EP1344182A1

EP1344182A1 - Method and device for reading postal codes of addresses on postal articles

Info

Publication number: EP1344182A1
Application number: EP01991649A
Authority: EP
Inventors: Walter Rosenbaum
Original assignee: Siemens AG
Current assignee: Siemens AG
Priority date: 2000-12-22
Filing date: 2001-12-20
Publication date: 2003-09-17
Also published as: WO2002052489A1; CA2432610A1; DE10064226A1; DE10064226B4

Abstract

The invention relates to a method and device for reading postal codes of addresses on postal articles, in which the postal code (300) designates the address up to the portion of a major street or of a number of minor streets. When addresses could not be clearly read during a first reading attempt (310) in the OCR unit (130), the postal code is first of all divided into a part that roughly depicts the address and into a part that depicts the address more precisely. The corresponding liknesses of the postal article surfaces to these addresses are then transmitted to the video coding stations (200) where only the parts of the postal codes (300) that roughly depict the addresses are video-coded (320) by operators provided therefor and are transmitted to additional video coding stations (200) where the remaining postal codes (300) that depict the addresses more precisely are asynchronously video-coded (330) by operators provided therefor. Afterwards, the buffered, video-coded postal code parts, which respectively pertain to a particular postal article, are combined (340) to form a complete, video-coded postal code.

Description

description

Method and device for reading postal codes from addresses on mail items

The invention relates to a method and a device according to the preambles of the independent claims.

Automatic address reading (OCR) systems are well known in the field of letter processing and are e.g. described in DE 195 31 392. With modern OCR letter sorting systems, processing rates of 10 letters per second, i.e. 36,000 letters per hour and more reachable. However, the recognition reliability varies greatly with the font and overall quality of the surface

Letters applied address information. In the event of successful recognition, the letter in question can be provided with a machine-readable bar code. This bar code permits further mechanical processing up to any desired sort order. In particular, the use of bar codes enables the letters to be sorted up to the sorting level of the mailbox, in which letters are sorted by the deliverer in the order in which they are distributed.

Since the recognition rates of the automatic reading systems vary considerably, it is necessary to support them with various forms of manual intervention.

The address entered is encoded and converted into a machine-readable sortable code by means of a directory, which is applied to the shipment.

Video images of the programs are presented to operators for coding in video coding systems. This can be done online and offline. In online video coding systems (OVS), the video image is shown to the operator, while the physical see broadcast is held in delay lines. In these delay lines the shipment is normally kept in motion for a period of time sufficient for the OVS operator to enter the necessary sorting information for the image in question. The usual delay lines allow a delay between 10 and 30 seconds. The longer the delay line, the greater the costs as well as the requirements for maintenance and the physical size of the system.

When using OVS, the time available is often only sufficient for a careful entry of the postal code (PK).

In offline coding systems, as described in US Pat. No. 4,992,649, mail items with unrecognized addresses are provided with additional information, a tracking identification (TID). The unrecognized programs are stored externally, while the images of these programs are presented to operators for coding, with no temporal ones

There are restrictions. The programs are then demonstrated using TID readers. The TID is linked to the entered address information. Based on this, customary barcode sorting information can also be applied to the item, so that the item in question can be processed like items that are usually OCR-read. Although the offline video coding method is an effective method for coding all the address components, additional capacities for the further processing of items with unread addresses and correspondingly complex logistics are required.

For postcodes with> 6 characters, which describe the address up to the street or several small streets, the video coding is done with the left and right hand. The object of the invention specified in claims 1 and 11 is to shorten the video coding process for reading a postal code of a mailing address which is not clearly recognized by an OCR unit and which identifies the address at least up to the street.

This is achieved by dividing the postal code into a part that roughly describes the address and a remaining part that describes the address in more detail. Each part is video-coded by surgeons designated for this part. After an unsuccessful attempt to read the respective address by the OCR unit, the left-hand part of the postal code roughly describing the address is video-coded at a corresponding video coding location and, asynchronously, the remaining, more detailed, right-hand part of the post code is video-coded at a corresponding video coding location.

Thereafter, the temporarily stored and video-coded postcode parts belonging to the respective shipment or image are combined to form a complete, video-coded postcode.

The time for video coding each part of the postal code is less than if the entire postal code had been video-coded by an operator, since each operator only has to enter part of the characters.

Advantageous embodiments of the invention are presented in the dependent claims.

It is advantageous if the part of the postal code which roughly describes the address identifies the destination and the part of the postal code which describes the address in more detail identifies the street, partial street in the case of large streets or several small streets. In a further advantageous embodiment, the video-coded post part codes can be assigned to the respective mail items or their images using identification numbers.

For this purpose, it is advantageous to apply the identification numbers to the mail items and read them together with the addresses, it being particularly advantageous to apply the identification numbers in a machine-readable manner, in particular as a bar code.

It is also advantageous to store the recorded images of the shipment surfaces under identification numbers.

To increase the coding speed, it is advantageous to use a preview coding method in which images of several consecutive programs are displayed simultaneously on the screen.

In order to check the result of the video coding process, it is advantageous to send the complete coding result of the OCR unit to a second reading attempt including the coding result. The confirmation is then based on the address database.

The invention is then explained in more detail in an exemplary embodiment with reference to the drawings. Show

1 shows a schematic representation of a device for reading postal codes,

2 shows the procedural sequence using a flow diagram.

1 shows a schematic representation of a mail distribution system with which the method according to the invention can be carried out. The OCR letter sorter 100 consists of an additional guide device 110, which successively withdraws mail items from a magazine and transports them to a high-resolution video scanner 120 at about 10 mail items per second. The mail items are then transported in a delay line 121. The mail items usually have address information on their surface. In an OCR unit 130, the address information of the images of the programs, which were obtained from the video scanner 120, is evaluated. In the case of a complete evaluation, a bar code printer 150 is activated and the item is provided with a corresponding bar code for the subsequent sorting into sorting compartments 160. The OCR unit 130 consists of one or more microprocessors 131 with associated memory 132 to store images of the programs. Furthermore, the OCR unit contains an address database 134 with post codes, city names and street names and possibly further address-related information. When evaluating the images having address information, a feature-controlled reduction of the entry obtained from the address database 134 takes place, so that a kind of partial dictionary is generated. Credibility is assigned in individual entries so that a number of data of correctly recognized addresses are generated during the evaluation. The device further includes an image controller 170 and a number of video coding stations 200, which are connected to the image controller 170 directly or through a local area network (LAN) 171. If the OCR evaluation of an image was not, ie completely successful, this image is transferred from the OCR unit 130 to the image controller 170, which on the one hand controls the TID barcode printer 151 and on the other hand sends the corresponding image to one of the video coding locations 200. The TID barcode printer 151 applies an identification code TID to the corresponding shipment, which makes it possible at a later time to link the evaluated address information with the physical shipment. In this case, the images are preferably evaluated off-line, although in principle with a sufficiently long delay an online evaluation by video coding is also possible. In the latter case, the TID can also be applied to the mail items at a later point in time, ie if the video coding has not led to a complete evaluation within a specific predetermined time.

To carry out the further method shown in more detail, the image controller 170 is designed in such a way that the images with address information which is not clearly read by the OCR unit 130 are transmitted to two video coding stations, at each of which only part of the post code is video-coded, and that the coded post code parts of the image in question can be combined again into a complete postal code after buffering.

The recorded and stored image of the respective consignment with the address, containing a postal code 300 which identifies the destination and the street, the part of a street on large streets or several small streets, is fed to the OCR unit 130 for a first automatic reading attempt. In this example, this postal code 300 is a 6-digit code in canonical form with the following character string ANA NAN, where A is a letter (alphabetical character) and N is a number (numerical character).

The specific implementation of the postal code is of course not limited to this example.

If the address in the OCR unit 130 can be read clearly in the first read attempt 310, the recognition task is solved. If not, the image with the post code 300 for video coding the left ANA part, which characterizes the destination, is transmitted to a video coding station 200, where an operator for the left post code parts video-codes 320 the left ANA part. For this purpose, this left post code part can be specially marked on the screen of the video coding station 200, for example by a colored background o the as shown in Figure 2 by a border. The coding result is then transmitted to the image controller 170. In addition, the image with the post code for video coding of the right-hand NAN part, which characterizes the streets, is transmitted to a further video coding station 200, at which a responsible operator video-codes 330 the right-hand NAN part asynchronously to the left-hand NAN part. Also in this case the part of the postal code to be coded is advantageously marked on the screen. The result of the video coding is then also transmitted to the image controller 170. In the image controller 170, the coding results are temporarily stored under an identification number for the respective image and combined 340 to form a complete video-coded postcode, with the transmission of the coding results to the image controller 170 also specifying which part (roughly or more specifically describing) it is, so that the assembly can be done correctly. The complete video-coded post code is then transmitted to the OCR unit 130 for a third reading attempt 350. Since this reading attempt 350 is now carried out with the entire entered postal code, the task of the OCR unit 130 in this case is to compare the postal code with the content of the address database and possibly with the other read address parts and to validate whether the postal code - de 300 was entered correctly.

The division of the postal code 300 into two parts, which are separately video coded and the link with the OCR reading process, has the following advantages:

1. The shorter sequence of characters to be encoded for an operator (video coding station) results in a much lower error rate and makes preview coding, in which the address images of several consecutive programs are displayed simultaneously, easier. The training time required to enter the characters in preview mode is greatly reduced.

Claims

claims

1. A method for reading postal codes from addresses of mail items, in which the images of the mail item surfaces having the addresses are recorded, stored and fed to an OCR unit (130) for recognizing the addresses and generating corresponding address codes, in the case of which no unambiguous reading results by the OCR unit (130), the relevant images are video-coded at at least one video coding location (200) and in which the postal code (300) identifies the address up to part of a larger street or several small streets, whereby

- After in the OCR unit (130) addresses could not be clearly read in a first reading attempt (310), first the postal codes are each divided into a part describing the address roughly and a more descriptive part and the corresponding images of the shipment surfaces are transmitted with these addresses to video coding stations (200), where only the parts of the postal codes (300) which roughly describe the addresses are video-coded (320) by the surgeons provided for them.

- And the images of the shipment surfaces with the corresponding addresses to other video coding stations (200) transmitters), where, asynchronously, the remainders of the postal codes (300) describing the addresses are video-coded (330) by the surgeons provided for this purpose and then each to a specific one Consigned, temporarily stored, video-coded postcode parts are combined to form a complete, video-coded postcode (340).

2. The method according to claim 1, wherein the part of the postal code (300) roughly describing the address identifies the destination.

3. The method according to claim 1, wherein the part of the postal code (300) describing the address identifies the street, partial street for large streets or several small streets.

_. The method according to claim 1, wherein the video-coded post part codes are assigned to the respective mail items or images on the basis of identification numbers and are combined to complete post codes (300).

5. The method according to claim 4, wherein the identification numbers are applied to the mailings and read together with the addresses.

6. The method according to claim 4, wherein the recorded images of the shipment surfaces are stored under identification numbers.

7. The method according to claim 5, wherein the identification numbers are applied to the mailpieces as machine-readable codes.

8. The method according to claim 7, wherein the identification numbers are applied as bar codes to the mailpieces.

9. The method according to claim 1, wherein a preview coding method is used in the video coding.

10. The method of claim 1, wherein the full, video-encoded postcode of the OCR unit (130) to a second

Read attempt (350) including the video coding results to validate the result is supplied.

11. Device for reading postal codes of addresses from Senge with an automatic address reading system, the

- a device for obtaining images of consignments (120), an OCR unit (130) for automatic evaluation of the images of the shipment surfaces that have the address information,

Video coding stations (200) for video coding the images of the mail item surfaces containing the address information,

- An image controller (170) for controlling the data flow between the OCR unit (130) and the video coding stations, wherein the image controller (17) is designed such that

- After in the OCR unit (130) addresses could not be clearly read in a first reading attempt (310), first the postal codes are each divided into a part describing the address roughly and a more detailed part and the corresponding images of the shipment surfaces are transmitted with these addresses to video coding stations (200), where only the parts of the postal codes (300) which roughly describe the addresses are video-coded (320) by the surgeons provided for this purpose - and the images of the mailing surface with the corresponding addresses are transmitted to further video coding stations (200) where, asynchronously, the remnants of the postal codes (300) describing the addresses are video-coded (330) by the surgeons provided for this purpose, and then the temporarily stored, video-coded postcode parts belonging to a particular program are combined to form a complete, video-coded postcode (340) ,

12. The apparatus of claim 11, wherein the image controller (170) is designed such that the respective assembled video-coded post code (300) of the OCR unit (130) for a second reading attempt including the video-coded post code (300) to validate the Result is fed.