ergebnissen und Leseergebnissen/Verteilkodes gelöscht werden, wenn eine bestimmte Verfallszeit überschritten wurde oder wenn der letzte Verarbeitungsschritt durchlau¬ fen wurde.5. The method of claim 1, dadurchgekenn ¬ characterized in that the stored in the database (4) characteristic features with the Lesezwischen¬ results and reading results / distribution codes are deleted when a certain expiration time has been exceeded or when the last processing step durchlau¬ fen has been.
6. Verfahren nach Anspruch 1, d a d u r c h g e k e n n ¬ z e i c h n e t , dass, falls die automatische Identifi¬ kation nicht erfolgreich abgeschlossen wurde, nur die Bilder oder Adressalternativen der Sendungskandida- ten (13) manuell an Videokodierplätzen mittels Selektion kodiert werden (18) . 6. Method according to claim 1, wherein, if the automatic identification has not been completed successfully, only the pictures or address alternatives of the program candidates (13) are coded manually at video coding stations by means of selection (18).
EP05785599A 2004-10-01 2005-09-07 Method for sorting addressed mailings according to the destination address Not-in-force EP1799359B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PL05785599T PL1799359T3 (en) 2004-10-01 2005-09-07 Method for sorting addressed mailings according to the destination address

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102004047934A DE102004047934B3 (en) 2004-10-01 2004-10-01 Method for sorting addressed items according to the destination address
PCT/EP2005/009585 WO2006037413A1 (en) 2004-10-01 2005-09-07 Method for sorting addressed mailings according to the destination address

Publications (2)

Publication Number Publication Date
EP1799359A1 true EP1799359A1 (en) 2007-06-27
EP1799359B1 EP1799359B1 (en) 2009-02-25

Family

ID=35406178

Family Applications (1)

Application Number Title Priority Date Filing Date
EP05785599A Not-in-force EP1799359B1 (en) 2004-10-01 2005-09-07 Method for sorting addressed mailings according to the destination address

Country Status (9)

Country Link
US (1) US20090026117A1 (en)
EP (1) EP1799359B1 (en)
KR (1) KR20070059202A (en)
AT (1) ATE423635T1 (en)
DE (2) DE102004047934B3 (en)
DK (1) DK1799359T3 (en)
ES (1) ES2321426T3 (en)
PL (1) PL1799359T3 (en)
WO (1) WO2006037413A1 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2171658B1 (en) * 2007-07-25 2017-06-14 Siemens Aktiengesellschaft Method and device for monitoring the transport of an object
US8059861B2 (en) * 2008-11-17 2011-11-15 Lockheed Martin Corporation Method and system for identifying and recognizing products for sorting/sequencing operations
CN118096001B (en) * 2024-04-26 2024-07-26 青岛冠成软件有限公司 Cargo storage data management method

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE4000603C5 (en) * 1990-01-11 2009-07-02 Siemens Ag Method and device for temporary storage of objects, such as letters or the like in a reading system
JPH09239325A (en) * 1996-03-11 1997-09-16 Hitachi Ltd Method for rearranging and sorting postal item delivery order and apparatus therefor
DE19947259C1 (en) * 1999-09-30 2000-09-28 Siemens Ag Sorting packages involves changing/emptying containers when full, storing packages in same sequence, entering package data in database and re-ordering during subsequent sorting runs
US6303889B1 (en) * 2000-02-15 2001-10-16 Opex Corporation Method and apparatus for sorting documents into a pre-defined sequence
FR2841673B1 (en) * 2002-06-26 2004-12-03 Solystic TIMING OF POSTAL OBJECTS BY IMAGE SIGNATURE AND ASSOCIATED SORTING MACHINE

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO2006037413A1 *

Also Published As

Publication number Publication date
ES2321426T3 (en) 2009-06-05
KR20070059202A (en) 2007-06-11
US20090026117A1 (en) 2009-01-29
DE102004047934B3 (en) 2006-04-20
ATE423635T1 (en) 2009-03-15
WO2006037413A1 (en) 2006-04-13
DE502005006712D1 (en) 2009-04-09
EP1799359B1 (en) 2009-02-25
PL1799359T3 (en) 2009-07-31
DK1799359T3 (en) 2009-06-15

Similar Documents

Publication Publication Date Title
EP0975442B2 (en) Method of processing postal matters
EP0980293B1 (en) Mail distribution information recognition method and device
DE19742771C1 (en) Distribution data recognition for video coding position on mail sorter
WO1998021689A1 (en) Method and device for recognizing distribution data on postal packets
DE10010241C1 (en) Shipment addresses reading method
EP1799359A1 (en) Method for sorting addressed mailings according to the destination address
DE10150560A1 (en) Method for automatic processing of postal items in which after address details have been automatically read in they are compared with existing details in a database and if necessary a new complete and accurate address applied
DE19933984C2 (en) Method for forming and / or updating dictionaries for automatic address reading
EP2259210A2 (en) Method and device for analysing a database
EP1159705B1 (en) Method for reading document entries and addresses
DE10212085A1 (en) Method and device for reading the addresses of consignments
EP1229484B1 (en) Method and apparatus for reading parcel addresses with postcodes
DE69928320T2 (en) Method and device for recognizing a pattern on a presented object
EP1389493A1 (en) Process and apparatus for automatic marking of address fields
EP1229483A1 (en) Method and apparatus for reading parceladdresses with postcodes
WO2007048452A1 (en) Method and device for reading addresses of items of mail
DE10345047B4 (en) Method for generating and / or updating learning and / or test samples
EP1916039A1 (en) Method for identifying objects and signature comparison device
DE102009025018A1 (en) Method for analyzing quality of database i.e. address-database, of sorting and distribution system for e.g. letters, involves determining condition of database based on legibility degree and comparison of data elements with reference data

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

17P Request for examination filed

Effective date: 20070321

AK Designated contracting states

Kind code of ref document: A1

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 NL PL PT RO SE SI SK TR

DAX Request for extension of the european patent (deleted)
GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

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 NL PL PT RO SE SI SK TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

Free format text: NOT ENGLISH

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

Free format text: LANGUAGE OF EP DOCUMENT: GERMAN

REF Corresponds to:

Ref document number: 502005006712

Country of ref document: DE

Date of ref document: 20090409

Kind code of ref document: P

REG Reference to a national code

Ref country code: CH

Ref legal event code: NV

Representative=s name: SIEMENS SCHWEIZ AG

REG Reference to a national code

Ref country code: ES

Ref legal event code: FG2A

Ref document number: 2321426

Country of ref document: ES

Kind code of ref document: T3

REG Reference to a national code

Ref country code: DK

Ref legal event code: T3

REG Reference to a national code

Ref country code: SE

Ref legal event code: TRGR

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

REG Reference to a national code

Ref country code: PL

Ref legal event code: T3

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090625

Ref country code: LV

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

REG Reference to a national code

Ref country code: IE

Ref legal event code: FD4D

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090812

Ref country code: IE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

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

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090525

26N No opposition filed

Effective date: 20091126

BERE Be: lapsed

Owner name: SIEMENS A.G.

Effective date: 20090930

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MC

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20090930

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20090930

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090526

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: CH

Payment date: 20101207

Year of fee payment: 6

Ref country code: DE

Payment date: 20101119

Year of fee payment: 6

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: IT

Payment date: 20100928

Year of fee payment: 6

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LU

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20090907

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: HU

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090826

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: TR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20090225

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DK

Payment date: 20110926

Year of fee payment: 7

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20111005

Year of fee payment: 7

Ref country code: GB

Payment date: 20110915

Year of fee payment: 7

Ref country code: PL

Payment date: 20110825

Year of fee payment: 7

Ref country code: SE

Payment date: 20110908

Year of fee payment: 7

Ref country code: AT

Payment date: 20110810

Year of fee payment: 7

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: NL

Payment date: 20110913

Year of fee payment: 7

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: ES

Payment date: 20111013

Year of fee payment: 7

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

REG Reference to a national code

Ref country code: DE

Ref legal event code: R119

Ref document number: 502005006712

Country of ref document: DE

Effective date: 20120403

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20120403

Ref country code: CH

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20110930

Ref country code: LI

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20110930

REG Reference to a national code

Ref country code: NL

Ref legal event code: V1

Effective date: 20130401

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20120908

REG Reference to a national code

Ref country code: SE

Ref legal event code: EUG

REG Reference to a national code

Ref country code: AT

Ref legal event code: MM01

Ref document number: 423635

Country of ref document: AT

Kind code of ref document: T

Effective date: 20120907

GBPC Gb: european patent ceased through non-payment of renewal fee

Effective date: 20120907

REG Reference to a national code

Ref country code: DK

Ref legal event code: EBP

REG Reference to a national code

Ref country code: FR

Ref legal event code: ST

Effective date: 20130531

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: AT

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20120907

Ref country code: GB

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20120907

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IT

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20120907

Ref country code: FR

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20121001

Ref country code: NL

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130401

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DK

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20121001

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: PL

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20120907

REG Reference to a national code

Ref country code: PL

Ref legal event code: LAPE

REG Reference to a national code

Ref country code: ES

Ref legal event code: FD2A

Effective date: 20140109

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: ES

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20120908