EP2371461B1 - Method for transporting an object to be printed - Google Patents

Description

The invention relates to a method for transporting an article to be printed, in particular a mailpiece. A method with the features of the preamble of claim 1 is made DE 10 2008 017 185 A1 known.

In DE 10 2008 017 185 A1 For example, a method and apparatus for transporting and processing multiple items will be described. At least one optically detectable transport attribute ("measurable processing attribute") and at least two optically detectable characteristics ("measurable characteristics") are specified. A first sorting system Anl-1 discharges several objects (flat mail items) into an output compartment Af-1.2 and further objects into other output compartments, cf. Fig. 1 , These mail items from the output tray Af-1.2 enter a container Beh-2, are transported to a second sorting system Anl-2 and pass through the second sorting system Anl-2. The first sorting system Anl-1 carries out for each item to be transported the steps of generating a digital image of the item, measuring for each item the value of this item for that item, a value for the transport attribute of the item ( Delivery address of the mail item) is measured and in a central database DB, a data record for the object is generated. This data record includes the transport attribute value and the measured characteristic values. The second sorting system Anl-2 carries out the steps for each object to again generate a digital image of the object, to re-measure for each feature what value this feature assumes, and to use these feature values to determine the data set stored in the database DB.

The transport attribute value (delivery address) in this record is used as the transport attribute value of the article, and the article is discharged into an output tray of the second sorting system Anl-2.

In DE 10 2008 017 185 A1 the case is described that individual mail items are to be provided with a respective delivery note after the mail items have passed through the first sorting system Anl-1. A printer 3 of the second sorting system Anl-2 prints a mail item or a label in accordance with a set of print commands. As a result, the second sorting system Anl-2 provides a postal item z. B. with a new delivery address. The second sorting system Anl-2 calculates the value of the first feature before the mailpiece has reached the printer 3. This first feature value is used to search for the record for the mailpiece.

In DE 10 2006 051 777 B4 For example, a method and apparatus for identifying a mail item while transporting that item of mail to a predetermined destination address is described. In a first pass ("registration run") characteristic image features of the mailpiece ("feature value vector", "signature") are determined and stored. In addition, at least one piece of information about the mailpiece is determined and stored together with the feature value vector in a data record. This information is for. B. the deciphered destination address, the weight, the rigidity and dimensions of the mail as well as information on a franking mark on the mailpiece. In addition, an identification code is applied to the mailpiece and stored in the data record. The variation possibilities of this identification code are so small that the identification code alone is not able to distinguish the mail item from all other mailpieces. For example, there are 16 or 25 different possible identification codes.

In the further course of transport, the case may arise that the surface of the mail piece is changed. For example, an additional canceler imprint or advertising imprint is applied to the mailpiece or else a Identification of a forwarding address. For further transport of the mail item, the stored information, in particular the destination address or a physical attribute of the mailpiece, is needed again. This information is needed in particular in a subsequent identification run. In this identification run, a feature value vector ("signature") is again generated by the mailpiece. The stored record for the item is searched for and determined. For this search, on the one hand, the feature value vector generated in the identification run is compared with stored feature value vectors. On the other hand, the identification code on the mail piece is read and compared with stored identification codes. The data record is determined with matching identification codes and the most similar feature value vector.

In DE 10 2008 026 088 A1 For example, a method and apparatus for transporting mass mailings will be described. To a sorting system, a target image is transmitted in computer-available form. This target image shows the surface of such a bulk mailer and is valid for every bulk mailing of a given set of mass mailings. However, the bulk mailings are to be transported to different delivery addresses, and each bulk mailing is provided with the respective delivery address in advance or in the course of transportation. Therefore, an actual image of a particular mass broadcast does not match the transmitted target image. Nevertheless, during the transport of a mailpiece, an actual image of the mailpiece is generated and compared with the transmitted target image in order to decide whether this mailpiece is a mass mailing of the amount of bulk mailings corresponding to the target image or another mailpiece , For this purpose, an image evaluation unit calculates the address block from the actual image and compares the thus computationally modified actual image with the transmitted desired image.

In WO 2008/152277 A2 and US 2010/0232642 A1 Also described are a method and a device in which a Mailing twice through a sorting system. In the first pass, a feature value vector ("signature numérique" - "digital signature") of the mailpiece is generated, for which purpose a computer-accessible image is generated and evaluated by the mailpiece. This feature value vector is stored as part of a data record in a central data memory. In a subsequent second sorting run, a feature value vector is again generated by the mail item, and the feature data vector is used to search for the stored data record. In this case, the problem arises that similar mass mailings can only be distinguished from one another on the basis of different address blocks. Therefore, a distinction is made between global features and local features. When searching for the stored feature value data set, first global feature values are compared in order to quickly exclude very dissimilar stored feature value vectors, and then only local feature values. In addition, the stored feature value vectors are automatically subdivided into classes. During the subsequent sorting run, it is first determined to which class the feature value vector to be examined belongs, and then the most similar feature value vector is searched within these classes. This makes it possible to eliminate the influence of different light conditions in the first and second sorting, which could otherwise lead to false results.

In FR 2841673 A1 and US 2005/0123170 A1 For example, a method and apparatus for processing mail is described. For each mail item, a digital image is generated. This image shows the delivery address on the mailpiece. The image is assigned an "identifier", for which the image is evaluated. This "identifier" is a signature for the mailpiece and consists of a feature value vector which on the one hand consists of physical feature values of the mailpiece (first component PC) and on the other hand of feature values which are determined by image processing (OCR) from the image (second component SC ). To the Feature values of the second component SC include z. B. the following features of the address block on the mailing, see. Fig. 2 : the arrangement, the row direction, the number of lines and certain letters of the address block, eg. B. the first letter of a line. Each mail item can be uniquely identified by means of this signature, if this mail item successively passes through several sorting systems, even if several mail items are to be transported to the same delivery address.

In DE 102008017191 A1 and DE 102008017190 A1 and DE 10 2008 017 189 A1 Methods are described in order to limit the search space in the search for the stored feature value vector and thus to perform fewer comparisons of the current feature value vector with stored feature value vectors.

In DE 10 2006 059 525 B3 Also, a method is described for transporting an article, wherein the article passes through a sorting plant twice. It is determined whether transport errors occur, for. For example, if the item was transported to a wrong destination and misdirected. Each pass generates a record for the item. This record includes a reading result, e.g. B. the determined delivery address, as well as an image of the subject. The following steps are performed for a misdirected object: The correct delivery address is determined. All data records generated in the first pass with this delivery address are determined. It checks which images include this data set. This makes it possible to differentiate between different transport errors.

In EP 1131793 B1 and DE 69931388 T2 For example, a method and apparatus are described for making and subsequently checking postage indicia.

The invention has for its object to provide a method with the features of the preamble of claim 1, which allows the object between physically altering the two decision-making processes and still finding the record for that item in the further decision-making process, without having to provide the item with a decipherable identification code.

The object is achieved by a method having the features of claim 1. Advantageous embodiments are specified in the subclaims.

In the method according to the invention, at least one object is transported to a predetermined destination. It is possible that several objects are transported to a given destination point.

At least one optically detectable feature, preferably a plurality of features, and at least one transport attribute are specified.

The transporting comprises, for each item to be transported, a first decision process and at least one further decision process. It is possible that after the first decision process several more decision processes are carried out in succession.

• Mindestens ein erstes rechnerverfügbares Abbild des Gegenstands wird erzeugt. Dieses Abbild zeigt mindestens eine Oberfläche des Gegenstands.
• Für jedes vorgegebene Merkmal wird erstmals gemessen, welchen Wert dieses Merkmal für den Gegenstand annimmt, wofür das mindestens eine erste rechnerverfügbares Abbild von der Oberfläche des Gegenstands ausgewertet wird. Bei n vorgegebenen Merkmalen wird dadurch ein Vektor mit n Merkmalswerten erzeugt.
• Für jedes Transport-Attribut wird gemessen, welchen Wert dieses Transport-Attribut für den Gegenstand annimmt.
• Ein Datensatz für den Gegenstand wird erzeugt und in einem zentralen Datenspeicher abgespeichert. Dieser Datensatz umfasst einen Vektor mit den gemessenen n Merkmals-Werten und mit dem mindestens einen gemessenen Transport-Attribut-Wert. und mit dem mindestens einen gemessenen Transport-Attribut-Wert.
• Der erste Entscheidungsvorgang wird abhängig von mindestens einem gemessenen Transport-Attribut-Wert getroffen.

The first decision process includes the following automated steps:

• At least a first computer-available image of the object is generated. This image shows at least one surface of the object.
• For each given feature, it is first measured what value this feature assumes for the item, for which the at least one first computer-available image is evaluated from the surface of the item. In the case of n predefined features, this produces a vector with n feature values.
• For each transport attribute, the value of this transport attribute for the object is measured.
• A data record for the object is generated and stored in a central data memory. This data set comprises a vector with the measured n feature values and with the at least one measured transport attribute value. and with the at least one measured transport attribute value.
• The first decision process is made depending on at least one measured transport attribute value.

Depending on the first decision process, the transport of the item continues.

• Ein weiteres rechnerverfügbares Abbild des Gegenstands wird erzeugt.
• Für jedes vorgegebene Merkmal wird erneut gemessen, welchen Wert dieses Merkmal für den Gegenstand annimmt, wofür das weitere rechnerverfügbare Abbild ausgewertet wird. Dadurch wird wiederum ein Vektor mit n Merkmals-Werten erzeugt.
• Derjenige Datensatz wird ermittelt, der für diesen Gegenstand erzeugt und im zentralen Datenspeicher abgespeichert wurde. Für dieses Ermitteln wird der beim erneuten Messen gemessene Merkmalswerte-Vektor verwendet, um im zentralen Datenspeicher nach dem Datensatz für diesen Gegenstand zu suchen und dabei den gemessenen Merkmalswerte-Vektor mit abgespeicherten Merkmalswerte-Vektoren zu vergleichen.
• Der mindestens eine Transport-Attribut-Wert, der vom ermittelten Datensatz umfasst wird, wird ermittelt.
• Der weitere Entscheidungsvorgang wird abhängig von mindestens einem ermittelten Transport-Attribut-Wert getroffen.
• Der Gegenstand wird abhängig vom Ergebnis des weiteren Entscheidungsvorgangs weitertransportiert.

The at least one further decision process comprises the following automatically performed steps:

• Another computer-accessible image of the object is generated.
• For each given feature, it is again measured what value this feature assumes for the item, for which the further computer-available image is evaluated. This in turn generates a vector with n feature values.
• The data record is determined which was generated for this object and stored in the central data memory. For this determination, the feature value vector measured during the renewed measurement is used to search for the data record for this object in the central data memory and thereby to compare the measured feature value vector with stored feature value vectors.
• The at least one transport attribute value that is included in the ascertained data record is determined.
• The further decision process is made dependent on at least one determined transport attribute value.
• The object is transported on depending on the result of the further decision process.

After the first measurement (for the first decision process) and before the first remeasurement (for the further decision process), the surface of the article is provided with an optically detectable element. This step affects the value of at least one measured feature in the sense that the optically detectable element in the another image can be seen, but not in the first image, and therefore the image of the object with the optically detectable element leads to a different value of this feature than the image of the object without the optically detectable element.

• eine vorgegebene rechnerverfügbare Festlegung der Position des Elements auf der Oberfläche des Gegenstands, also wo das Element auf die Oberfläche des Gegenstands zu platzieren ist, und
• ein vorgegebenes rechnerverfügbares Muster des Elements.

For the step of providing the surface of the object with the optically detectable element, the following given objects are used:

• a predetermined computer-accessible definition of the position of the element on the surface of the object, ie where the element is to be placed on the surface of the object, and
• a given computer-accessible pattern of the element.

The position setting and pattern together act as a template for the process of providing the article with the optically detectable element. The element is z. B. applied directly to the object or sprayed or etched. Or on a previously empty label, the optically detectable element is printed, and the label is glued to the object at the predetermined position. The default pattern is used to print the label.

• Dieser Merkmalswerte-Vektor enthält für jedes Merkmal denjenigen Wert, den das Merkmal für den Gegenstand dann annehmen würde, wenn die Oberfläche des Gegenstands bereits beim ersten Messen mit dem optisch erfassbaren Element versehen gewesen wäre. Für den Schritt, diesen Merkmalswerte-Vektor zu erzeugen, werden die Positions-Festlegung und das Element-Muster verwendet. Das mindestens eine weitere Abbild, welches für das erneute Messen ausgewertet wird, wird von dem mit dem optisch erfassbaren Element versehenen Gegenstand erzeugt.

The feature value vector stored in the data record-that is, the feature value vector generated in the first decision process-for this object is generated in such a way that the stored feature value vector fulfills the following property:

• This feature value vector contains for each feature the value which the feature would assume for the article if the surface of the article had already been provided with the optically detectable element during the first measurement. For the step of generating this feature value vector, the position fix and the element pattern are used. The at least one further image, which is evaluated for the remeasurement, is generated by the object provided with the optically detectable element.

This mathematically modified feature value can be equal to the actually measured feature value, namely if the application of the optically detectable element does not change the value of this feature, ie. H. the feature is not affected. The mathematically modified feature value can also be a value that deviates from the actually measured feature value because the application of the element influences the feature.

According to the solution, the article to be transported is measured without the optically detectable element in the first decision process. Only then is the optically detectable element applied. This order is z. B. predetermined by the arrangement of measuring devices and a printer and / or by the processing during transport of the object. The effect of this element on the optically detectable features is computationally supplemented in the feature value vectors to be stored. In the or each further decision process, the article is measured with the optically detectable element. The feature value vector obtained during retiming is compared with the computationally changed feature value vector from the first measurement.

Measuring the transport attribute requires effort and / or time, especially if the measurement requires human input. Therefore, it makes sense to measure the value of this transport attribute only once for each item. However, the at least one transport attribute value is repeatedly needed during transport to decide between different alternatives for the continuation of the transport. The destination address to which the item is to be transported is an example of such a transport attribute value that is repeatedly required to decide how to continue the transport of the item. The weight, dimension or finish of the article are further examples of transport attributes.

To be able to measure the transport attribute only once, the measured value must be stored and determined whenever the value is needed again. This requires finding the stored transport attribute value among several stored transport attribute values. For this purpose, the item is re-identified in each decision process.

The solution according to the invention avoids the necessity of having to provide the item with an identifier ("ID tag") in order to be able to identify it and to be able to determine the transport attribute value. In order to identify the object, rather, a feature value, preferably a vector with multiple feature values, is used. At least one feature is measured by capturing and evaluating an image of the object.

The solution according to the invention eliminates the need to apply an identifier to the article during transport and decipher it later. In particular, neither coding of the transport attribute value, e.g. As a sort code, nor an identifying identifier ("ID code") nor an identifier as they are in

DE 10 2006 051 777 B4 is described, imprinted or otherwise applied. This saves time and material for printing and eliminates the risk of mis-decoding an identifier causing a transport error. The optically detectable element need not be machine decipherable and may also be a pictogram, a logo or a string.

The invention solves the problem resulting from the article being provided with an optically detectable element between the first measurement and the second measurement. The application of this optically detectable element results in the feature or feature having a different value after application than before application. Despite this change, the object should be based on the feature value vector be identified. The invention shows a way to do this.

The feature values measured during the first measurement are mathematically modified in such a way that those values are obtained which the respective feature would assume if the optically detectable element already existed on the object before the first measurement. Therefore, the optically detectable element can be used to distinguish this object from other transported objects and to find the correct record in the central data memory. This effect also occurs when the optically detectable element can not be decoded by machine or is not deciphered. In particular, this effect distinguishes the invention of a procedure in which the optically detectable element is simply "hidden".

• eine Abmessung des Gegenstands,
• die Verteilung von Grauwerten auf der Oberfläche des Gegenstands,
• die Verteilung von Farbwerten auf der Oberfläche des Gegenstands,
• die Anzahl von Textblöcken auf der Oberfläche des Gegenstands und die jeweilige Position und/oder Abmessung jedes Textblocks,
• die Lage und/oder die Größe mindestens eines Textblocks,
• die Anzahl von graphischen Elementen auf der Oberfläche des Gegenstands, z. B. Transportvermerke, Logos oder Freimachungsvermerke,
• die Position und graphische Eigenschaften mindestens eines graphischen Elements.

The at least one optically detectable feature is z. For example, from the following list:

• a dimension of the object,
• the distribution of gray values on the surface of the object,
• the distribution of color values on the surface of the object,
• the number of text blocks on the surface of the object and the respective position and / or dimension of each text block,
• the location and / or size of at least one text block,
• the number of graphical elements on the surface of the article, e.g. B. transport marks, logos or franking marks,
• the position and graphic properties of at least one graphic element.

• das Zielpunkt, an den der Gegenstand zu transportieren ist, wobei der Gegenstand mit einer zu entziffernden Kennzeichnung des Gegenstands versehen ist oder dieser Zielpunkt mindestens einem rechnerverfügbaren Empfänger-Liste vorgegeben wird,
• das Gewicht des Gegenstands,
• eine Abmessung des Gegenstands,
• eine Oberflächenbeschaffenheit des Gegenstands,
• eine Vorausverfügung für das Zustellen des Gegenstands oder
• der Wert eines Freimachungsvermerks oder sonstigen Hinweises auf ein Beförderungsentgelt, wobei der Gegenstand mit diesem Freimachungsvermerk oder sonstigem Hinweis versehen ist.

As a transport attribute z. For example, you can use the following attributes:

• the destination point to which the object is to be transported, the object being provided with an identification of the object to be decoded, or this destination being specified for at least one computer-accessible receiver list,
• the weight of the object,
• a dimension of the object,
• a surface finish of the object,
• a preliminary order for delivery of the item or
• the value of a franking mark or other indication of a transport charge, the item being marked with this franking mark or other indication.

• ein Freimachungsvermerk, der nach dem ersten Messen und vor dem weiteren Messen auf den Gegenstand aufgebracht wird,
• eine Entwertung eines Freimachungsvermerks, mit dem der Gegenstand versehen ist,
• ein Werbeaufdruck, der nach dem ersten Messen aufgebracht wird,
• ein Transportvermerk,
• eine Kennzeichnung einer Zieladresse, an dem der Gegenstand zu transportieren ist, wobei diese Kennzeichnung nach dem ersten Messen aufgebracht wird,
• ein Vermerk über das Ergebnis einer Sicherheitsprüfung oder einer sonstigen Inhaltskontrolle, wobei der Gegenstand dieser Sicherheitsprüfung unterzogen wurde, nachdem er zum ersten Mal gemessen wurde.

The optically detectable element is z. B.

• a franking mark applied to the article after the first measurement and before further measurement,
• a cancellation of a franking mark affixed to the item,
• an advertisement printed after the first measurement,
• a shipping note,
• an identification of a destination address at which the article is to be transported, this marking being applied after the first measurement,
• a note of the result of a safety check or other content inspection, subject to the safety test after it has been measured for the first time.

In one embodiment, the optically detectable element is "calculated" into the computer-accessible image of the object, and the feature values are generated by evaluating this supplemented image.

In another embodiment, the effect of the optically detectable element in the feature values is "calculated".

In one embodiment, each item is already provided with information on a destination before the first decision process. The object is to be transported to this destination. The destination information acts as a transport attribute. Preferably, such properties of the object are used as transport attributes, which can be measured with such great effort that the identification of the object and the determination of the data set are faster than the re-measurement of the transport attribute.

In another embodiment, the object is provided with information about the destination after the first decision process and before the further decision process. These destination information acts as the optically detectable element. A list with destination information is specified. As a transport attribute z. As weight, dimensions and / or logos and other graphical and / or textual elements on the surface of the article.

This embodiment can be used in particular to transport a lot of similar objects to different destinations, z. B. many copies of a copy of a magazine to different addressees. A sender delivers the copies without delivery addresses and also a computer-accessible list with the delivery addresses of the recipients of these bulk mailings. A transport service provider provides the items with the delivery addresses during transport and after the first measurement so that a delivery person can correctly deliver the items. Preferably, both the first image and each additional image of the article are generated while illuminating the article with light in the visible region. Preferably, the same defined and reproducible environmental condition is established for each illumination of the object, e.g. B. a darkened room and a lighting with white light.

The invention can be z. B. for the transport of mail, baggage items of travelers, containers or other items of freight or for workpieces in a manufacturing plant.

Fig. 1 :

eine Anordnung mit zwei Sortieranlagen und einer zentralen Datenbank,

Fig. 2 :

den Durchlauf einer Postsendung durch die erste Sortieranlage,

Fig. 3

den Durchlauf einer Postsendung durch die zweite Sortieranlage,

Fig. 4

die Berechnung eines ergänzten Abbilds aus einem Abbild ohne optisch erfassbares Element und

Fig. 5

die Verwendung eines Eliminations-Bereichs ("blinder Fleck").

In the following the invention will be described with reference to an embodiment. Showing:

Fig. 1:

an arrangement with two sorting systems and a central database,

Fig. 2:

the passage of a mail item through the first sorting system,

Fig. 3

the passage of a mail item through the second sorting system,

Fig. 4

the calculation of a supplemented image from an image without optically detectable element and

Fig. 5

the use of an elimination region ("blind spot").

In the exemplary embodiment, the method according to the solution is used to control the transport of mailpieces (letters, large letters, postcards, catalogs, parcels, etc.). Each item of mail is provided with a respective identification of the destination at which this item of mail is to be transported. This destination is a postal address or other location of the earth's surface, e.g. B. Geo coordinates.

It is possible that the item of mail is provided with a destination marking only in the course of transporting. For example, a print shop supplies many similar copies of a mass mailing without specifying the destination and also provides a computer-accessible list of the destinations to which these bulk mailings are to be delivered.

In the exemplary embodiment, each mail item by means of suitable means of transport, for. B. by means of containers, in suitable vehicles on rail, road and / or transported by air. During this transport, each mail item first passes through an alignment device and then at least twice a sorting system. The alignment device aligns each mailpiece and orients it. After aligning and orienting, the text box with the destination address of each mail item points to the same page and so that the characters are upright, not upside down. The franking mark also points to this page. Each mail item is oriented so that the franking mark is located near the leading edge, as seen in the transport direction. The later mentioned printhead is also on this page.

The sorting system of the first pass is responsible for the location at which the mailpiece was delivered. The sorting system of the second pass is responsible for the destination of the mailing. Of course, this destination point is determined only on the first pass by the first sorting system deciphering the destination point information on the mailpiece or evaluating the computer-accessible list. If the same sorting system is responsible for the place of delivery and for the destination point, then the mail item passes through the same sorting system twice, but is configured differently during the second pass than during the first pass.

Fig. 1 illustrates this arrangement. The three mail items Ps-1, Ps-2, Ps-3 first pass through the first sorting system Anl-1 and then through the second sorting system Anl-2. The first sorting system Anl-1 points

• eine Datenverarbeitungsanlage DVA-1 und
• mehrere Sortierausgänge ("sorting outlets") Aus-1.1, Aus-1.2, ...

auf. Die zweite Sortieranlage Anl-2 weist

• eine Zuführeinrichtung ZE-2 mit einem Vereinzeler,
• eine Datenverarbeitungsanlage DVA-2 und
• mehrere Sortierausgänge Aus-2.1, Aus-2.2, ...

auf.a feeder ZE-1 with a singulator,

• a data processing system DVA-1 and
• several sorting outputs ("sorting outlets") Aus-1.1, Aus-1.2, ...

on. The second sorting system Anl-2 points

• a feeder ZE-2 with a separator,
• a data processing system DVA-2 and
• several sorting outputs Aus-2.1, Aus-2.2, ...

on.

Each mail item Ps-1, Ps-2, Ps-3 is fed by means of the feeder ZE-1 of the first sorting system Anl-1 and passes through this first sorting system Anl-1 in the first pass. The first sorting system Anl-1 discharges each mail item into a sorting output Aus-1.2, Aus-1.2, .... In this case, the first sorting system Anl-1 makes a first decision process for each mail item in order to automatically decide in which sorting output Aus-1.2, Aus-1.2,... This mail item is rejected.

The mail items from a sorting output are transported to the same second sorting system Anl-2 and pass through this second sorting system Anl-2 in a second sorting pass. Which sorting system is this second sorting system can vary from mailing to mailing. Each mail item is fed by means of the feeder ZE-2 of the second sorting system Anl-2 and passes through this second sorting system Anl-2 in the second pass. The second sorting system Anl-2 discharges each mail item into a sorting output Aus-2.1, Aus-2.2, .... Here, the second sorting system Anl-2 meets for each mail item in each case a further decision process in order to automatically decide in which sorting output Aus-2.2, Aus-2.2, ... this mail item is discharged during the second pass.

• Mindestens ein rechnerverfügbares Abbild von einer Oberfläche der Postsendung wird erzeugt. Dieses rechnerverfügbare Abbild zeigt die Zielpunkt-Kennzeichnung, mit der die Postsendung versehen wird oder versehen ist.

On the first pass, the following steps are performed for each mail item Ps-x:

• At least one computer-accessible image of a surface of the mailpiece is generated. This computer-accessible image shows the destination mark with which the mail item is provided or provided.

The image with the destination marking is evaluated. For this purpose, an OCR unit first tries to automatically decipher the destination mark in the image of the mailpiece. OCR means "optical character recognition". Preferably, the OCR unit has a read access to an address database with identifications of valid destination points, e.g. B. Identification of all postal addresses of a country. The OCR unit resolves ambiguity in deciphering as well as address information errors by matching the deciphering result with the address database.

If the OCR unit fails to decipher the destination designation automatically, the image is transmitted to a video coding station and displayed on a video display device of this video coding station. An editor reads the destination mark on the display device and enters at least a portion of the read destination mark into an input device, e.g. For example, the postal code or the "ZIP Code".

A data record for the mailpiece is generated and stored in a central database or other central data memory. The first sorting system Anl-1 triggers this process. As a result, the item of mail is registered in the central database. Each sorting system through which the mailpiece runs has read access to this central database.

In the example of Fig. 1 For example, each data processing system DVA-1, DVA-2 of the sorting systems Anl-1, Anl-2 is connected to the central database DB as the central data store. The data processing system DVA-1 of the first sorting system Anl-1 generates in each case a data record for each mail item Ps-1, Ps-2, Ps-3. The data processing system DVA-2 of the second sorting system Anl-2 determined by a read access the respective data record for a continuous mail item, which is stored in the central database DB.

This record includes a unique identifier ("ID") for the mailpiece and an encoding of the deciphered destination tag. In one embodiment, the data record additionally includes the computer-accessible image of the mailpiece. The destination marking of a mail item acts as a transport attribute, the value of which depends on the further transport of the item of mail and whose measuring is time-consuming.

It is possible that the values of further transport attributes are measured on the first pass. For example, it is determined which value the franking mark (stamp, postage meter, matrix code, or the like) has on the mailpiece. A mail piece that is sufficiently franked should be transported to the specified destination address. By contrast, a postal item that is not sufficiently franked should be removed from ordinary processing and subjected to special treatment. This rejection can also be carried out only on the second pass through a sorting system.

Or the mail piece is weighed and / or the dimensions of the mail piece are measured. The weight or a measurement is z. B. required to spend the mail in a suitable means of transport and / or transport to a suitable further sorting system and to make a proper choice or the weight and dimensions are also used to pay the actually paid transport fee with a target Compare transport fee.

For example, only one of the sorting systems used has a color camera or a scale. However, the colored computer-accessible image or the measured weight should be available to all sorting systems.

Codings of these further measured transport attribute values are also stored as part of the data record for the mail item in the central database.

In one embodiment, a plurality of similar bulk shipments are supplied without destination information and a list of destination markings is transmitted to the transporter. In this embodiment, preferably an image of such a mass transmission is generated and used for all similar mass transmissions. Such a procedure is over DE 10 2007 038 186 B4 known. For each mass mailing, a record is created for each of which the list of destination tagging is used.

• eine OCR-Einheit OCR,
• eine Kamera Ka-1,
• einen Drucker Dr,
• einen Entwerter ("canceler") Ent,
• ein Etikettiergerät ("labeler") Lab,
• eine Auswerteeinheit AE-1,
• eine Muster-Datenbank ("pattern database") Mu-DB,
• eine Steuerungseinheit ("control unit") SE,
• eine Waage Waa und
• einen Freimachungsvermerk-Auswerteeinheit Fm-AE.

Fig. 2 illustrates the passage of the mail items Ps-x through the first sorting system Anl-1. The mail item Ps-x is transported in a transport direction T. The first sorting system Anl-1 comprises

• an OCR unit OCR,
• a camera Ka-1,
• a printer Dr,
• a canceler Ent,
• a labeler Lab,
• an evaluation unit AE-1,
• a pattern database Mu-DB,
• a control unit ("control unit") SE,
• a scale Waa and
• a franking evaluation unit Fm-AE.

• eine Kennzeichnung der Zieladresse Add-x und
• einen Freimachungsvermerk Fm-x

auf der Postsendung Ps-x.While the mail items Ps-x in the first pass through the first sorting system Anl-1, the camera Ka-1 generates a computer-accessible image Abb-x1 from a surface of the mail item Ps-x. This image fig-x1 shows

• an identification of the destination address Add-x and
• a franking mark Fm-x

on the mailing Ps-x.

The OCR unit OCR evaluates this image Abb-x1 to decipher the destination address Add-x. An encoding of the deciphered Destination address Add-x is stored as part of the data record for the mail item Ps-x in the central data memory DB.

The balance Waa weighs the mail item Ps-x and thereby determines the weight Gew-x of the mail item Ps-x. The postage indicium evaluation unit Fm-AE determines which fare has been paid for the transport of the mail item Ps-x. For this purpose, the franking mark evaluation unit Fm-AE evaluates the franking mark Fm-x, which the image Abb-x1 shows. If necessary, the franking mark evaluation unit Fm-AE compares this determination result with the measured weight and / or the measured dimensions of the mail item Ps-x.

It would be impractical to measure the transport attributes again with each new pass of a mail item through a sorting system. Therefore, the centrally stored transport attribute values measured during the first pass are reused. However, this presupposes that the mail item is identified each time it is run again. The identification takes less time to re-measure reliable transport attributes.

In the exemplary embodiment, the mail item Ps-x should not be printed with an identifier for the mail item itself nor with a coding of a transport attribute value. In particular, no sorting code is to be printed on the mailpiece. This saves printer liquid and labels as well as a bar code reader, and avoids sometimes undesirable changes to the mail item. Furthermore, the step is saved to search for a printable area for printing a bar pattern.

• die Verteilung von Grauwerten und/oder Farbwerten auf der gesamten Oberfläche oder auf einem bestimmten Bereich der Oberfläche der Postsendung, z. B. eines Quadranten,.
• die Anzahl von Textblöcken,
• die Lage und/oder die Größe des Adressblocks oder der Adressblöcke (Adressat, Absender),
• die Lage und/oder die Größe des Freimachungsvermerks,
• ein entzifferter Bestandteil der Zieladresse, z. B. die Postleitzahl, wobei dieser entzifferte Bestandteil nur eines von insgesamt n Merkmalen ist,
• die Anzahl von graphischen Elementen, z. B. Logos oder Werbeaufdrucke, die Lage und/oder die Größe oder Farbe jedes Logo- oder Werbeaufdrucks auf der Postsendung und
• das Vorhandensein und ggf. die Lage und/oder die Größe eines Sichtfensters der Postsendung.

Therefore, the mail item is identified on each further pass on the basis of a vector with values of optically detectable features. These feature values are measured by evaluating a computer-accessible image of the mailpiece. Examples of such optically detectable features are:

• the distribution of gray levels and / or color values on the entire surface or on a certain area of the surface of the mailpiece, z. B. a quadrant ,.
• the number of text blocks,
• the location and / or the size of the address block or the address blocks (addressee, sender),
• the location and / or size of the franking mark,
• a deciphered part of the destination address, e.g. The postal code, this deciphered component being only one of a total of n features,
• the number of graphical elements, e.g. As logos or advertising imprints, the location and / or the size or color of any logo or advertising print on the mailpiece and
• the presence and possibly the position and / or the size of a viewing window of the mailpiece.

In one embodiment, a computer-accessible grid is laid over the computer-accessible image of the surface. Each distribution of color values and each distribution of gray values in a rectangle formed by this grid is a unique feature.

During the first pass of a mail item Ps-x, for each optically detectable feature it is first measured which value this feature assumes for the mailpiece. As a result, a feature value vector is obtained. For n predetermined features to be measured, this vector usually comprises n feature values. The data record for the mail item Ps-x, which is stored in the central database DB, comprises the feature value vector which was obtained on the first pass of the mail item Ps-x. This feature value vector is hereinafter referred to as "registration feature value vector".

Fig. 2 illustrates the steps that performs the evaluation unit AE-1 in the evaluation of the image. The computer-accessible image Abb-x1 is transmitted on the one hand to the OCR unit and on the other hand to the evaluation unit AE-1 of the first sorting system Anl-1. The evaluation unit AE-1 evaluates the Image Abb-x1 and generates the registration feature value vector RMV-x for the mail item Ps-x.

The evaluation unit AE-1 also determines the position of the franking mark Fm-x on the mail item Ps-x. The evaluation unit AE-1 transmits a corresponding message to the control unit SE. This message includes in computer-available form a plurality of position information Pos-x, which describe the dimensions of the mail piece Ps-x and the position of the franking mark Fm-x on the surface of the mail item Ps-x. The position information Pos-x also describe the position of the marking of the destination address Add-x on the surface and a desired position for a still to be generated advertising print W-x to the left of the franking mark Fm-x.

The control unit SE controls the validator Ent, the printer Dr and, if necessary, the labeller Lab. The validator Ent invalidates the franking mark Fm-x with a stamp imprint St-x. The printer prints an advertising print W-x on the mail item Ps-x. For this purpose, the control unit SE generates corresponding control commands and uses the position information Pos-x. For example, a desired position of each imprint with respect to the front edge and the top edge of the mail item Ps-x is calculated, for which purpose a computer-accessible general specification as well as the actual position of the franking mark Fm-x are used. The target position z. Example, the respective distance of each imprint of the upper edge and the leading edge of the mail item Ps-x firmly. The sample database Mu-DB each delivers a computer-accessible print template for the stamp print St-x and the advertising print W-x. In one embodiment, a light barrier arrangement measures the position of the leading edge and the top edge of a mailpiece. The control device SE generates the control commands so that the imprint is printed on the position relative to the leading edge and the upper edge, which is predetermined by the desired position.

In particular, when the recipient of the mailing Ps-x a forwarding order ("re-forwarding order, change of address information "), the mail item Ps-x is to be sent to a different destination address Add-x-new than to the original destination address Add-x, in which case the printer Dr additionally prints a label of the new address Add-x New on the mail item Ps-x If a direct printing on the mail item Ps-x is not possible, the Lab labeller produces a label with a label of Add-x-new and brings the printed label on the Mailing Ps-x on.

• der Registrierungs-Merkmalswerte-Vektor RMV-x,
• das gemessene Gewicht Gew-x,
• das ermittelte Beförderungsentgelt Bef-x für die Postsendung Ps-x und
• in einer Ausgestaltung die Positions-Informationen Pos-x.

In the exemplary embodiment, the following information is additionally stored in the central data memory DB as part of the data record for the mail item Ps-x:

• the registration feature value vector RMV-x,
• the measured weight Gew-x,
• the determined transport fee Bef-x for the mail item Ps-x and
• in one embodiment, the position information Pos-x.

During each further passage of the mail item Ps-x through a sorting system Anl-2, a computer-accessible image of the mail item is again generated and evaluated. The evaluation again measures for each optically detectable feature which value this feature assumes for the mailpiece. This feature value vector with also n feature values is used to identify the record for the Possendung in the central data memory DB and thus the mail item, and is therefore referred to as "identification feature value vector". The second sorting system Anl-2 does not use an OCR unit in order to automatically decide on the further transport of the mailing during the further decision process.

Fig. 3 illustrates the passage of the mail piece Ps-x through the second sorting system Anl-2. A camera Ka-2 of the second sorting installation Anl-2 generates another computer-accessible image Abb-x2 from the surface of the mail item Psx. An evaluation unit AE-2 of the second sorting system Anl-2 evaluates this image Abb-x2 and generates an identification feature value vector IMV-x for the mail item Ps-x. The identification feature value vector IMV-x is compared with registration feature value vectors stored in the central database DB.

Because many millions of postal items are transported daily in Germany alone, it would take far too long to compare the identification feature value vector IMV-x for the mail item Ps-x with all the registration feature value vectors stored in the central database DB are. Therefore, a method is preferably used to restrict the search space among the data records in the central database DB. Such methods are for. B. off EP 1222037 B1 . DE 10 2008 017191 A1 and DE 10 2008 017190 A1 known. The search space constraint significantly reduces the amount of stored registration feature value vectors with which an identification feature value vector IMV-x is compared.

In the comparison between the identification feature value vector IMV-x and a stored registration feature value vector RMV-y, it is preferable to calculate a match measure between these two feature value vectors IMV-x and RMV-y. The stored registration feature value vector having the largest coincidence with the identification feature value vector IMV-x from the mail item Ps-x is used as the registration feature value vector RMV-x of this mail item Ps-x.

The data record to which the found registration feature value vector RMV-x belongs with the largest match measure is determined. This data set comprises the destination point identification of the mail item Ps-x and, in one embodiment, further transport attribute values which were measured during the first pass. These transport attribute values are used to carry out the further decision process on how to forward the mail item Ps-x.

Each sorting system has multiple sorting outlets, e.g. B. sorting compartments. In Fig. 1 sorting outputs Aus-1.1, Aus-1.2, ..., Aus-2.1, Aus-2.2, ... of the two sorting systems Anl-1, Anl-2 are illustrated. Each sorting system Anl-1, Anl-2 respectively evaluates a computer-available sorting plan, which assigns each possible or actually occurring destination marking in each case to a sorting output of the sorting system used. The sorting system discharges each item of mail according to this sorting plan into that sorting output which is associated with the destination item identification on the item of mail. On the second and each subsequent pass, the sorter uses the destination point identifier of the determined record to select a sort exit.

• Ein Freimachungsvermerk auf der Postsendung wird entwertet. Beispiele für einen Freimachungsvermerk sind eine Briefmarke, ein Freistempler oder eine Matrixcode mit einer Codierung eines Bezahlvorgangs. Diese Entwertung wird durchgeführt, nachdem der Freimachungsvermerk ausgewertet wurde, wofür das erste Abbild der Postsendung Ps-x ausgewertet wurde. Dieses erste Abbild zeigt den noch nicht entwerteten Freimachungsvermerk. Die Entwertung hängt in einer Ausgestaltung davon ab, ob die Postsendung mit einem ausreichenden Freimachungsvermerk versehen wurde oder nicht. Außerdem könnte der Stempelaufdruck die Auswertung des Abbilds erschweren. Ob das tatsächlich entrichtete Ist-Entgelt, welches durch Auswertung des Freimachungsvermerks ermittelt wurde, für den Transport der Postsendung ausreicht, hängt von mehreren Transport-Attribut-Werten ab, z. B. die Zielpunkt-Kennzeichnung (Postsendungen ins Inland oder ins Ausland), das gemessene Gewicht und/oder Abmessungen der Postsendung.

In the exemplary embodiment, some or even all mailpieces are provided with at least one optically detectable element, after the first time a computer-accessible image of the mailpiece has been generated. Examples of such optically detectable elements are:

• A franking mark on the mailing is canceled. Examples of a franking mark are a postage stamp, a postage stamp or a matrix code with a coding of a payment transaction. This devaluation is carried out after the franking mark has been evaluated, for which purpose the first image of the mail item Ps-x has been evaluated. This first image shows the not yet validated franking mark. In one embodiment, the cancellation depends on whether or not the item of mail has been provided with a sufficient franking mark. In addition, the stamp imprint could complicate the evaluation of the image. Whether the actually paid actual remuneration, which was determined by evaluating the franking mark, is sufficient for the transport of the mailpiece depends on several transport attribute values, eg. For example, the destination marking (domestic or foreign mail), the measured weight and / or dimensions of the mailing.

A copy of a previously unaddressed mass mailing is provided in one embodiment after the first measurement with a destination marking. This destination mark is taken from a computer-accessible list of destination markings that the sender has transmitted to the carrier.

After the destination point label has been deciphered, this destination point identifier is compared to entries in a forwarding file or a forwarding data store. In this forwarding file entries are registered about address changes of recipients of mail, z. Due to resend requests from recipients because a recipient has rented a mailbox or parcel compartment, or because a company has renamed, moved or has been disbanded. If a mail item is to be forwarded or has to be returned to the sender, the previous destination item identifier is replaced by a new one, e.g. As an identification of the new address of the recipient or the sender address. Either the new address is printed directly on the mail piece or a label with the new address is printed on the mail piece. The use of a label in particular required when the mailpiece is wrapped in a clear plastic film and this film stick to, but can not print. Examples of such methods are out US 5,703,783 and from EP 1656217 B1 known.

• den Stempel St-x auf dem Freimachungsvermerk Fm-x,
• den Werbeaufdruck W-x und
• der Kennzeichnung der neuen Zieladresse Add-x-neu.

In the example of Fig. 2 For example, the postal item Ps-x is provided with the following three optically detectable elements:

• the stamp St-x on the franking mark Fm-x,
• the advertising imprint Wx and
• the identification of the new destination add-x-new.

• ein rechnerverfügbares Muster des Aufdrucks, z. B. eine Pixel-Datei mit einem Logo oder eine Folge von alphanumerischen Zeichen, verbunden mit Farb- und Formatierungsinformationen, sowie
• eine Festlegung derjenigen Position, an der dieser Aufdruck bzw. dieses Etikett auf die Postsendung aufzubringen ist.

This at least one optically detectable element is automatically applied by a printer Dr during the first pass of the mail item Ps-x through a sorting system and after the camera Ka-1 has produced an image of the mail item Ps-x. The printer Dr is given the following:

• a computer-available pattern of the imprint, e.g. As a pixel file with a logo or a sequence of alphanumeric characters, combined with color and formatting information, as well
• a determination of the position at which this imprint or this label is applied to the mailpiece.

Each optically detectable element is printed according to the computer-available pattern Mu-x by a printer Dr or a Lab labeller at the point on the mail item Ps-x, which is defined by the position-fixing Pos-x. A light barrier preferably detects when a front edge or front surface of the mail item Ps-x has reached a specific position when passing through the sorting system. In addition, the transport speed with which the mail item is transported is measured. The control unit SE controls the printer Dr or the labeller Lab depending on signals of the light barrier and the transport speed and transmits the pattern Mu-x and the position-fixing Pos-x to the printer. Preferably, the printer Dr is designed as a wide-area printer, so that the printer Dr can print elements at different heights on a surface of the vertical mail piece.

Each time it passes through a sorting system, the mail item has the optically detectable element. Each further computer-accessible image of the mailpiece therefore shows the optically detectable element. Therefore, the effect of the optically detectable element on the feature value vectors of the mail item is taken into account. There are several possible configurations for this.

In one embodiment, a supplemented computer-accessible image is calculated from the first image of the mail item Ps-x. An image of the optically detectable element is computationally mounted in the first image. For this mounting, the computer-available pattern as well as the position fixing are used used. If required, a magnification is also taken into account. This magnification is part of the artwork and takes into account the possibility that the given pattern is a factor smaller or larger than the actual imprint.

For example, both the first image Abb-x1 of the mail item Ps-x and the computer-available pattern Mu-x for the optically detectable element are each composed of many pixels ("pixels"). Each pixel is assigned an encoding of a color value in each case. When "mounting in" a resulting color value is calculated from the color value of a pixel of the first image Abb-x1 and from the color value of the corresponding pixel of the pattern Mu-x and used as the color value of the pixel of the supplemented image Abb-x1-erg. The pattern is thus calculated pixel by pixel in the first image.

The registration feature value vector RMV-x is calculated by evaluating the thus supplemented image and determining for each optically detectable feature what value the supplemented image for that feature assumes. The n feature values are calculated in the same way as for the other image.

• das erste Abbild Abb-x1 der Postsendung Ps-x, welches von der Kamera Ka-1 geliefert wurde,
• die rechnerverfügbaren Positionsinformationen Pos-x für den Stempelaufdruck St-x und den Werbeaufdruck W-x sowie
• die rechnerverfügbaren Muster Mu-x für den Stempelaufdruck St-x und den Werbeaufdruck W-x aus der Muster-Datenbank Mu-DB.

Fig. 4 illustrates the calculation of the supplemented computer-accessible image Abb-x1-erg by the evaluation unit AE-1 of the first sorting system Anl-1. The evaluation unit AE-1 uses for this calculation

• the first image Abb-x1 of the mail item Ps-x, which was supplied by the camera Ka-1,
• the computer-accessible position information Pos-x for the stamp imprint St-x and the advertising imprint Wx as well
• the computer-available patterns Mu-x for the stamp imprint St-x and the advertising imprint Wx from the pattern database Mu-DB.

The first evaluation unit AE-1 generates the registration feature value vector RMV-x by the first evaluation unit AE-1 evaluates the supplemented image Abb-x1-erg and not the first image Abb-x1.

In another embodiment, an output feature value vector is generated from the first image of the mail item Ps-x. Because the first image Abb-x1 does not show the optically detectable element, the output feature value vector does not take into account the effect of this optically detectable element. A supplemented feature value vector is then calculated from the output feature value vector and used as registration feature value vector RMV-x. This supplemented feature value vector contains for each feature the value that the feature for the mail item Ps-x will assume after the application of each optically detectable item Pos-x. In order to calculate this supplemented feature value vector, the position fix Pos-x and the element pattern Mu-x are used.

How a feature value of the supplemented feature value vector is calculated depends on the feature. Some features are not affected by the application of the optically detectable element, so that the value remains identical. This applies in particular if the feature relates exclusively to a first area of the mail item, the optically detectable element is printed on a second area and these two areas do not overlap. For many other features, the value of the feature for the mailpiece having the optically detectable element is equal to the sum of the feature value excluding the optically detectable element plus a value that the feature assumes when the optically detectable element is applied to a neutral mailpiece at the same location would be, for. B. on a completely white mail piece. This neutral mailpiece acts as a reference item. This additivity of the two feature values is especially true if the feature is a color value or gray value distribution.

In a third embodiment, that region of the surface of the mail item in which the optically detectable element is located is made up of the registration and the identification the mailing hidden ("blind spot"). For this purpose, a determination of a region of the surface is predetermined or determined, which completely covers the optically detectable element, so that the optically detectable element is completely within the predetermined range. This area is z. For example, a rectangle or an ellipse. For example, the range setting is derived from the position setting and the element pattern. The area setting defines the position and dimensions, and preferably a color, e.g. B. white, fixed.

Fig. 5 illustrates how two reduced images are calculated using a "blind spot" bF. The first evaluation unit AE-1 calculates a first reduced image Abb-x1-red from the first image Abb-x1 of the mail item Ps-x, generated by the first camera Ka-1, and calculates the registration feature value vector RMV-x for the mail item Ps-x from this first reduced image Abb-x1-red. The second evaluation unit AE-2 calculates a second reduced image Abb-x2-red from the second image Abb-x2 of the mail item Ps-x, generated by the second camera Ka-2, and calculates the identification feature value vector IMV-x for the mail item Ps-x from this second reduced image Abb-x2-red. In one embodiment, the contour of the mail item Ps-x - seen from the direction from which the images are made by the mail item Ps-x - mirror-symmetrical about at least one axis, z. B. is a rectangular contour. The overlapping region is preferably also symmetrical about this axis of symmetry. For example, the area consists of four rectangles, which are arranged symmetrically in the four corners of a rectangular mail piece.

In one embodiment, this area is computationally mounted in each image Abb-x1, Fig-x2 of the mail item Ps-x, in such a way that the area is calculated at the predetermined position in the image into it. This area completely covers the image of the optical element. Each feature value vector is taken from the image in which the area is the Image covered by the optically detectable element, calculated. As a result, the optically detectable element is mathematically removed from the images.

In another embodiment, as described above, an initial feature value vector is first calculated from the respective image of the mail item Ps-x. The first image of the mailpiece shows the surface of the mailpiece without the optically detectable element, each additional image additionally this optically detectable element. The output feature value vector is computationally changed. For this purpose, it is calculated for each optically detectable feature what value this feature would assume for the mail item if the surface of the mail item had the area instead of the optically detectable element. The modified feature value vector is used as a registration feature value vector or as an identification feature value vector. LIST OF REFERENCE NUMBERS reference numeral importance Abb-x1-erg supplemented computer-accessible image of the mail item Ps-x is calculated from the first image Abb-x1 and the position information Pos-x and the pattern Mu-x Abb-x1-red reduced first image of the mail item Psx, is calculated from the first image Abb-x1 by means of the "blind spot" bF Abb-x2-red reduced second image of the mail item Psx, is calculated from the second image Abb-x2 by means of the "blind spot" bF Abb-x1 computer-accessible image of the mail item Ps-x, generated by the camera Ka-1 on the first pass Abb-x2 computer-accessible image of the mail item Ps-x, generated by the camera Ka-2 on the second pass Add-x Destination address of the mail item Ps-x Add-X new new destination address of the mail item Ps-x AE-1 Evaluation unit of the first sorting system Anl-1 AE-2 Evaluation unit of the second sorting system Anl-2 Anl-1 first sorting plant Anl-2 second sorting plant Aus-1.1, Aus-1.2, ... Sorting outlets of the first sorting plant Anl-1 Aus-2.1, Aus-2.2, ... Sorting outlets of the second sorting plant Anl-2 Cmd-x determined fare on the mailing Ps-x bF "blind spot", computer-accessible description of an elimination area to ignore DB central data memory with data records for the mail items, stored in the central database DB Dr Printer of the first sorting plant Anl-1 DVA-1 first data processing system, belongs to the first sorting plant Anl-1 DVA-2 first data processing system, belongs to the first sorting plant Anl-1 Ent Validator of the first sorting plant Anl-1 Fm-AE Postage paid evaluation unit of the first sorting system Anl-1 Fm-x Postage stamp on the mailing Ps-x Weight-x Weight of mailing Ps-x IMV-x Identification feature value vector Ka-1 Camera of the first sorting plant Anl-1 Ka-2 Camera of the second sorting plant Anl-2 rennet Labeler of the first sorting plant Anl-1 Mu-DB Sample database with computer-accessible print templates Mu-x Computer-available pattern for stamp printing St-x and for advertising imprint Wx OCR OCR unit of the first sorting plant Anl-1 Pos-x Position information for the stamp imprint St-x and the advertising imprint Wx on the mail item Ps-x Ps-x, Ps-1, Ps-2, ... mail to be sorted RMV-x Registration feature value vector of mail item Ps-x SE Control unit of the first sorting system Anl-1 St-x Stamp imprint on the franking mark Fm-x on the mailing Ps-x T Transport direction, in which the mail item Ps-x is transported Waa Balance of the first sorting plant Anl-1 Wx Advertising print on the mailing Ps-x ZE-1 Feeding device of the first sorting system Anl-1 ZE-2 Feeding device of the second sorting system Anl-2

Claims (8)

1. Method for transporting an object (Ps-x) to a target point, wherein at least one optically detectable feature and at least one transport attribute are predetermined,
   the transportation comprises a first decision process and at least one further subsequent decision process about the respective continuation of the transportation,
   the first decision process comprises the automatically performed steps in which

   - a first computer-accessible image (Abb-x1) of the object (Ps-x) is generated,

   - for each predetermined feature a measurement is taken for the first time to determine the value which said feature assumes for the object (Ps-x), for which the at least one first object image (Abb-x1) is evaluated,

   - for each transport attribute a measurement is taken to determine the value (Add-x) which said transport attribute assumes for the object (Ps-x),

   - a data record is generated for the object (Ps-x) and is stored in a data memory (DB), wherein the data record comprises a vector (RMV-x) with the measured feature values and the at least one measured transport attribute value (Add-x), and

   - the first decision process is taken as a function of the at least one measured transport attribute value (Add-x),

   the object (Ps-x) is transported further as a function of the outcome of the first decision process,
   the further decision process comprises the automatically performed steps in which

   - a further computer-accessible image (Abb-x2) of the object (Ps-x) is generated,

   - for each predetermined feature a new measurement is taken to determine the value which said feature assumes for the object, for which the further computer-accessible object image (Abb-x2) is evaluated,

   - the data record generated for said object (Ps-x) and stored in the data memory (DB) is determined, for which the measured feature value vector (IMV-x) measured during the new measurement is used to search for the data record in the data memory (DB),

   - the at least one transport attribute value (Add-x), which is comprised of the determined data record, is determined, and

   - the further decision process is taken as a function of the at least one determined transport attribute value (Add-x) and

   the object (Ps-x) is transported further as a function of the outcome of the further decision process,
   wherein after the first measurement and before the new measurement the surface of the object (Ps-x) is provided with at least one optically detectable element (St-x, W-x), characterised in that
   for the step of providing the surface with the optically detectable element (St-x, W-x)

   - a predetermined computer-accessible localisation of the position of the element (St-x, W-x) on the surface of the object (Ps-x) and

   - a predetermined computer-accessible pattern (Mu-x) of the element (St-x, W-x)

   are used,
   the feature value vector (RMV-x) generated during the first decision process and stored as part of the data record is generated such that
   for every feature said feature value vector (RMV-x) contains that value
   which the feature would assume for the object (Ps-x) if the surface of the object (Ps-x) had already been provided with the optically detectable element (St-x, W-x) during the first measurement,
   wherein for the step of generating said feature value vector (RMV-x), the position localisation and the element pattern are used, and
   at least one further image (Abb-x2), which is evaluated for the new measurement, is generated by the object (Ps-x) provided with the element (St-x, W-x).
2. Method according to claim 1,
   characterised in that
   the step of generating the feature value vector (RMV-x) to be stored in the data memory (DB)
   comprises the steps in which

   - the first computer-accessible image (Abb-x1) is generated by the object (Ps-x) without the optically detectable element (St-x, W-x),

   - a supplemented image (Abb-x1-erg) of the object (Ps-x) is calculated, which shows what the object (Ps-x) will look like after the surface of the object (Ps-x) has been provided with the element (St-x, W-x),
   for which the first computer-accessible image (Abb-x1) is used, and

   - the feature value vector (RMV-x) is generated by evaluating the supplemented image (Abb-x1-erg).
3. Method according to claim 2,
   characterised in that
   for at least one of the two steps

   - of generating the supplemented image (Abb-x1-erg) or

   - of generating the feature value vector (RMV-x) by evaluating the supplemented image (Abb-x1-erg),

   the following information is used:

   - the position localisation and/or

   - the element pattern (Mu-x).
4. Method according to one of claims 1 to 3, characterised in that
   the step of generating the feature value vector (RMV-x) to be stored in the data memory (DB)
   comprises the steps in which

   - the first computer-accessible image (Abb-x1) is generated by the object (Ps-x) without the optically detectable element,

   - an output feature value vector is generated by evaluating said first image (Abb-x1), and

   - a supplemented feature value vector is calculated such that for each feature the supplemented feature value vector contains that value which the feature will assume for the object (Ps-x) after the surface of the object (Ps-x) has been provided with the optically detectable element (St-x, W-x),
   wherein the supplemented feature value vector is calculated using the output feature value vector.
5. Method according to claim 4,
   characterised in that
   for the step of calculating the supplemented feature value vector,

   - the output feature value vector,

   - the position localisation and

   - the element pattern

   are used.
6. Method according to claim 4 or claim 5,
   characterised in that
   for at least one feature the value for the object with the optically detectable element is calculated as the sum of

   - the value for the object (Ps-x) without the optically detectable element (St-x, W-x) and

   - the value which a reference object assumes when the reference object is provided with the optically detectable element (St-x, W-x) using the position localisation and the element pattern.
7. Method according to one of claims 1 to 6, characterised in that
   a computer-accessible localisation of an elimination region (bF) of the surface of the object (Ps-X) is predetermined, wherein the optically detectable element (St-x, W-x) lies completely in said elimination region (bF),
   the feature value vector (RMV-x) to be stored in the data record is generated such that
   for each feature the stored feature value vector (RMV-x) contains that value
   which the feature would assume if the elimination region (bF) was removed from the surface,
   the feature value vector (IMV-x) obtained during the new measurement is modified such that for each feature the modified feature value vector (IMV-x) contains the value which the feature would assume if the elimination region (bF) had been removed from the surface, and is used in the determination of the data record of the modified feature value vector.
8. Method according to claim 7,
   characterised in that
   both the first image (Abb-x1) and the further image (Abb-x2) of the object (Ps-x) are generated such that both images (Abb-x1, Abb-x2) show the respective surface, along with the elimination region (bF),
   a first elimination image (Abb-x1-red) is generated from the first image (Abb-x1), and shows the surface without the elimination region (bF),
   the feature value vector (RMV-x) to be stored is generated by evaluating the first elimination image (ABB-x1-red),
   a further elimination image (Abb-x2-red) is generated from the further image (Abb-x2), and shows the surface without the elimination region (bF) and
   the feature value vector (IMV-x) measured during the new measurement is generated by evaluating the further elimination image (Abb-x2-red).

Images