← Back to Patent Explorer
US5774579A Expired / Lapsed US ⏱️ 0.0 years remaining

Block selection system in which overlapping blocks are decomposed

Assignee: Canon Inc
•
Filing: 1995-08-11
•
Granted: 1998-06-30
•
Expires: 2015-08-11
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract In an image processing system for processing image data which includes both text areas and non-text areas, a method for extracting image data by performing block selection to obtain circumscribing rectangles around each block of text type areas in the image data and around each block of non-text type areas in the image data, obtaining outline pairs for each text and non-text block, determining whether the circumscribing rectangles overlap, decomposing overlapped rectangles based on the outline pairs, extracting image data based on the circumscribing rectangles for non-overlapped rectangles and based on the decomposed rectangles for overlapped rectangles, and processing the extracted image data.

Inventors

  • 👤 Shin-Ywan Wang
  • 👤 Toshiaki Yagasaki

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-11-06 18:02
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/40

Claims Analysis

Total Claims: 22
Claim 1
Independent Claim 118 words
An image processing method for processing image data which includes both text areas and non-text areas, comprising the steps of: performing block selection to obtain circumscribing rectangles around each block of text type areas in the image data and around each block of non-text type areas in the image data; obtaining, for each text and non-text block, an outline composed of outline pairs, the outline surrounding a plurality of connected components; determining whether the circumscribing rectangles overlap; decomposing overlapped rectangles into non-overlapping rectangles based on the circumscribing rectangles and the obtained outlines; extracting image data based on the circumscribing rectangles for non-overlapped rectangles and based on the decomposed rectangles for overlapped rectangles; and processing the extracted image data.
Claim 2
Dependent Claim 118 words
An image processing method for processing image data which includes both text areas and non-text areas, comprising the steps of: performing block selection to obtain circumscribing rectangles around each block of text type areas in the image data and around each block of non-text type areas in the image data; obtaining, for each text and non-text block, an outline composed of outline pairs, the outline surrounding a plurality of connected components; determining whether the circumscribing rectangles overlap; decomposing overlapped rectangles into non-overlapping rectangles based on the circumscribing rectangles and the obtained outlines; extracting image data based on the circumscribing rectangles for non-overlapped rectangles and based on the decomposed rectangles for overlapped rectangles; and processing the extracted image data.
Claim 3
Dependent Claim 60 words
An image processing method according to claim 1, wherein said step of performing block selection to obtain circumscribing rectangles includes the step of defining coordinates for upper-left and lower-right corners of each rectangle, and wherein said step of determining whether circumscribing rectangles overlap includes the step of comparing coordinates for one rectangle with coordinates for each of the other rectangles.
Claim 4
Dependent Claim 40 words
An image processing method according to claim 1, further comprising the step of determining whether overlapped rectangles affect image extraction, and wherein said step of decomposing overlapped rectangles is performed only when it is determined that overlap affects image extraction.
Claim 5
Dependent Claim 66 words
An image processing method according to claim 1, wherein said step of obtaining an outline for each block comprises the steps of determining which of plural mutually exclusive categories each block falls into, and obtaining outline pairs based on a selected one of mutually different outline pair techniques, the selected one being determined in accordance with which of the mutually exclusive categories the block falls into.
Claim 6
Dependent Claim 31 words
An image processing method according to claim 4, wherein the mutually exclusive categories consist of a text category, a non-text without internal component category, and a non-text with internal component category.
Claim 7
Dependent Claim 61 words
An image processing method according to claim 4, wherein in the case where the category for a block is a text-type category, outline pairs are obtained by tracing top, bottom, left and right edges of text connected components in the block, combining the top, bottom, left and right edges into a tight outline, and obtaining outline pairs from the tight outline.
Claim 8
Dependent Claim 40 words
An image processing method according to claim 4, wherein in a case where the category for a block is a non-text block without internal components, outline pairs are obtained by connecting outline pairs of each connected component in the block.
Claim 9
Dependent Claim 34 words
An image processing method according to claim 4, wherein in a case where the category for a block is a non-text block with internal components, outline pairs include outline pairs of interior white contours.
Claim 10
Dependent Claim 62 words
An image processing method according to claim 1, wherein said step of decomposing overlapped rectangles is comprised by the steps of determining which of plural mutually exclusive different categories the overlapped rectangle falls into, and decomposing the overlapped rectangle based on a selected one of plural different decomposition techniques, the selected one being selected based on which category the rectangle falls into.
Claim 11
Dependent Claim 145 words
A computer-readable memory medium storing computer-executable process steps to process image data which includes both text areas and non-text areas, the steps comprising: a performing step to perform block selection to obtain circumscribing rectangles around each block of text type areas in the image data and around each block of non-text type areas in the image data; an obtaining step to obtain, for each text and non-text block, an outline composed of outline pairs, the outline surrounding a plurality of connected components; a determining step to determine whether the circumscribing rectangles overlap; a decomposed step to decompose overlapped rectangles into non-overlapping rectangles based on the circumscribing rectangles and the obtained outlines; an extracting step to extract image data based on the circumscribing rectangles for non-overlapped rectangles and based on the decomposed rectangles for overlapped rectangles; and a processing step to process the extracted image data.
Claim 12
Dependent Claim 145 words
A computer-readable memory medium storing computer-executable process steps to process image data which includes both text areas and non-text areas, the steps comprising: a performing step to perform block selection to obtain circumscribing rectangles around each block of text type areas in the image data and around each block of non-text type areas in the image data; an obtaining step to obtain, for each text and non-text block, an outline composed of outline pairs, the outline surrounding a plurality of connected components; a determining step to determine whether the circumscribing rectangles overlap; a decomposed step to decompose overlapped rectangles into non-overlapping rectangles based on the circumscribing rectangles and the obtained outlines; an extracting step to extract image data based on the circumscribing rectangles for non-overlapped rectangles and based on the decomposed rectangles for overlapped rectangles; and a processing step to process the extracted image data.
Claim 13
Dependent Claim 54 words
A computer-readable memory medium storing computer-executable process steps according to claim 10, wherein said performing step includes a defining step to define coordinates for upper-left and lower-right corners of each rectangle, and wherein said determining step includes a comparing step to compare coordinates for one rectangle with coordinates for each of the other rectangles.
Claim 14
Dependent Claim 49 words
A computer-readable memory medium storing computer-executable process steps according to claim 10, further comprising a determining step to determine whether overlapped rectangles affect image extraction, and wherein said decomposing step to decompose overlapped rectangles is performed only in a case that it is determined that overlap affects image extraction.
Claim 15
Dependent Claim 76 words
A computer-readable memory medium storing computer-executable process steps according to claim 10, wherein said obtaining step to obtain an outline for each block comprises a determining step to determine which of plural mutually exclusive categories each block falls into, and an obtaining step to obtain outline pairs based on a selected one of mutually different outline pair techniques, the selected one being determined in accordance with which of the mutually exclusive categories the block falls into.
Claim 16
Dependent Claim 35 words
A computer-readable memory medium storing computer-executable process steps according to claim 13, wherein the mutually exclusive categories consist of a text category, a non-text without internal component category, and a non-text with internal component category.
Claim 17
Dependent Claim 65 words
A computer-readable memory medium storing computer-executable process steps according to claim 13, wherein in the case where the category for a block is a text-type category, outline pairs are obtained by tracing top, bottom, left and right edges of text connected components in the block, combining the top, bottom, left and right edges into a tight outline, and obtaining outline pairs from the tight outline.
Claim 18
Dependent Claim 44 words
A computer-readable memory medium storing computer-executable process steps according to claim 13, wherein in a case where the category for a block is a non-text block without internal components, outline pairs are obtained by connecting outline pairs of each connected component in the block.
Claim 19
Dependent Claim 38 words
A computer-readable memory medium storing computer-executable process steps according to claim 13, wherein in a case where the category for a block is a non-text block with internal components, outline pairs include outline pairs of interior white contours.
Claim 20
Dependent Claim 72 words
A computer-readable memory medium storing computer-executable process steps according to claim 10, wherein said decomposing step to decompose overlapped rectangles is comprised by a determining step to determine which of plural mutually exclusive different categories the overlapped rectangle falls into, and a decomposing step to decompose the overlapped rectangle based on a selected one of plural different decomposition techniques, the selected one being selected based on which category the rectangle falls into.
Claim 21
Dependent Claim 134 words
An image processing apparatus for processing image data which includes both text areas and non-text areas, comprising: block selection means for performing block selection to obtain circumscribing rectangles around each block of text type areas in the image data and around each block of non-text type areas in the image data; obtaining means for obtaining, for each text and non-text block, an outline composed of outline pairs, the outline surrounding a plurality of connected components; determination means for determining whether the circumscribing rectangles overlap; decomposition means for decomposing overlapped rectangles into non-overlapping rectangles based on the circumscribing rectangles and the obtained outlines; extraction means for extracting image data based on the circumscribing rectangles for non-overlapped rectangles and based on the decomposed rectangles for overlapped rectangles; and process means for processing the extracted image data.
Claim 22
Dependent Claim 134 words
An image processing apparatus for processing image data which includes both text areas and non-text areas, comprising: block selection means for performing block selection to obtain circumscribing rectangles around each block of text type areas in the image data and around each block of non-text type areas in the image data; obtaining means for obtaining, for each text and non-text block, an outline composed of outline pairs, the outline surrounding a plurality of connected components; determination means for determining whether the circumscribing rectangles overlap; decomposition means for decomposing overlapped rectangles into non-overlapping rectangles based on the circumscribing rectangles and the obtained outlines; extraction means for extracting image data based on the circumscribing rectangles for non-overlapped rectangles and based on the decomposed rectangles for overlapped rectangles; and process means for processing the extracted image data.

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 2001-06-29 2001-12-29 2002-06-30 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 2005-06-29 2005-12-29 2006-06-30 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2009-06-29 2009-12-29 2010-06-30 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag