EP0567344A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Method and apparatus for character recognition
Assignee: Canon Inc
•
Filing: 1993-04-23
•
Granted: —
•
Expires: 2013-04-23
Abstract
Abstract A method and apparatus for recognizing characters in pixel image data and for forming a text file of the characters. Pixel image data is inputted and, if the pixel image data is not binary image data then the pixel image data is converted into binary pixel image data. Blocks of pixel image data are selected by outlining contours of connected components in the pixel image data, determining whether the outlined connected components include text unit or non-text units based on the size of the outlined connected components, selectively connecting text units widthwisely to form text lines based on proximity of adjacent text units, and 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. A hierarchical tree is formed based on the outlined connected components. Text blocks are segmented into text lines of pixel data by adaptively dividing the text blocks into at least one column based on a horizontal projection of pixel density across the column, and characters are cut from the segmented lines in two cutting steps in which the first cutting step cuts between non-touching and non-overlapping characters and the second cutting step cuts between touching characters. The cut characters are recognized and character codes are derived based on such recognition. The character codes are stored in a computer text file in accordance with the order established by the hierarchical tree. If desired, the non-text units may be interspersed with the stored character codes in accordance with the order established by the hierarchical tree. The pixel image data may be pre-processed by, for example, image compression or image enhancement, and the recognized characters may be subjected to post-processing, for example, context checking. Designators may be appended to non-text units based on characteristics of the non-text units. For example, white contour tracing may be employed on the interior of non-text units, non-grid-arranged white contours may be recombined, and the fill rate of the white contours may be calculated, and table designators appended to the non-text unit based on the number of white contours or the recombination rate of non-grid-arranged white contours or the fill rate of white contours. Cutting between non-touching and non-overlapping characters may be accomplished by sparsely stepping through the line segment, and cutting between touching characters may be accomplished in accordance with whether information concerning the spacing between touching characters is known. If information concerning the spacing is known, then cutting may be accomplished based on the spacing statistics. If information is not known, then cutting between touching characters may be accomplished in accordance with rotated projections of pixel density so as to make an oblique cut through the touching characters at an angle and position determined by the rotated projection. Inadvertently characters may be recombined.
Inventors
- 👤 Shin-Ywan c/o Canon Information Systems Wang
- 👤 Mehrzad R. c/o Canon Information Systems Vaezi
- 👤 Christopher A. c/o Canon Info. Systems Sherrick
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-31 15:42
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/40; G06V30/41; G06V30/413; G06V30/10; G06V30/14; G06V30/148; G06V30/15; G06V30/155; G06V30/414
Claims Analysis
Total Claims: 170
Claim 1
Independent Claim
81 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; forming a rectangle around each connected component outlined in said outlining step; a first connecting step in which rectangles are selectably connected widthwisely based on size and proximity to other rectangles to form lines; and a second connecting step in which lines are selectably connected vertically based on size and proximity to other lines to form blocks.
Claim 2
Independent Claim
81 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; forming a rectangle around each connected component outlined in said outlining step; a first connecting step in which rectangles are selectably connected widthwisely based on size and proximity to other rectangles to form lines; and a second connecting step in which lines are selectably connected vertically based on size and proximity to other lines to form blocks.
Claim 3
Dependent Claim
47 words
A method according to Claim 1, further comprising the step of inputting pixel image data, wherein said input 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 4
Dependent Claim
20 words
A method according to Claim 1, wherein in said forming step the smallest rectangle is formed around each connected component.
Claim 5
Dependent Claim
35 words
Amethod 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 rectangles formed in said forming step.
Claim 6
Dependent Claim
24 words
A method according to Claim 4, further comprising the step of classifying the rectangles formed in said forming step into text and non-text units.
Claim 7
Dependent Claim
19 words
A method according to Claim 5, further comprising the step of recognizing character images in blocks of text units.
Claim 8
Dependent Claim
21 words
A method according to Claim 5, wherein said classifying step is performed in accordance with a predetermined threshold of unit height.
Claim 9
Dependent Claim
28 words
A method according to Claim 6, wherein said classifying step is performed in accordance with statistical information concerning the height of said rectangles formed in said forming step.
Claim 10
Dependent Claim
22 words
A method according to Claim 6, wherein said first connecting step and said second connecting step are not performed for non-text units.
Claim 11
Dependent Claim
17 words
A method according to Claim 6, further comprising the step of deriving white contours for non-text units.
Claim 12
Dependent Claim
22 words
A method according to Claim 10, wherein non-text units are designated as table units in accordance with the number of white contours.
Claim 13
Dependent Claim
17 words
A method according to Claim 10, further comprising the step of calculating the white contour filling rate.
Claim 14
Dependent Claim
25 words
A method according to Claim 12, wherein the non-text unit is not designated as image data in the event that the filling rate is high.
Claim 15
Dependent Claim
15 words
A method according to Claim 12, further comprising the step of recombining non-grid-arranged white contours.
Claim 16
Dependent Claim
25 words
A method according to Claim 14, wherein the non-text unit is designated as a table in the event that the recombination rate is not high.
Claim 17
Dependent Claim
13 words
A method according to Claim 10, wherein white contours are calculated in 4-directions.
Claim 18
Dependent Claim
17 words
A method according to Claim 1, wherein contours of connected components are outlined in at least 8-directions.
Claim 19
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 20
Dependent Claim
40 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 rectangles are not connected into lines in the event that a gap separates the rectangles.
Claim 21
Dependent Claim
18 words
A method according to Claim 19, wherein columns are detected in accordance with vertically extending gaps between rectangles.
Claim 22
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 23
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 24
Independent Claim
115 words
A method for recognizing characters in pixel image data comprising the steps of: selecting blocks of pixels from the pixel image data, said selecting step including the step of outlining contours of connected components in the pixel image data, determining whether the outlined connected components include text units or non-text units, selectively connecting text units widthwisely to form text lines, and selectively connecting text lines vertically to form text blocks; segmenting text blocks into lines of pixel image data; cutting characters from the line segmented in said segmenting step; recognizing characters cut in said cutting step; and storing characters recognized in said recognizing step in accordance with an order established in said block selecting step.
Claim 25
Independent Claim
115 words
A method for recognizing characters in pixel image data comprising the steps of: selecting blocks of pixels from the pixel image data, said selecting step including the step of outlining contours of connected components in the pixel image data, determining whether the outlined connected components include text units or non-text units, selectively connecting text units widthwisely to form text lines, and selectively connecting text lines vertically to form text blocks; segmenting text blocks into lines of pixel image data; cutting characters from the line segmented in said segmenting step; recognizing characters cut in said cutting step; and storing characters recognized in said recognizing step in accordance with an order established in said block selecting step.
Claim 26
Dependent Claim
19 words
A method according to Claim 23, further comprising the step of recognizing character images in blocks of text units.
Claim 27
Dependent Claim
19 words
A method according to Claim 23, further comprising a pre-processing step in which the pixel image data is pre-processed.
Claim 28
Dependent Claim
16 words
A method according to Claim 25, wherein said pre-processing step includes the step of image compression.
Claim 29
Dependent Claim
22 words
A method according to Claim 25, wherein said pre-processing step includes the step of filtering so as to enhance pixel image data.
Claim 30
Dependent Claim
18 words
Amethod according to Claim 23, further comprising the step of post-processing the characters recognized in said recognizing step.
Claim 31
Dependent Claim
12 words
A method according to Claim 28, wherein said post-processing includes context checking.
Claim 32
Dependent Claim
47 words
A method according to Claim 23, further comprising the step of inputting pixel image data, wherein said input 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 33
Dependent Claim
29 words
A method according to Claim 23, wherein said block selecting step includes the step of forming a hierarchical tree based on the connected components outlined in said outlining step.
Claim 34
Dependent Claim
22 words
Amethod according to Claim 31, further comprising the step of forming a rectangle around the connected components outlined in said outlining step.
Claim 35
Dependent Claim
24 words
A method according to Claim 32, wherein the hierarchical tree is formed based on the position of the rectangles formed in said forming step.
Claim 36
Dependent Claim
23 words
A method according to Claim 31, further comprising the step of updating the hierarchial tree based on the first and second connecting steps.
Claim 37
Dependent Claim
21 words
A method according to Claim 31, further comprising the step of classifying the connected contours as text units or non-text units.
Claim 38
Dependent Claim
22 words
A method according to Claim 35, wherein said first and second connecting steps connect text units but do not connect non-text units.
Claim 39
Dependent Claim
18 words
A method according to Claim 35, further comprising the step of white-contour tracing the interior of non-text units.
Claim 40
Dependent Claim
25 words
A method according to Claim 37, further comprising the step of designating non-text units as tables based on the number of white contours contained therein.
Claim 41
Dependent Claim
15 words
A method according to Claim 37, further comprising the step of recombining non-grid-arranged white contours.
Claim 42
Dependent Claim
19 words
Amethod according to Claim 39, wherein non-text units are designated as tables based on recombination in said recombining step.
Claim 43
Dependent Claim
18 words
A method according to Claim 35, further comprising calculating the fill rate of white contours in non-text units.
Claim 44
Dependent Claim
25 words
A method according to Claim 41, wherein the non-text unit is not designated as a table in the event that the fill rate is high.
Claim 45
Independent Claim
208 words
A method for forming a text file of characters in pixel image data comprising the steps 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; selecting blocks of pixel image data, said selecting step including the steps of outlining contours of connected components in the pixel image data, determining whether the outlined connected components include text units or non-text units based on the size of the outlined connected components, selectively connecting text units widthwisely to form text lines based on proximity of adjacent text units, and 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; forming a hierarchical tree based on the connected components outlined in said outlining step; segmenting text blocks into lines of pixel image data; cutting characters from the line segmented in said segmenting step; recognizing characters cut in said cutting step and deriving character codes based on said recognition; and storing the character codes in a computer text file in accordance with an order established by said hierarchical tree.
Claim 46
Independent Claim
208 words
A method for forming a text file of characters in pixel image data comprising the steps 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; selecting blocks of pixel image data, said selecting step including the steps of outlining contours of connected components in the pixel image data, determining whether the outlined connected components include text units or non-text units based on the size of the outlined connected components, selectively connecting text units widthwisely to form text lines based on proximity of adjacent text units, and 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; forming a hierarchical tree based on the connected components outlined in said outlining step; segmenting text blocks into lines of pixel image data; cutting characters from the line segmented in said segmenting step; recognizing characters cut in said cutting step and deriving character codes based on said recognition; and storing the character codes in a computer text file in accordance with an order established by said hierarchical tree.
Claim 47
Dependent Claim
19 words
A method according to Claim 43, further comprising a pre-processing step in which the pixel image data is pre-processed.
Claim 48
Dependent Claim
16 words
A method according to Claim 44, wherein said pre-processing step includes the step of image compression.
Claim 49
Dependent Claim
18 words
A method according to Claim 45, wherein said pre-processing step includes the step of enhancing pixel image data.
Claim 50
Dependent Claim
22 words
Amethod according to Claim43, further comprising the step of post-processing the characters recognized in said recognizing step, said post-processing including context checking.
Claim 51
Dependent Claim
18 words
A method according to Claim 43, further comprising the step of white-contour tracing the interior of non-text units.
Claim 52
Dependent Claim
16 words
A method according to Claim 48, further comprising the step of appending designators to non-text units.
Claim 53
Dependent Claim
26 words
A method according to Claim 49, further comprising the step of appending table designators to non-text units based on the number of white contours contained therein.
Claim 54
Dependent Claim
32 words
A method according to Claim 49, further comprising the step of recombining non-grid-arranged white contours, wherein table designators are appended to non-text units based on the recombination rate in said recombining step.
Claim 55
Dependent Claim
36 words
A method according to claim 49, further comprising calculating the fill rate of white contours in non-text units, wherein table designators are appended to non-text units in the event that the fill rate is not high.
Claim 56
Independent Claim
66 words
A method of identifying the position of lines in pixel image data comprising the steps of: obtaining a horizontal projection of image density across a widthwisely extending portion of the image data; determining, based on the horizontal projection, whether to decrease the width of the portion across which image density is projected; and identifying a position of a line on the basis of the horizontal projection.
Claim 57
Independent Claim
66 words
A method of identifying the position of lines in pixel image data comprising the steps of: obtaining a horizontal projection of image density across a widthwisely extending portion of the image data; determining, based on the horizontal projection, whether to decrease the width of the portion across which image density is projected; and identifying a position of a line on the basis of the horizontal projection.
Claim 58
Dependent Claim
39 words
A method according to claim 53, wherein said determining step comprises the step of inspecting the horizontal projection for substantially empty regions and the step of decreasing the width in the event that substantially empty regions are not found.
Claim 59
Dependent Claim
19 words
A method according to Claim 54 wherein said inspecting step includes the step of connecting closely spaced non-empty regions.
Claim 60
Dependent Claim
19 words
A method according to Claim 53 wherein said obtaining step and said determining step are serially and repeatedly executed.
Claim 61
Dependent Claim
30 words
Amethod according to Claim 53 wherein in said identifying step the position of lines of image data between substantially empty areas of the horizontal projection is identified as a line.
Claim 62
Dependent Claim
17 words
A method according to Claim 53 further comprising a pre-processing step for pre-processing the pixel image data.
Claim 63
Independent Claim
81 words
A method of identifying the position of a line in pixel image data that is dividable into columns, comprising the steps of: obtaining a horizontal projection of image density across at least one widthwisely extending column of the image data; determining, based on the horizontal projection obtained in said obtaining step, whet her to increase the number of columns across which image density is projected; and identifying the position of lines in the digital image data based on the horizontal projection.
Claim 64
Independent Claim
81 words
A method of identifying the position of a line in pixel image data that is dividable into columns, comprising the steps of: obtaining a horizontal projection of image density across at least one widthwisely extending column of the image data; determining, based on the horizontal projection obtained in said obtaining step, whet her to increase the number of columns across which image density is projected; and identifying the position of lines in the digital image data based on the horizontal projection.
Claim 65
Dependent Claim
41 words
A method according to Claim 59 wherein said determining step comprises the step of inspecting the horizontal projection for substantially empty regions and the step of increasing the number of columns in the event that substantially empty regions are not found.
Claim 66
Dependent Claim
19 words
A method according to Claim 60 wherein said inspecting step includes the step of connecting closely spaced non-empty regions.
Claim 67
Dependent Claim
19 words
A method according to Claim 59 wherein said obtaining step and said determining step are serially and repeatedly executed.
Claim 68
Dependent Claim
30 words
Amethod according to Claim 59 wherein in said identifying step the position of lines of image data between substantially empty areas of the horizontal projection is identified as a line.
Claim 69
Dependent Claim
22 words
A method according to Claim 59 further comprising the step of determining whether lines in adjacent columns of the image data overlap.
Claim 70
Dependent Claim
25 words
A method according to Claim 64 wherein the step of determining whether blocks in adjacent columns of image data overlap comprises a scale invariant determination.
Claim 71
Dependent Claim
26 words
A method according to Claim 59 further comprising a pre-processing step for pre-processing the pixel image data, said pre-processing step including the step of image reduction.
Claim 72
Dependent Claim
17 words
A method according to Claim 66 wherein said image reduction is different in horizontal and vertical directions.
Claim 73
Independent Claim
51 words
A method for cutting character images from a line segment of pixel image data comprising the steps of: a first cutting layer step in which non-touching and non-overlapping characters are cut from a line segment; and a second cutting layer step in which touching characters are cut from the line segment.
Claim 74
Independent Claim
51 words
A method for cutting character images from a line segment of pixel image data comprising the steps of: a first cutting layer step in which non-touching and non-overlapping characters are cut from a line segment; and a second cutting layer step in which touching characters are cut from the line segment.
Claim 75
Dependent Claim
27 words
A method according to Claim 68 further comprising the step of pre-processing line segment image data so as to compress high resolution image segments into low resolution.
Claim 76
Dependent Claim
15 words
Amethod according to Claim 69 wherein different compression ratios are utilized forvertical and horizontal directions.
Claim 77
Dependent Claim
37 words
A method according to Claim 68 further comprising the step of recognition-processing characters cut in said first cutting layer step, wherein said second layer cutting step is performed only for characters not recognized in said recognizing step.
Claim 78
Dependent Claim
26 words
A method according to Claim 71 further comprising an intermediate cutting layer step in which non-touching but overlapping character data is cut from the line segment.
Claim 79
Dependent Claim
27 words
A method according to Claim 72 wherein said intermediate cutting layer step includes the step of cutting non-touching but overlapping characters by outlining contours of pixel data.
Claim 80
Dependent Claim
20 words
A method according to Claim 72 wherein said intermediate cutting layer step includes the step of recombining inadvertently cut characters.
Claim 81
Dependent Claim
19 words
A method according to Claim 71 further comprising the step of recombining characters not recognized in said recognizing step.
Claim 82
Dependent Claim
28 words
A method according to Claim 68 wherein said first cutting layer step includes the step of sparsely stepping across said line segment until non-blank pixel data is found.
Claim 83
Dependent Claim
30 words
A method according to Claim 76 further comprising the step of densely searching forwardly and backwardly in the event that a non-blank pixel is found in said sparsely stepping step.
Claim 84
Dependent Claim
22 words
A method according to Claim 68 wherein said second cutting layer step includes the step of cutting touching characters by non-vertical cuts.
Claim 85
Dependent Claim
25 words
A method according to Claim 78 wherein the angle of the non-vertical cuts is determined in accordance with a vertical projection profile of pixel density.
Claim 86
Dependent Claim
24 words
A method according to Claim 79 further comprising the step of obtaining at least one rotated projection profile based on the vertical projection profile.
Claim 87
Dependent Claim
32 words
A method according to Claim 80 further comprising the step of obtaining plural rotated projection profiles at angles corresponding to angles in the vicinity of the angle of said vertical projection profile.
Claim 88
Dependent Claim
37 words
A method according to Claim 81 wherein the angle of the non-vertical cut is obtained based on the minimum value of the projection profiles obtained from said rotated projection profiling steps and said vertical projection profiling steps.
Claim 89
Dependent Claim
27 words
A method according to Claim 68 wherein said second cutting layer step is selectable based on whether characteristics of the characters in said line segment are known.
Claim 90
Dependent Claim
28 words
A method according to Claim 83 wherein said second cutting layer step includes the step of cutting based on spacing statistics of character data in the character set.
Claim 91
Dependent Claim
15 words
Amethod according to Claim 84 further comprising the step of recombining pairs of undersized characters.
Claim 92
Independent Claim
110 words
A method for cutting between touching characters in a line segment of character pixel data comprising the steps of: obtaining a vertical projection profile of pixel data in the line segment; a first calculating step in which at least one angle is calculated from a minimum in the vertical projection profile to an adjacent maximum in the vertical projection profile; a second calculating step in which at least one rotated projection profile is calculated based on the angle calculated in said first calculating step; and cutting the line segment at the angle of said rotated projection profile and at a position corresponding to a minimum in the rotated projection profile.
Claim 93
Independent Claim
110 words
A method for cutting between touching characters in a line segment of character pixel data comprising the steps of: obtaining a vertical projection profile of pixel data in the line segment; a first calculating step in which at least one angle is calculated from a minimum in the vertical projection profile to an adjacent maximum in the vertical projection profile; a second calculating step in which at least one rotated projection profile is calculated based on the angle calculated in said first calculating step; and cutting the line segment at the angle of said rotated projection profile and at a position corresponding to a minimum in the rotated projection profile.
Claim 94
Dependent Claim
34 words
A method according to Claim 86 wherein said first calculating step includes the step of comparing the vertical projection profile to plural thresholds to determine the location of the minimum and the adjacent maximum.
Claim 95
Dependent Claim
27 words
A method according to Claim 87 further comprising the step of incrementing said thresholds in the event that a minimum and an adjacent maximum are not located.
Claim 96
Dependent Claim
39 words
Amethod according to Claim 87 wherein a minimum is identified as a point on the vertical projection profile below a first threshold that is surrounded on at least one side by a maximum that is above a second threshold.
Claim 97
Dependent Claim
40 words
Amethod according to Claim 86 further comprising the step of calculating plural rotated projection profiles, each of the plural rotated projection profiles being calculated at angles in the vicinity of a rotated projection profile calculated in said second calculating step.
Claim 98
Dependent Claim
55 words
A method according to Claim 90 further comprising the step of identifying an overall minimum in the plural rotated projection profiles and the vertical projection profile, wherein said cutting step cuts at an angle corresponding to the angle from which the minimum was obtained and at a position corresponding to the position of the minimum.
Claim 99
Independent Claim
127 words
A method for recognizing characters in pixel image data comprising the steps of: selecting blocks of pixels from the pixel image data; segmenting text blocks into lines of pixel data by adaptively dividing the text blocks into at least one column based on a horizontal projection of pixel density across said at least one column; cutting characters from the line segmented in said segmenting step, said cutting step including a first cutting layer step in which non-touching and non-overlapping characters are cut from the line segment and at least one additional cutting layer step in which touching characters are cut; recognizing the characters cut in said cutting step; and storing characters recognized in said recognizing step in accordance with an order established in said block selecting step.
Claim 100
Independent Claim
127 words
A method for recognizing characters in pixel image data comprising the steps of: selecting blocks of pixels from the pixel image data; segmenting text blocks into lines of pixel data by adaptively dividing the text blocks into at least one column based on a horizontal projection of pixel density across said at least one column; cutting characters from the line segmented in said segmenting step, said cutting step including a first cutting layer step in which non-touching and non-overlapping characters are cut from the line segment and at least one additional cutting layer step in which touching characters are cut; recognizing the characters cut in said cutting step; and storing characters recognized in said recognizing step in accordance with an order established in said block selecting step.
Claim 101
Dependent Claim
47 words
A method according to Claim 92 further comprising the step of inputting pixel image data, wherein said input 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 102
Dependent Claim
19 words
A method according to Claim 92 further comprising a pre-processing step in which said pixel image data is pre-processed.
Claim 103
Dependent Claim
15 words
Amethod according to Claim 94 wherein said pre-processing step includes the step of image compression.
Claim 104
Dependent Claim
23 words
A method according to Claim 94 wherein said pre-processing step includes the step of filtering so as to enhance the pixel image data.
Claim 105
Dependent Claim
19 words
A method according to Claim 92 further comprising the step of post-processing the characters recognized in said recognizing step.
Claim 106
Dependent Claim
12 words
A method according to Claim 97 wherein said post-processing includes context checking.
Claim 107
Dependent Claim
22 words
A method according to Claim 92 wherein said first cutting layer step includes the step of sparsely stepping through the line segment.
Claim 108
Dependent Claim
29 words
A method according to Claim 92 wherein said additional cutting layer step is selectable in accordance with whether characteristics are known about the characters in the pixel image data.
Claim 109
Dependent Claim
21 words
A method according to Claim 100 wherein said additional cutting layer step cuts based on statistics of a known character set.
Claim 110
Dependent Claim
22 words
A method according to Claim 100 wherein said additional cutting layer step cuts in accordance with a rotated projection of pixel density.
Claim 111
Dependent Claim
27 words
A method according to Claim 102 wherein the rotated projection of pixel density is obtained at an angle determined based on a vertical projection of pixel density.
Claim 112
Dependent Claim
27 words
A method according to Claim 102 further comprising an intermediate cutting layer step between said first cutting layer and said at least one additional cutting layer step.
Claim 113
Dependent Claim
23 words
Amethod according to Claim 104 wherein said intermediate cutting layer step includes the step of outlining overlapping pixel images in the line segment.
Claim 114
Dependent Claim
29 words
A method according to Claim 105 further comprising the step of recombining characters cut in said intermediate cutting layer step in the event that the characters were cut inadvertently.
Claim 115
Dependent Claim
44 words
A method according to Claim 106 wherein said recognizing step recognizes characters cut in said first cutting layer step before said additional cutting layer step, and wherein said additional cutting layer step is applied to characters that are not recognized in said recognizing step.
Claim 116
Dependent Claim
36 words
A method according to Claim 107 further comprising the step of recombining the characters cut in said at least one additional cutting layer step in the event that characters are not recognized in said recognizing step.
Claim 117
Independent Claim
199 words
A method for forming a text file of characters in pixel image data comprising the steps 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; selecting blocks of pixel image data in accordance with whether the blocks of pixel image data are text blocks or non-text blocks; obtaining a hierarchical tree of the text and non-text blocks; segmenting text blocks into lines of pixel image data by adaptively dividing the text blocks into at least one column based on a horizontal projection of pixel density across said at least one column; cutting characters from the line segmented in said segmenting step, said cutting step including a first cutting layer step in which non-touching and non-overlapping characters are cut from the line segment and at least one additional cutting layer step in which touching characters are cut; recognizing characters cut in said cutting step and deriving character codes based on said recognition; and storing the character codes in a computer text file in accordance with an order established by the hierarchical tree.
Claim 118
Independent Claim
199 words
A method for forming a text file of characters in pixel image data comprising the steps 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; selecting blocks of pixel image data in accordance with whether the blocks of pixel image data are text blocks or non-text blocks; obtaining a hierarchical tree of the text and non-text blocks; segmenting text blocks into lines of pixel image data by adaptively dividing the text blocks into at least one column based on a horizontal projection of pixel density across said at least one column; cutting characters from the line segmented in said segmenting step, said cutting step including a first cutting layer step in which non-touching and non-overlapping characters are cut from the line segment and at least one additional cutting layer step in which touching characters are cut; recognizing characters cut in said cutting step and deriving character codes based on said recognition; and storing the character codes in a computer text file in accordance with an order established by the hierarchical tree.
Claim 119
Independent Claim
18 words
A method according to 109 further comprising a pre-processing step in which the pixel image data is pre-processed.
Claim 120
Independent Claim
18 words
A method according to 109 further comprising a pre-processing step in which the pixel image data is pre-processed.
Claim 121
Dependent Claim
16 words
A method according to Claim 110 wherein said pre-processing step includes the step of image compression.
Claim 122
Dependent Claim
18 words
A method according to Claim 111 wherein said pre-processing step includes the step of enhancing pixel image data.
Claim 123
Dependent Claim
24 words
A method according to Claim 109 further comprising the step of post-processing the characters recognized in said recognizing step, said post-processing including context checking.
Claim 124
Dependent Claim
21 words
Amethod according to Claim 109 wherein said first cutting layer step includes the step of sparsely stepping through the line segment.
Claim 125
Dependent Claim
29 words
A method according to Claim 109 wherein said additional cutting layer step is selectable in accordance with whether characteristics are known about the characters in the pixel image data.
Claim 126
Dependent Claim
21 words
Amethod according to Claim 115 wherein said additional cutting layer step cuts based on spacing statistics of a known character set.
Claim 127
Dependent Claim
22 words
A method according to Claim 115 wherein said additional cutting layer step cuts in accordance with a rotated projection of pixel density.
Claim 128
Dependent Claim
27 words
A method according to Claim 117 wherein the rotated projection of pixel density is obtained at an angle determined based on a vertical projection of pixel density.
Claim 129
Dependent Claim
27 words
A method according to Claim 109 further comprising an intermediate cutting layer step between said first cutting layer and said at least one additional cutting layer step.
Claim 130
Dependent Claim
23 words
Amethod according to Claim 119 wherein said intermediate cutting layer step includes the step of outlining overlapping pixel images in the line segment.
Claim 131
Dependent Claim
29 words
A method according to Claim 120 further comprising the step of recombining characters cut in said intermediate cutting layer step in the event that the characters were cut inadvertently.
Claim 132
Dependent Claim
44 words
A method according to Claim 121 wherein said recognizing step recognizes characters cut in said first cutting layer step before said additional cutting layer step, and wherein said additional cutting layer step is applied to characters that are not recognized in said recognizing step.
Claim 133
Dependent Claim
36 words
A method according to Claim 122 further comprising the step of recombining the characters cut in said at least one additional cutting layer step in the event that characters are not recognized in said recognizing step.
Claim 134
Independent Claim
270 words
A method for forming a text file of characters in pixel image data, comprising the steps 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 image data; selecting blocks of pixel image data, said selecting step including the step of outlining contours of connected components in the pixel image data, determining during the steps of outlining determining outlined connected components include text units or non-text units based on the size of the outlined connected components, selectively connecting text units widthwisely to form text lines based on proximity of adjacent text units, and 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; forming a hierarchical tree based on the connected components outlined in said outlining step; segmenting text blocks into lines of pixel data by adaptively dividing text blocks into at least one column based on a horizontal projection of pixel density across said at least one column; cutting characters from the lines segmented in said segmenting step, said cutting step including a first cutting layer step in which non-touching and non-overlapping characters are cut from the line segment and at least one additional cutting layer step in which touching characters are cut; recognizing the characters cut in said cutting step and deriving character codes based on said recognition; and storing the character codes in a computer text file in accordance with an order established by the hierarchical tree.
Claim 135
Independent Claim
270 words
A method for forming a text file of characters in pixel image data, comprising the steps 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 image data; selecting blocks of pixel image data, said selecting step including the step of outlining contours of connected components in the pixel image data, determining during the steps of outlining determining outlined connected components include text units or non-text units based on the size of the outlined connected components, selectively connecting text units widthwisely to form text lines based on proximity of adjacent text units, and 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; forming a hierarchical tree based on the connected components outlined in said outlining step; segmenting text blocks into lines of pixel data by adaptively dividing text blocks into at least one column based on a horizontal projection of pixel density across said at least one column; cutting characters from the lines segmented in said segmenting step, said cutting step including a first cutting layer step in which non-touching and non-overlapping characters are cut from the line segment and at least one additional cutting layer step in which touching characters are cut; recognizing the characters cut in said cutting step and deriving character codes based on said recognition; and storing the character codes in a computer text file in accordance with an order established by the hierarchical tree.
Claim 136
Independent Claim
18 words
A method according to 124 further comprising a pre-processing step in which the pixel image data is pre-processed.
Claim 137
Independent Claim
18 words
A method according to 124 further comprising a pre-processing step in which the pixel image data is pre-processed.
Claim 138
Dependent Claim
16 words
A method according to Claim 125 wherein said pre-processing step includes the step of image compression.
Claim 139
Dependent Claim
18 words
A method according to Claim 126 wherein said pre-processing step includes the step of enhancing pixel image data.
Claim 140
Dependent Claim
24 words
A method according to Claim 124 further comprising the step of post-processing the characters recognized in said recognizing step, said post-processing including context checking.
Claim 141
Dependent Claim
22 words
A method according to Claim 124 wherein said first cutting layer step includes the step of sparsely stepping through the line segment.
Claim 142
Dependent Claim
29 words
A method according to Claim 124 wherein said additional cutting layer step is selectable in accordance with whether characteristics are known about the characters in the pixel image data.
Claim 143
Dependent Claim
21 words
Amethod according to Claim 130 wherein said additional cutting layer step cuts based on spacing statistics of a known character set.
Claim 144
Dependent Claim
22 words
A method according to Claim 130 wherein said additional cutting layer step cuts in accordance with a rotated projection of pixel density.
Claim 145
Dependent Claim
27 words
A method according to Claim 132 wherein the rotated projection of pixel density is obtained at an angle determined based on a vertical projection of pixel density.
Claim 146
Dependent Claim
27 words
A method according to Claim 124 further comprising an intermediate cutting layer step between said first cutting layer and said at least one additional cutting layer step.
Claim 147
Dependent Claim
23 words
Amethod according to Claim 134 wherein said intermediate cutting layer step includes the step of outlining overlapping pixel images in the line segment.
Claim 148
Dependent Claim
29 words
A method according to Claim 135 further comprising the step of recombining characters cut in said intermediate cutting layer step in the event that the characters were cut inadvertently.
Claim 149
Dependent Claim
44 words
A method according to Claim 136 wherein said recognizing step recognizes characters cut in said first cutting layer step before said additional cutting layer step, and wherein said additional cutting layer step is applied to characters that are not recognized in said recognizing step.
Claim 150
Dependent Claim
36 words
A method according to Claim 137 further comprising the step of recombining the characters cut in said at least one additional cutting layer step in the event that characters are not recognized in said recognizing step.
Claim 151
Dependent Claim
18 words
A method according to Claim 124 further comprising the step of white-contour tracing the interior of non-text units.
Claim 152
Dependent Claim
16 words
A method according to Claim 139 further comprising the step of appending designators to non-text units.
Claim 153
Dependent Claim
23 words
A method according to claim 140, wherein table designators are appended to non-text units based on the number of white contours contained therein.
Claim 154
Dependent Claim
31 words
Amethod according to claim 140, further comprising the step of recombining non-grid-arranged white contours, wherein table designators are appended to non-text units based on the recombination rate in said recombining step.
Claim 155
Dependent Claim
39 words
A method according to claim 140, further comprising the step of calculating the fill rate of white contours in non-text units, wherein table designators are appended to non-text units in the event that the fill rate is not high.
Claim 156
Independent Claim
35 words
A method of recognising text data in an image, including the steps of identifying individual components as text characters and selectively connecting said components into lines of text and said lines into blocks of text.
Claim 157
Independent Claim
35 words
A method of recognising text data in an image, including the steps of identifying individual components as text characters and selectively connecting said components into lines of text and said lines into blocks of text.
Claim 158
Independent Claim
41 words
A method of recognising text data in an image, wherein text and or non-text units of the image are connected by a hierarchical tree structure, recognised individually and assembled into an output document in an order determined by said hierachical structure.
Claim 159
Independent Claim
41 words
A method of recognising text data in an image, wherein text and or non-text units of the image are connected by a hierarchical tree structure, recognised individually and assembled into an output document in an order determined by said hierachical structure.
Claim 160
Independent Claim
15 words
A method of recognising tabulated text data in an image by means of white contouring.
Claim 161
Independent Claim
15 words
A method of recognising tabulated text data in an image by means of white contouring.
Claim 162
Independent Claim
25 words
A method of identifying text lines in an image wherein sub-division of the image into columns is increased adaptively until the text lines are resolved.
Claim 163
Independent Claim
25 words
A method of identifying text lines in an image wherein sub-division of the image into columns is increased adaptively until the text lines are resolved.
Claim 164
Independent Claim
29 words
A method of identifying individual characters in an image representing a text line, wherein characters are cut from the image by sparsely steping along the pixels of the line.
Claim 165
Independent Claim
29 words
A method of identifying individual characters in an image representing a text line, wherein characters are cut from the image by sparsely steping along the pixels of the line.
Claim 166
Independent Claim
25 words
A method identifying characters in an image of a text line, including cutting overlapping and/or touching characters based on statistical information of a character set.
Claim 167
Independent Claim
25 words
A method identifying characters in an image of a text line, including cutting overlapping and/or touching characters based on statistical information of a character set.
Claim 168
Independent Claim
25 words
A method of identifying individual characters in an image of a text line, wherein character boundaries are determined from rotated projection profiles of the image.
Claim 169
Independent Claim
25 words
A method of identifying individual characters in an image of a text line, wherein character boundaries are determined from rotated projection profiles of the image.
Claim 170
Independent Claim
21 words
An apparatus comprising means configured to operate in accordance with the steps of a method as claimed in any preceding claim.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.