Method and apparatus for selecting blocks of image data from image data having both horizontally- and vertically-oriented blocks

Claim 3

A method according to claim 1, further comprising an inputting step in which pixel image data is input, 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 4

A method according to claim 1, wherein in said forming step, the smallest irregularly-shaped curve is formed around each block of pixel image data.

Claim 5

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 6

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 7

A method according to claim 5, further comprising the step of recognizing character images in the text blocks.

Claim 8

A method according to claim 6, further comprising the step of deriving white contours for non-text outlined connected components.

Claim 9

A method according to claim 7, wherein non-text blocks are designated as table units in accordance with the number of white contours.

Claim 10

A method according to claim 8, further comprising the step of calculating the white contour filling rate.

Claim 11

A method according to claim 10, wherein the non-text block is not designated as image data in the event that the white contour filling rate is high.

Claim 12

A method according to claim 9, further comprising the step of recombining non-grid-arranged white contours.

Claim 13

A method according to claim 11, wherein the non-text block is designated as a table in the event that the recombination rate is not high.

Claim 14

A method according to claim 7, wherein white contours are calculated in 4 directions.

Claim 15

A method according to claim 1, wherein contours of connected components are outlined in at least 8 directions.

Claim 16

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

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 event that a gap separates the connected components.

Claim 18

A method according to claim 16, wherein columns are detected in accordance with vertically-extending gaps between connected components.

Claim 19

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

A method according to claim 1, further comprising the step of compressing the pixel image data before said outlining step.

Claim 21

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 rectangles around blocks of pixel image data, and (4) forming an irregularly-shaped curve around each block of pixel image data surrounded by a rectangle which overlaps another block of pixel image data.

Claim 22

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 rectangles around blocks of pixel image data, and (4) forming an irregularly-shaped curve around each block of pixel image data surrounded by a rectangle which overlaps another block of pixel image data.

Claim 23

An apparatus according to claim 20, 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 24

An apparatus according to claim 20, wherein said processing means forms the smallest irregularly-shaped curve around each block of pixel image data.

Claim 25

An apparatus according to claim 20, 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 26

An apparatus according to claim 23, wherein said processing means classifies the formed irregularly-shaped curves into text and non-text blocks.

Claim 27

An apparatus according to claim 24, wherein said processing means recognizes character images in the text blocks.

Claim 28

An apparatus according to claim 24, wherein said processing means derives white contours for non-text outlined connected components.

Claim 29

An apparatus according to claim 26, wherein said processing means designates non-text blocks as table units in accordance with the number of white contours.

Claim 30

An apparatus according to claim 26, wherein said processing means calculates a white contour filling rate.

Claim 31

An apparatus according to claim 28, wherein said processing means does not designate the non-text block as image data in the event that the white contour filling rate is high.

Claim 32

An apparatus according to claim 28, wherein said processing means recombines non-grid arranged white contours.

Claim 33

An apparatus according to claim 30, wherein said processing means designates the non-text block as a table in the event that the recombination rate is not high.

Claim 34

An apparatus according to claim 26, wherein said processing means calculates white contours in four directions.

Claim 35

An apparatus according to claim 20, wherein said processing means outlines contours of connected components in at least 8 directions.

Claim 36

An apparatus according to claim 20, wherein said processing means outlines the contours of connected components only at exterior portions of the connected components.

Claim 37

An apparatus according to claim 20, 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

An apparatus according to claim 35, wherein said processing means detects columns in accordance with vertically-extending gaps between connected components.

Claim 39

An apparatus according to claim 20, 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

An apparatus according to claim 20, wherein said processing means compresses the pixel image data before outlining.

Claim 43

A method according to claim 39, further comprising a pre-processing step in which the pixel image data is pre-processed.

Claim 44

A method according to claim 40, wherein said pre-processing step includes the step of image compression.

Claim 45

A method according to claim 41, wherein said pre-processing step includes the step of enhancing pixel image data.

Claim 46

A method according to claim 39, further comprising the step of white-contour tracing the interior of non-text units.

Claim 47

A method according to claim 43, further comprising the step of appending designators to non-text units.

Claim 48

A method according to claim 43, wherein table designators are appended to non-text units based on the number of white contours contained therein.

Claim 49

A method according to claim 39, wherein in said forming step, the hierarchical tree is formed with both text units and non-text units.

Claim 50

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 pixel image 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 rectangles around blocks of text units based on proximity of adjacent text lines and on the position of non-text units between text lines, (5) surrounding each block of text units in the blocks of text units with an irregularly-shaped curve when rectangles around the blocks of text units overlap, (6) forming a hierarchical tree of the blocks of text units based on the outlined connected components, and (7) segmenting the treed text blocks into lines of pixel image data by adaptively dividing blocks of text units into at least one line.

Claim 51

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 pixel image 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 rectangles around blocks of text units based on proximity of adjacent text lines and on the position of non-text units between text lines, (5) surrounding each block of text units in the blocks of text units with an irregularly-shaped curve when rectangles around the blocks of text units overlap, (6) forming a hierarchical tree of the blocks of text units based on the outlined connected components, and (7) segmenting the treed text blocks into lines of pixel image data by adaptively dividing blocks of text units into at least one line.

Claim 52

Apparatus according to claim 47, wherein said processing means pre-processes the input pixel image data.

Claim 53

An apparatus according to claim 47, wherein said processing means forms the hierarchical tree with both text units and non-text units.