scispace - formally typeset
Patent

Method for inset detection in document layout analysis

Reads0
Chats0
TLDR
In this paper, a method for detecting insets in the structure of a document page so as to further complement the document layout and textual information provided in an optical character recognition system is presented.
Abstract
The present invention is a method for detecting insets in the structure of a document page so as to further complement the document layout and textual information provided in an optical character recognition system. A system employing the present method preferably includes a document layout analysis system wherein the inset detection methodology is used to extend the capability of an associated character recognition package to more accurately recreate the document being processed.

read more

Citations
More filters
Patent

Reformatting documents using document analysis information

TL;DR: In this paper, a method and apparatus for reformatting electronic documents is disclosed, which consists of performing layout analysis on an electronic version of a document to locate text zones, assigning attributes for scale and importance to text zones in the electronic version, and reformating text based on the attributes to create an image.
Patent

Document reflowing technique

TL;DR: Disclosed as mentioned in this paper is a technique for generating a reflowed document image that fits the width of target display so that original electronic documents can be viewed without the necessity for tedious, horizontal scrolling.
Patent

Automated document layout design

TL;DR: In this article, a method and apparatus for automated document layout creation is described, which comprises receiving a first layout of document image objects and creating a second layout of image objects subject to placement constraints corresponding to the placement of the image objects.
Patent

Content Profiling to Dynamically Configure Content Processing

TL;DR: In this article, the authors identify a default set of document reconstruction operations for reconstructing the unstructured document to define a structured document and then modify the set of reconstruction operations according to the identified profile.
Patent

System and method for data publication through web pages

TL;DR: In this paper, a system and a method for publishing a newspaper page or other data through a Web page, such that the information can be made available more easily through a network such as the Internet, is presented.
References
More filters
Patent

Document identification by characteristics matching

TL;DR: In this paper, the authors used the technique of recognition of global document features compared to a knowledge base of known document types to segment the digitized image of a document into physical and logical areas of significance and attempt to label these areas by determining the type of information they contain.
Patent

Segmentation of text, picture and lines of a document image

TL;DR: In this article, a method and apparatus for segmenting a document image into areas containing text and non-text is presented, which is comprised of the steps of: providing a bit-mapped representation of the document image, extracting run lengths for each scanline from the bit-map representation of document image; constructing rectangles from the run lengths; initially classifying each of the rectangles as either text or nontext; correcting for the skew in the Rectangles; merging associated text into one or more text blocks; and logically ordering the text blocks.
Patent

Advanced data capture architecture data processing system and method for scanned images of document forms

TL;DR: In this paper, an advanced data capture architecture is proposed which enables the free definition and re-definition of the format of document forms without requiring any reprogramming of the data processors which capture and use the data on the completed forms.
Patent

Information processing system.

TL;DR: In this paper, an information processing system which comprises an integral input and display unit comprising a display (101) which enables an object to be selectively displayed at one of a plurality of positions in a display area and a tablet (112) having an input face overlaid on a display face of the display, being disposed substantially horizontally, and a display whose display face is disposed substantially uprightly, where when an object is presented to a user in the display area of display, a display position of the object is determined in response to at least one of the state of the user,
Patent

Method and apparatus for separating static and dynamic portions of document images

TL;DR: In this paper, a method and apparatus for compressing images of financial instruments and other documents is presented, which includes the steps of scanning a plurality of documents to obtain an electronic image of each document, identifying a static portion in the electronic image, containing information which remains substantially unchanged for the plurality of document, by locating and reading a document identifier in the image; storing the document identifier and identifying a dynamic portion, typically containing distinct information for each of the documents, in each electronic images; isolating the dynamic portion from the static portion within the image to obtain a dynamic image containing