scispace - formally typeset
Search or ask a question

Showing papers on "Document layout analysis published in 1986"


Proceedings Article
11 Aug 1986
TL;DR: A rule-based system to make inferences about document images is introduced that uses a goal-directed top down approach, and utilizes a three-level rule hierarchy to implement its control strategy.
Abstract: A rule-based system to make inferences about document images is introduced. Given a digitized document image, the sys tern controls the analysis of the document, and identifies all the different printed regions in the document image. Logical "blocks" of information on the document image are interpreted and classified by this system which then produces as output an editable description of the entire document. The system uses a goal-directed top down approach, and utilizes a three-level rule hierarchy to implement its control strategy.

44 citations


Journal ArticleDOI
TL;DR: The author presents an interactive document editor based on an expressive abstract document model that is the basis for a document processing system that allows its users to edit the logical structure of a document using specific structure editing commands.
Abstract: The author presents an interactive document editor based on an expressive abstract document model for paper and electronic documents. The model introduces the notions of abstract and concrete objects, hierarchical composition of ordered and unordered objects, sharing of components, and reference links. It has been used to specify a wide variety of document objects, and is the basis for a document processing system that allows its users to edit the logical structure of a document using specific structure editing commands. This system introduces two new ideas. The first involves computational objects; each object can be programmed to generate its own unique view of the document, and each of these views can be displayed in a separate window on the screen. The second involves multiple windows to display the document structure. The windows are arranged hierarchically as sets and sequences, depending on the composite structure of the document. This system is used for both editing and viewing documents.

18 citations


01 Jan 1986
TL;DR: The work described in this dissertation is unique in its use of a heterogeneous document representation rather than a homogeneous one and the related use of cooperating editors, its explicit representation of all possible document components through the template, its exploitation of the separation of the Integrated from the Exact-representation Editor/Formatters, and in its mechanisms for region-oriented manipulations of the document.
Abstract: A document formatting system converts a document description into a formatted document, which is then displayed or printed on a hardware device. An integrated Editor/Formatter merges the creation and editing of the document description, the formatting, and the viewing of the formatted document into a single, unified, interactive system. A trend in non-interactive document formatting systems is to describe the document by its logical structure instead of its physical makeup, thereby increasing the flexibility of the document description. A trend in interactive systems is that of the Exact-representation Editor/Formatter (also known as WYSIWYG), which presents the same representation of the document on all output devices, with editing operations performed directly on this representation. This dissertation presents an interactive system that incorporates a description by logical structure with a naturalness of document manipulation like that found in the Exact-representation Editor/Formatters. The result is an Integrated Editor/Formatter but not an Exact-representation one. The work identifies a hybrid tree-based document representation with a variety of objects as leaves (e.g., text, tables, and mathematical equations). This representation permits the inclusion of a wide variety of document objects while providing a consistent, simple enclosing structure. A central part of the dissertation work is embodied in a prototype system for displaying and manipulating a portion of this three-based document representation. The interactive interface of the prototype is drive directly from a grammatical description of the document's structure and presents a template-based document view that is manipulated through separate, interacting editors. Editing commands operate directly on the document's displayed form, not on its structure. Important in providing this are heuristics that translate operations on regions in the display into operations on the underlying structure. Other recent systems have had similar goals. The work described in this dissertation is unique in its use of a heterogeneous document representation rather than a homogeneous one and the related use of cooperating editors, its explicit representation of all possible document components through the template, its exploitation of the separation of the Integrated from the Exact-representation Editor/Formatters, and in its mechanisms for region-oriented manipulations of the document.

10 citations


Patent
25 Jun 1986
TL;DR: In this paper, a document image reducing means 15 reduces the document image in a text document image file means 14 and displays their list on an image display means 13, so that the operator can utilize the image information directly and easily read the document images.
Abstract: PURPOSE:To facilitate the retrieval of a document image by using an image obtained by reducing an actual filed document image itself as a means for indexing in addition to key words. CONSTITUTION:A document image reducing means 15 reduces the document image in a document image file means 14. The command for file retrieval is inputted by a command input means 12 and then the key word for document images is inputted, so that a CPU 16 displays the number of document images corresponding to the key word in the document image file means 14. When an operator commands the reference of the reduced image, the CPU 16 reduces said number of document images in the document image file means 14 and displays their list on an image display means 13. The operator, therefore, utilizes the image information directly and easily reads the document images.

6 citations


Patent
03 Jun 1986
TL;DR: In this paper, a titled system is constituted of an input part 1 for inputting data such as images, an output part 2 for displaying or printing out necessary information, an internal storage part 3, an external storage part 4, and a control part for controlling respective parts.
Abstract: PURPOSE: To form a document corresponding to a purpose without using unnecessary labor for the layout of the document by displaying items described by a user in an priority order on the basis of layout structure corresponding to its logical structure. CONSTITUTION: The titled system is constituted of an input part 1 for inputting data such as images, an output part 2 for displaying or printing out necessary information, an internal storage part 3, an external storage part 4, and a control part for controlling respective parts. At the time of formation of a business document, a user inputs only a sentence item to be described and selects layout structure appropriate for the item from the logical structure of the described contents. Then, the described sentence item inputted by the user is converted into layout structure, which is displayed to check whether the use satisfies the layout display or not. When the user does not satisfies the display, similar conversion is applied to the succeeding layout structure and the converted structure is displayed. Thus, the user can select his preferably layout display pattern. COPYRIGHT: (C)1987,JPO&Japio

5 citations