Page analysis system

• US 5,987,171 A
• Filed: 11/10/1994
• Issued: 11/16/1999
• Est. Priority Date: 11/10/1994
• Status: Expired due to Term

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Wang, Shin-Ywan
• Primary Examiner(s): Johns, Andrew W.
• Application Number:
  US08/338,781
• Time in Patent Office: 1,832 Days
• Field of Search: 382/176, 382/173, 382/180, 382/226
• US Class Current: 382/173
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1456 based on user interactions
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• CPC Class Codes: H04N 1/40062 Discrimination between different image types, e.g. two-tone, continuous tone
• CPC Class Codes: H04N 1/41 Bandwidth or redundancy reduction by scanning H04N1/17 ; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00

Abstract

A page analysis system which analyzes image data of a document page includes analysis of image data of one of a plurality of portions of the page, identification of a block of image data which has an association to another separate block of image data, and determination of whether or not picture information in the image data is half-tone line-drawing, joint-line, or unknown.

Claims

1. In a page analysis system for analyzing image data in a document page, a method for selecting one of a plurality of portions of the document page to be analyzed, comprising the steps of:

inputting image data of a document page;

displaying the document page utilizing the input image data;

designating coordinates, using a coordinate designating device, of the one portion of the document page to be analyzed;

extracting image data of the portion of the document page designated in the designating step; and

performing block selection on the portion in order to analyze the extracted image data of the portion.

2. In a page analysis system for analyzing image data in the document page, an apparatus for selecting one of a plurality of portions of the document page to be analyzed, comprising:

inputting means for inputting image data of a document page;

displaying means for displaying the document page utilizing the input image data;

a coordinate designating device for designating coordinates of the portion of the document page to be analyzed;

image data extracting means for extracting image data of the portion of the document page designated by the coordinate designating device; and

block selection means for performing block selection on the portion in order to analyze the extracted image data of the portion.

3. For use in a page analysis system for analyzing image data in a document page, a computer-readable medium storing computer-executable process steps to select one of a plurality of portions of the document page to be analyzed, the process steps comprising:

an inputting step to input image data of a document page;

a displaying step to display the document page utilizing the input image data;

a designating step to designate coordinates, using a coordinate designating device, of the one portion of the document page to be analyzed;

an extracting step to extract image data of the portion of the document page designated in the designating step; and

a performing step to perform block selection on the portion in order to analyze the extracted image data of the portion.

4. In a page analysis system for analyzing image data in a multi-page document, wherein a hierarchical tree structure of the analyzed pages is created utilizing a block selection program, and wherein the hierarchical tree structure includes a root node, a method for defining a composite region of image data in a page of the multi-page document, comprising the steps of:

inputting image data of a page of a multi-page document;

performing block selection processing so as to identify and separate the image data into blocks having the same image type;

identifying at least one block of image data which has an association to another separate block of image data, the associated blocks represented by nodes in the hierarchical tree structure;

combining said associated blocks of image data within a composite block; and

adding a node representing the composite block to the hierarchical tree structure, the node representing the composite block added such that the nodes representing the associated blocks descend from the node representing the composite block.

5. In a page analysis system for analyzing image data in a multi-page document, wherein a hierarchical tree structure is created for the analyzed pages, and wherein the hierarchical tree structure includes a root node, an apparatus for defining a composite region of image data in a page of the multi-page document;

block selection processing means for identifying and separating the image data into blocks having the same image type;

identifying means for identifying at least one block of image data which has an association to another separate block of image data, the associated blocks represented by nodes in the hierarchical tree structure;

combining means for combining said associated blocks of image data within a composite block; and

modifying means for modifying the hierarchical tree by adding a node representing the composite block, the node representing the composite block added such that the nodes representing the associated blocks descend from the node representing the composite block.

6. For use in a page analysis system for analyzing image data in a multi-page document, wherein a hierarchical tree structure of the analyzed pages is created utilizing a block selection program, and wherein the hierarchical tree structure includes a root node, a computer-readable medium storing computer-executable process steps to define a composite region of image data in a page of the multi-page document, the process steps comprising:

an inputting step to input image data of a page of a multi-page document;

a performing step to perform block selection processing so as to identify and separate the image data into blocks having the same image type;

an identifying step to identify at least one block of image data which has an association to another separate block of image data, the associated blocks represented by nodes in the hierarchical tree structure;

a combining step to combine said associated blocks of image data within a composite block; and

an adding step to add a node representing the composite block to the hierarchical tree structure, the node representing the composite block added such that the nodes representing the associated blocks descend from the node representing the composite block.

7. In a page analysis system which creates a hierarchical tree structure corresponding to a block template of a document image wherein the hierarchical tree structure includes a plurality of nodes each of which represents a block of image data in the block template of a document image and contains feature data defining features of the block template of a document image, a method of identifying and indicating a picture type, the method comprising steps of:

inputting image data of a page of a multi-page document;

performing block selection processing so as to identify and separate the image data into blocks having the same image type;

identifying blocks of image data which contain picture information;

storing information in nodes corresponding to the blocks of picture information, the information indicating that the blocks contain picture information;

determining a type of picture information within a block of picture information, wherein, in the determining step, it is determined whether or not picture information is half-tone, line-drawing, joint-line, or unknown; and

storing, in a node representing the block of picture information in the hierarchical tree, information indicating the type of picture determined in the determining step.

8. In a page analysis system which creates a hierarchical tree structure corresponding to a block template of a document image wherein the hierarchical tree structure includes a plurality of nodes each of which represents a block image data in the block template of a document image and contains feature data defining features of the block template of a document image, an apparatus for identifying and indicating a picture type, comprising:

input means for inputting image data of a page of a multi-page document;

block selection processing means for identifying and separating the image data into blocks having the same image type;

identifying means for identifying blocks of image data which contain picture information;

determining means for determining a type of picture information within the block of picture information, wherein said determining means determines whether or not picture information is half-tone, line-drawing, joint-line, or unknown; and

storing means for storing, in a node representing the block of picture information in the hierarchical tree, the type of picture determined by said determining means.

9. For use in a page analysis system which creates a hierarchical tree structure corresponding to a block template of a document image wherein the hierarchical tree structure includes a plurality of nodes each of which represents a block of image data in the block template of a document image and contains feature data defining features of the block template of a document image, a computer-readable medium storing computer-executable process steps to identify and to indicate a picture type, the process steps comprising:

an inputting step to input image data of a page of a multi-page document;

a performing step to perform block selection processing so as to identify and separate the image data into blocks having the same image type;

an identifying step to identify blocks of image data which contain picture information;

a storing step to store information in nodes corresponding to the blocks of picture information, the information indicating that the blocks contain picture information;

a determining step to determine a type of picture information within a block of picture information, wherein, in the determining step, it is determined whether or not picture information is half-tone, line-drawing, joint-line, or unknown; and

a storing step to store, in a node representing the block of picture information in the hierarchical tree, information indicating the type of picture determined in the determining step.