Image analysis – Pattern recognition – Feature extraction
Reexamination Certificate
1998-11-13
2002-10-22
Johns, Andrew W. (Department: 2621)
Image analysis
Pattern recognition
Feature extraction
C235S462160
Reexamination Certificate
active
06470096
ABSTRACT:
FIELD OF THE INVENTION
The invention relates to a pattern-matching methods and, more particularly, to an image processing scheme adapted to locate and identify a substantially rectangular pattern, in any orientation, within a digitized image.
BACKGROUND OF THE INVENTION
Many people are most comfortable dealing with documents in hardcopy format. In general, hardcopy documents are easier to read, handle, and store than documents kept in the digital domain. No special expertise or computer hardware is needed.
However, in general, it is far easier to manipulate documents in the digital domain. Text can be indexed, searched upon, reformatted, extracted, and otherwise changed. Stored documents can be easily duplicated, without loss of quality, and transmitted from person to person (for example, via e-mail). And significantly, all of this can be accomplished without using paper. Moreover, digital copiers and scanners are becoming far more prevalent in both office and home settings.
On the other hand, handling documents in the digital domain typically requires access to a computer system or network. If the user of the computer system does not have a baseline level of expertise or competence in using the system, then productivity can suffer. This is a serious impediment to the implementation of a “paperless office,” in which digital documents are the prevailing document type.
Accordingly, there is a need to be able to effectively manage documents in the digital domain, as well as to ease the transition from hardcopy documents to digital documents.
Previous attempts to facilitate handling digital documents have often used traditional user-interface paradigms. For example, when a hardcopy document is to be scanned and entered into a document repository, commands to that effect are first entered into a computer terminal or scanning device, which then performs the desired service with the document. A similar sequence of steps is performed when the hardcopy is to be scanned and faxed, scanned and e-mailed, scanned and recognized (via optical character recognition software), or any of numerous other possibilities. Although the entry of commands can be facilitated via user-friendly software or self-explanatory commands, these extra steps are still tedious and may still require a certain level of expertise. Moreover, the sequence of commands entered may be lost once the operation has been performed, and there is a potential for error even with experienced users.
Another possibility is to employ a cover sheet that includes a form for specifying commands. The cover sheet is filled out as the user desires (either by hand-writing commands or by marking check-boxes, for example), and the scanner interprets the commands on the cover sheet and processes the following document accordingly. This, too, can be tedious and relatively inefficient, as it requires a special-purpose cover sheet to be used for each job. It can be inconvenient to maintain a supply of the proper cover sheets.
Various one- and two-dimensional data codes are known and available to be used to store digital data on hardcopy documents. For example, various types of barcodes (for example, the familiar UPC symbol used as a retail product code) are very well known and are robustly decodable. Other examples of linear barcodes are known as Code 39, Code 128, Interleaved 2 of 5, and Postnet. Two-dimensional codes, such as the PDF417 code and the UPS MaxiCode used by the United Parcel Service to track packages, for example, are becoming more and more widespread.
Self-clocking glyph codes, such as Xerox DataGlyphs, are attractive for embedding machine-readable digital information in images of various types, including ordinary hardcopy documents. These codes have substantial tolerance to image distortion and noise because the digital information they encode is embedded in and fully defined by explicit machine-readable marks (i.e., “glyphs,” a term used herein which is not intended to be limited to Xerox DataGlyphs, but rather is intended to cover all machine-readable marks). These glyphs not only encode the information that is embedded in the code, but also define the sample clock that is employed to extract that information from the code, so they are responsible for the “self-clocking” property of the code as well as the distortion and noise tolerance.
Another known advantage of self-clocking glyph codes is that they ordinarily have an unobtrusive visual appearance. This is especially so of codes composed of glyphs that are written on a two-dimensional spatially periodic pattern of centers, such as a regular lattice-like pattern of centers, because the spatial periodicity of the glyphs causes the code to have a more-or-less uniformly textured appearance. For example, logically ordered single bit digital quanta typically are encoded by respective elongated slash-like glyphs which are written on a two-dimensional, spatially periodic pattern of centers in accordance with a predetermined spatial formatting rule, with the individual glyphs being tilted to the left or right of vertical by approximately +45° and −45° for encoding logical “0's” and “1's”, respectively. The mutual orthogonality of the glyph encodings for the two logical states of these single bit digital quanta enhances the discriminability of the code sufficiently to enable the embedded information to be recovered, even when the code pattern is written on a sufficiently fine grain pattern of center to cause the code pattern to have a generally uniform grayscale appearance. It, however, is to be noted that it also has been shown that self-clocking glyph codes can be designed to encode multi-bit digital quanta in the glyphs.
Accordingly, it would be desirable to provide a solution that facilitates the use of documents in the digital domain and the transition of documents from hardcopy to digital formats. Such a solution should be simple, efficient, convenient, and require little or no expertise on the part of the user.
SUMMARY OF THE INVENTION
The present invention uses a scheme of encoded tags, such as adhesive stickers or labels, to serve as the primary user interface in a hardcopy document processing system. Such a system would permit a user to specify an action or a service to be performed and his own identity simply by applying a sticker to the document and placing it into a bin to be scanned.
The stickers are relatively small and unobtrusive, and in an embodiment of the invention use Xerox DataGlyphs to encode the user's identity, a desired service, and an optional argument for the service. The user maintains a supply of stickers corresponding to a particular service (e.g., “scan and send to my personal e-mail account”). When the user desires that service to be performed, he simply applies one of the appropriate stickers to the document.
A computer system performing the invention operates by first accepting information on the user's identity. This can be obtained, for example, by scanning and analyzing one of the user's business cards. This information is stored in a database and is given a unique user ID number. The user ID is combined with a desired service code, and the resulting data set is encoded into the desired printed data format. The system then prints a customized set of labels representing the user ID and service.
When the user then wishes to have the service specified by his stickers performed, he simply applies one of the stickers to a document and places it into a scanning queue. The document is scanned, the sticker is identified and decoded, re-associated with the user's information retrieved from the database, and the desired service is performed.
As will be recognized, this system can be adapted to perform numerous services and actions, including but not limited to simply scanning and storing the document in a repository, faxing the document, converting the document into a standard electronic format (such as Microsoft Word format), and others.
Accordingly, the sticker-based user interface of the present invention is con
Craig Julia A.
Davies Daniel
Azarian Seyed
Johns Andrew W.
LandOfFree
Method for locating user interface tags in a document... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method for locating user interface tags in a document..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for locating user interface tags in a document... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2991530