Patent EP0660256A2 successfully refreshed from Google Patents.
EP0660256A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Method and apparatus for selecting text and/or non-text blocks in a stored document
Assignee: Canon Inc
•
Filing: 1994-12-22
•
Granted: —
•
Expires: 2014-12-22
Abstract
Abstract Method and apparatus for selecting text and/or non-text blocks in a stored document includes functions and structure for identifying connected pixel components in a stored document, separating the identified pixel components into text and non-text components, searching the document for a visible and invisible lines along edges of the non-text components, forming irregularly-shaped text and non-text blocks using the identified text components and the visible and invisible lines, detecting the text orientation for each formed text block, extracting text lines from the text block based on the detected orientation, detecting the skew angle for the stored document based on the extracted lines, and modifying the formed text and non-text blocks based on the detected skew angle. The thus- formed text blocks are preferably subjected to character recognition routines.
Inventors
- 👤 Shin-Ywan Wang
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-08 23:25
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/40; G06V30/41; G06V30/413; G06V30/10; G06V30/14; G06V30/146; G06V30/1463
Claims Analysis
Total Claims: 85
Claim 1
Independent Claim
88 words
A method of selecting blocks of pixels from pixel image data comprising the steps of: outlining contours of connected components in the pixel data; a first connecting step in which connected components are selectably connected widthwisely based on size and proximity to other connected components to form lines; a second connecting step in which lines of widthwise connected components are selectably connected vertically based on size and proximity to other lines to form blocks; and forming an irregularly-shaped curve around the blocks formed in said second connecting step.
Claim 2
Dependent Claim
47 words
A method according to Claim 1, further comprising the step of inputting pixel image data, wherein said inputting step includes the step of converting the pixel image data into binary pixel image data in the event that the pixel image data is not binary pixel image data.
Claim 3
Dependent Claim
21 words
A method according to Claim 1, wherein in said forming step, the smallest irregularly-shaped curve is formed around each text block.
Claim 4
Dependent Claim
37 words
A method according to Claim 1, further comprising the step of forming a hierarchical tree of the connected components outlined in said outlining step based on the position of corresponding irregularly-shaped curves formed in said forming step.
Claim 5
Dependent Claim
25 words
A method according to Claim 4, further comprising the step of classifying the irregularly-shaped curves formed in said forming step into text and non-text blocks.
Claim 6
Dependent Claim
18 words
A method according to Claim 5, further comprising the step of recognizing character images in the text blocks.
Claim 7
Dependent Claim
23 words
A method according to Claim 6, wherein said first connecting step and said second connecting step are not performed for non-text connected components.
Claim 8
Dependent Claim
19 words
A method according to Claim 6, further comprising the step of deriving white contours for non-text outlined connected components.
Claim 9
Dependent Claim
22 words
A method according to Claim 8, wherein non-text blocks are designated as table units in accordance with the number of white contours.
Claim 10
Dependent Claim
17 words
A method according to Claim 9, further comprising the step of calculating the white contour filling rate.
Claim 11
Dependent Claim
25 words
A method according to Claim 10, wherein the non-text block is not designated as image data in the event that the filling rate is high.
Claim 12
Dependent Claim
15 words
A method according to Claim 10, further comprising the step of recombining non-grid-arranged white contours.
Claim 13
Dependent Claim
25 words
A method according to Claim 12, wherein the non-text block is designated as a table in the even that the recombination rate is not high.
Claim 14
Dependent Claim
14 words
A method according to Claim 8, wherein white contours are calculated in 4 directions.
Claim 15
Dependent Claim
18 words
A method according to Claim 1, wherein contours of connected components are outlined in at least 8 directions.
Claim 16
Dependent Claim
25 words
A method according to Claim 1, wherein in said outlining step, contours of connected components are outlined only at exterior portions of the connected components.
Claim 17
Dependent Claim
43 words
A method according to Claim 1, further comprising the step of detecting gaps in the pixel image data, and wherein in said first connecting step connected components are not connected widthwisely into lines in the even that a gap separates the connected components.
Claim 18
Dependent Claim
18 words
A method according to Claim 17, wherein columns are detected in accordance with vertically-extending gaps between connected components.
Claim 19
Dependent Claim
52 words
A method according to Claim 1, wherein said second connecting step includes the step of determining non-text boundaries between lines of text data connected in said first connecting step, and wherein said second connecting step does not connect lines vertically into blocks in the event that there is an intervening non-text boundary.
Claim 20
Dependent Claim
20 words
A method according to Claim 1, further comprising the step of compressing the pixel image data before said outlining step.
Claim 21
Dependent Claim
84 words
Apparatus for selecting blocks of pixels from pixel image data comprising: storing means for storing the pixel image data; and processing means for (1) outlining contours of connected components in the stored pixel image data, (2) selectably connecting connected components widthwisely based on size and proximity to other connected components to form lines, (3) selectably connecting lines of widthwise connected components vertically based on size and proximity to other lines to form blocks, and (4) forming an irregularly-shaped curve around each outlined connected component.
Claim 22
Dependent Claim
51 words
An apparatus according to Claim 21, further comprising input means for inputting pixel image data into said storing means, said input means including converting means for converting the pixel image data into binary pixel image data in the event that the input pixel image data is not binary pixel image data.
Claim 23
Dependent Claim
19 words
An apparatus according to Claim 21, wherein said processing means forms the smallest irregularly-shaped curve around each text block.
Claim 24
Dependent Claim
29 words
An apparatus according to Claim 21, wherein said processing means forms a hierarchical tree of the outlined connected components based on the position of the formed corresponding irregularly-shaped curves.
Claim 25
Dependent Claim
20 words
An apparatus according to Claim 24, wherein said processing means classifies the formed irregularly-shaped curves into text and non-text blocks.
Claim 26
Dependent Claim
17 words
An apparatus according to Claim 25, wherein said processing means recognizes character images in the text blocks.
Claim 27
Dependent Claim
20 words
An apparatus according to Claim 25, wherein said processing means does not perform the connecting functions for non-text connected components.
Claim 28
Dependent Claim
18 words
An apparatus according to Claim 25, wherein said processing means derives white contours for non-text outlined connected components.
Claim 29
Dependent Claim
24 words
An apparatus according to Claim 28, wherein said processing means designates non-text blocks as table units in accordance with the number of white contours.
Claim 30
Dependent Claim
16 words
An apparatus according to Claim 28, wherein said processing means calculates a white contour filling rate.
Claim 31
Dependent Claim
28 words
An apparatus according to Claim 30, wherein said processing means does not designate the non-text block as image data in the event that the filling rate is high.
Claim 32
Dependent Claim
15 words
An apparatus according to Claim 30, wherein said processing means recombines non-grid arranged white contours.
Claim 33
Dependent Claim
27 words
An apparatus according to Claim 32, wherein said processing means designates the non-text block as a table in the event that the recombination rate is not high.
Claim 34
Dependent Claim
16 words
An apparatus according to Claim 28, wherein said processing means calculates white contours in four directions.
Claim 35
Dependent Claim
20 words
An apparatus according to Claim 21, wherein said processing means outlines contours of connected components in at least 8 directions.
Claim 36
Dependent Claim
24 words
An apparatus according to Claim 21, wherein said processing means outlines the contours of connected components only at exterior portions of the connected components.
Claim 37
Dependent Claim
35 words
An apparatus according to Claim 21, wherein said processing means detects gaps in the pixel image data, and does not connect connected components widthwisely into lines in the event that a gap separates the components.
Claim 38
Dependent Claim
20 words
An apparatus according to Claim 37, wherein said processing means detects columns in accordance with vertically-extending gaps between connected components.
Claim 39
Dependent Claim
41 words
An apparatus according to Claim 21, wherein said processing means determines non-text boundaries between lines of connected text data, and wherein said processing means does not connect lines vertically into blocks in the event that there is an intervening non-text boundary.
Claim 40
Dependent Claim
17 words
An apparatus according to Claim 21, wherein said processing means compresses the pixel image data before outlining.
Claim 41
Independent Claim
139 words
A method for forming a text file of characters in pixel image data, comprising the steps of: inputting and storing binary pixel image data; selecting blocks of stored pixel image data; outlining contours of connected components in the stored pixel image data; determining whether outlined connected components include text units or non-text units; selectively connecting text units widthwisely to form text lines based on proximity of adjacent text units; selectively connecting text lines vertically to form text blocks based on proximity of adjacent text lines and the position of non-text units between text lines; surrounding the text blocks with irregularly-shaped curves; forming a hierarchical tree of text blocks based on the connected components outlined in said outlining steps; and segmenting the treed text blocks into lines of pixel data by adaptively dividing text blocks into at least one column.
Claim 42
Dependent Claim
19 words
A method according to Claim 41, further comprising a pre-processing step in which the pixel image data is pre-processed.
Claim 43
Dependent Claim
16 words
A method according to Claim 42, wherein said pre-processing step includes the step of image compression.
Claim 44
Dependent Claim
18 words
A method according to Claim 43, wherein said pre-processing step includes the step of enhancing pixel image data.
Claim 45
Dependent Claim
18 words
A method according to Claim 41, further comprising the step of white-contour tracing the interior of non-text units.
Claim 46
Dependent Claim
16 words
A method according to Claim 45, further comprising the step of appending designators to non-text units.
Claim 47
Dependent Claim
23 words
A method according to Claim 45, wherein table designators are appended to non-text units based on the number of white contours contained therein.
Claim 48
Dependent Claim
146 words
Apparatus for forming a text file of characters in pixel image data, comprising: inputting means for inputting pixel image data; storing means for storing the inputted pixel image data; and processing means for (1) outlining contours of connected components in the stored image pixel data, (2) determining whether outlined connected components include text units or non-text units, (3) selectively connecting text units widthwisely to form text lines based on proximity of adjacent text units, (4) selectively connecting text lines vertically to form text blocks based on proximity of adjacent text lines and on the position of non-text units between text lines, (5) surrounding the text blocks with irregularly-shaped curves, (6) forming a hierarchical tree of the text blocks based on the outlined connected components, and (7) segmenting the treed text blocks into lines of pixel data by adaptively dividing text blocks into at least one column.
Claim 49
Dependent Claim
15 words
Apparatus according to Claim 48, wherein said processing means pre-processes the input pixel image data.
Claim 50
Independent Claim
116 words
A method of separating blocks of text areas and non-text areas of a stored document, comprising the steps of: identifying connected pixel components in the stored document; separating the identified pixel components into text and non-text components; searching said document for visible lines and for invisible lines along edges of non-text components; forming text and non-text blocks using the identified text components and the visible and invisible lines; detecting the text orientation for each formed text block; extracting text lines from the text block based on the detected text orientation; detecting the skew angle for the stored document based on the extracted text lines; and modifying the formed text blocks based on the detected skew angle.
Claim 51
Dependent Claim
21 words
A method according to Claim 50, further comprising the step of forming horizontal and vertical title lines after said searching step.
Claim 52
Dependent Claim
28 words
A method according to Claim 50, further comprising the step of, after said forming step, splitting a formed text block if a visible or invisible line passes therethrough.
Claim 53
Dependent Claim
34 words
A method according to Claim 50, wherein said forming step includes the step of determining whether an identified text component is vertically above one text component which is included with the forming text block.
Claim 54
Dependent Claim
38 words
A method according to claim 50, wherein said forming steps includes the step of detecting whether any line-drawing object falls between an identified text component and one other text component which is included in the forming text block.
Claim 55
Dependent Claim
20 words
A method according to Claim 50, wherein said forming step takes place before the step of detecting the skew angle.
Claim 56
Dependent Claim
19 words
A method according to Claim 50, further comprising the step of character recognizing the modified and formed text blocks.
Claim 57
Dependent Claim
27 words
A method according to Claim 50, further comprising, after said separating step, classifying the non-text components into at least one of a predetermined plurality of non-text classifications.
Claim 58
Independent Claim
136 words
An apparatus for separating blocks of text areas and non-text areas of a stored document, comprising: storing means for storing a document containing pixel components; and processing means for (1) identifying connected pixel components in the stored document, (2) separating the identified pixel components into text and non-text components, (3) searching the document for visible lines and for invisible lines along edges of non-text components, (4) forming text and non-text blocks using the identified text components and the visible and invisible lines, (5) detecting the text orientation for each formed text block, (6) extracting text lines from the text block based on the detected text orientation, (7) detecting the skew angle for the stored document based on the extracted text line, and (8) modifying the formed text and non-text blocks based on the detected skew angle.
Claim 59
Dependent Claim
21 words
Apparatus according to Claim 58, wherein said processing means forms horizontal and vertical title lines after the step of (3) searching.
Claim 60
Dependent Claim
28 words
Apparatus according to Claim 58, wherein said processing means splits a text block if a visible line or an invisible line passes therethrough, after said (4) forming step.
Claim 61
Dependent Claim
30 words
Apparatus according to Claim 58, wherein said processing means forms text blocks by determining whether an identified text component vertically overlaps another text component included in the forming text block.
Claim 62
Dependent Claim
35 words
Apparatus according to Claim 50, wherein said processing means forms the text blocks by determining whether any line-drawing object falls between an identified text component and another text component included in the forming text block.
Claim 63
Dependent Claim
25 words
Apparatus according to Claim 58, wherein said processing means forms the text and non-text blocks before the skew angle of the stored document is detected.
Claim 64
Dependent Claim
17 words
Apparatus according to Claim 58, wherein said processing means character recognizes the modified and formed text blocks.
Claim 65
Dependent Claim
24 words
Apparatus according to Claim 58, wherein said processing means classifies the non-text components into at least one of a predetermined plurality of non-text classifications.
Claim 66
Independent Claim
64 words
A method for forming text blocks in a stored document having both horizontal and vertical text, comprising the steps of: identifying connected pixel components; grouping the identified pixel connected components horizontally and vertically; forming irregularly-shaped horizontal and vertical text blocks based on the grouped components and without having performed skew detection; and thereafter detecting the skew angle for each of the formed text blocks.
Claim 67
Dependent Claim
20 words
A method according to Claim 66, wherein said grouping step includes the step of separating text and non-text connected components.
Claim 68
Dependent Claim
25 words
A method according to Claim 67, further comprising the step of classifying non-text components into at least one of a predetermined plurality of non-text classifications.
Claim 69
Dependent Claim
25 words
A method according to Claim 67, further comprising the step of searching the stored document for invisible lines along edges of the non-text connected components.
Claim 70
Dependent Claim
26 words
A method according to Claim 60, further comprising the step of splitting a formed text block if a visible line or an invisible line passes therethrough.
Claim 71
Dependent Claim
24 words
A method according to Claim 66, further comprising the step of forming text lines for each text block based on the detected skew angle.
Claim 72
Dependent Claim
22 words
A method according to Claim 66, further comprising the step of character recognizing the pixel connected components within the formed text blocks.
Claim 73
Dependent Claim
74 words
Apparatus for forming text blocks in a stored document having both horizontal and vertical text, comprising: storing means for storing the stored documents; processing means for (1) identifying connected pixel components, (2) grouping the identified pixel connected components horizontally and vertically, (3) forming irregularly-shaped horizontal and vertical text blocks based on the grouped components and without having performed skew detection, and (4) thereafter detecting the skew angle for each of the formed text block.
Claim 74
Dependent Claim
16 words
Apparatus according to Claim 73, wherein said processing means separates text and non-text pixel connected components.
Claim 75
Dependent Claim
24 words
Apparatus according to Claim 74, wherein said processing means classifies the non-text components into at least one of a predetermined plurality of non-text classifications.
Claim 76
Dependent Claim
22 words
Apparatus according to Claim 74, wherein said processing means searches the stored document for invisible lines along edges of non-text connected components.
Claim 77
Dependent Claim
24 words
Apparatus according to Claim 73, wherein said processing means splits a formed text block of a visible line or an invisible line passes therethrough.
Claim 78
Dependent Claim
22 words
Apparatus according to Claim 73, wherein said processing means forms text lines for each text block based on the detected skew angle.
Claim 79
Dependent Claim
20 words
Apparatus according to Claim 73, wherein said processing means character recognizes the connected pixel components in the formed text blocks.
Claim 80
Independent Claim
139 words
A method for forming text and non-text blocks in a stored document having non-text information and horizontal and vertical text information, comprising the steps of: identifying connected pixel components; separating the identified pixel components into text and non-text components; grouping connected text components horizontally and vertically; searching said document for visible lines and for invisible lines along edges of non-text components; forming irregularly-shaped non-text blocks and irregularly-shaped horizontal and vertical text blocks based on the grouped text components and visible and invisible lines, without having performed skew detection; detecting the text orientation for each formed text block; extracting text lines from the text block based on the detected text orientation; thereafter detecting the skew angle for each of the formed text and non-text blocks; and modifying the formed horizontal and vertical text blocks based on the detected skew angle.
Claim 81
Dependent Claim
156 words
Apparatus for forming text and non-text blocks in a stored document having non-text information and horizontal and vertical text information, comprising: storing means for storing the stored documents; and processing means for (1) identifying connected pixel components, (2) separating the identified pixel components into text and non-text components, (3) grouping connected text components horizontally and vertically, (4) searching the stored document for visible lines and for invisible lines along edges of non-text components, (5) forming irregularly-shaped non-text blocks and irregularly-shaped horizontal and vertical text blocks based on the grouped text components and visible and invisible lines, without having performed skew detection, (6) detecting the text orientation for each formed text block, (7) extracting text lines from the text blocks based on the detected text orientation, (8) thereafter detecting the skew angle for each of the formed text and non-text blocks, and (9) modifying the formed horizontal and vertical text blocks based on the detected skew angle.
Claim 82
Independent Claim
30 words
A method of or apparatus for processing image data by classifying blocks of said image data based upon their characteristics and performing alternative processing on the basis of such classification.
Claim 83
Independent Claim
40 words
A method of or apparatus for forming image data of similar characteristics into blocks by identifying portions with a desired characteristic and combining identified portions of the image horizontally and/or vertically dependent upon the size and/or closeness of adjoining portions.
Claim 84
Dependent Claim
23 words
A method or apparatus according to claim 83 wherein said portions comprise text characters identified by outlining connected pixels of an input image.
Claim 85
Independent Claim
11 words
A method or apparatus comprising any combination of the preceding claims.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.