Image analysis – Applications – Mail processing
Reexamination Certificate
1999-11-03
2003-07-01
Patel, Jayanti K. (Department: 2721)
Image analysis
Applications
Mail processing
C235S375000, C209S584000, C209S630000
Reexamination Certificate
active
06587572
ABSTRACT:
BACKGROUND OF THE INVENTION
The invention relates to a method and an arrangement for recognizing distribution information on mail items and can be used particularly advantageously for determining distribution information written in non-alphabetic language on mail items.
Systems for the automatic reading of distribution information, particularly addresses (OCR), are well known in the field of mail processing and are described, for example, in the DE 195 31 392. Modern OCR letter sorting equipment makes it possible to achieve processing rates of 10 letters per second, that is to say 36,000 letters per hour and more. However, the recognition reliability varies strongly based on the lettering style and total quality of the address information on the surfaces of the letters. In the case of a successful recognition, the respective letter can be provided with a machine-readable bar code. This bar code permits a further mechanical processing up to an optionally desired sorting arrangement. In particular, the use of bar codes makes it possible to sort the letters up to the sorting level of the mail carrier route, for which letters are sorted on the basis of the distribution sequence by the delivery person.
Economic trends and an increased mail volume in Asia have led to increased efforts in the automatic recognition of eastern writing styles, so as to limit costs and improve the delivery of mail. As compared to the situation in western countries where mail automation already represents an established technology, the recognition systems must meet new requirements, which stem from the fact that Chinese characters are used for local mail addresses in most countries of the Asiatic basin. Unlike the letters used in western alphabetic writing, Chinese characters are configured as ideograms. Each of these ideograms can represent a word. In place of an alphabet numbering thirty to sixty letters, 3000 to 6000 different Chinese characters are used daily, each with its own characteristic form. This practical non-perfectivity of the Chinese character system and the ideographic structure of the individual characters lead to a reduced effectiveness of OCR systems as compared to western alphabetical writing systems. In addition, problems are caused by the fact that the address on postal items appears to be oriented either in vertical or in horizontal direction and that frequently there is a mixture of Chinese and western writing.
Since the recognition rates for the automatic reading systems generally vary considerably for western as well as for Chinese characters, it is necessary to support these through various forms of manual intervention. Reverting to a manual sorting method is the simplest method of intervention in case of a rejection of letters that cannot be read automatically. However, the resulting costs are uneconomically high, owing to the increasing operating costs. Added to this is the fact that such hand-sorted mail cannot be further sorted mechanically at a later point in time, so that two separate flows of mail items are created, which must again be combined manually at a specific point in time.
Various methods for manually coding mail items have been developed to avoid the disadvantages of the manual sorting of OCR rejected mail items. All of these methods use operator intervention to apply bar codes to the mail items, in a manner that is consistent with the requirement for a mechanical sorting with the same equipment used to process the OCR read and bar-coded mail.
Another method for coding rejected mail items uses so-called manual coding stations. At these manual-coding stations, the mail items are physically moved sequentially past an operator, wherein the operator encodes as much information for each of these items, as is necessary to clearly identify the destination location. In the process, the input address is converted by means of a directory to a sorting bar code, which is then applied to the mail item. The coded mail items are then processed further with the aid of bar-code sorters (BCS), which are mechanically identical to OCR-suitable BCS. Such manual coding stations were initially introduced by the US Postal Service and the Royal Mail in the Seventies. The main disadvantages of such devices are the required removal of mail items from the OCR mail flow and the ergonomic difficulties, experienced by the operator during the recognition of the mail items that are moved past the operator.
The next advance in the treatment of mail items rejected in the OCR was the development of on-line video-coding systems (OVS). In an OVS, a video image of the item is presented to an operator for coding in place of the physical mail item that is present at manual coding stations. The video image is shown to the operator while the physical item is held in delay loops. In these delay loops, the item is normally held in motion for a period of time that is sufficient for the OVS operator to input the necessary sorting information for the respective image. The standard delay loops permit a delay of between 10 and 30 seconds. The longer the delay loop, the higher the costs as well as the requirements for maintenance and the physical size of the installation.
The main problem when using OVS is that the available time is sufficient only for a careful input of the zip code (ZIP) or the postal code (PC) unless long, impractical delay loops are used.
As long as a ZIP or PC exists, OVS can also be used effectively for items addressed with Chinese characters. However, the share of such mail items in many eastern countries is very low and probably will remain so in the foreseeable future.
For that reason, special coding methods were developed to keep the on-line delay time as low as possible.
In order to increase the coding productivity and/or make it possible to give all address elements, meaning the ZIP/PC, street/post office box, addressee/post office box, addressee/firm, various methods have been developed in prior art. Essentially, these include:
Preview Coding:
The preview coding involves a simultaneous display of images from two mail items, one above the other. The lower image in this case is the active one, meaning the one for which data are coded. Following a suitable training, operators can encode the information on the lower image while simultaneously visually recognizing the address information on the upper image. The upper image subsequently becomes active and the process is continued. The preview coding makes it possible to double the operator productivity through a complete overlapping of the cognitive and the motorized functions during the coding of sequential images.
Extraction Coding:
Owing to the fact that only the ZIP/PC address elements can be input reliably by the operator given the on-line delay times that can be achieved in practical operations, certain key components of the address components referring to the street are input during the extraction coding. The extraction coding normally is based on specially developed rules, for which a code with fixed length is used as access key to an address directory. For example, the Royal Mail uses an extraction formula that is based on the first three and the last two letters. For this, the operator must memorize special rules to avoid superfluous address information and to take into account specific, distinguishing characteristics, e.g. directions such as east, west or categories such as street, lane, road.
Despite being very effective, extraction coding has several considerable disadvantages, particularly complex extraction rules, which frequently require taking into account the end of a street name, even though these components normally are the least clear with hand-written addresses on mail items. In addition, there is a significantly high rate of unclear extractions, for which several entries in a directory correspond to the extraction code, so that it is not possible to make a definite sorting decision. It must also be considered that the input productivity of the operators is reduced as soon as the operators must make decisions instea
Miletzki Udo
Rosenbaum Walter
Suchenwirth-Bauersachs Richard
Kinberg Robert
Patel Jayanti K.
Siemens Aktiengesellschaft
Venable LLP
Voorhees Catherine M.
LandOfFree
Mail distribution information recognition method and device does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Mail distribution information recognition method and device, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Mail distribution information recognition method and device will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3105753