Method of analyzing digital document images

• US 8,306,335 B2
• Filed: 03/30/2011
• Issued: 11/06/2012
• Est. Priority Date: 03/30/2011
• Status: Active Grant

• Current Assignee: Seiko Epson Corporation (Seiko Group)
• Original Assignee: Seiko Epson Corporation (Seiko Group)
• Inventors: Lukac, Rastislav
• Primary Examiner(s): Desire, Gregory M
• Application Number:
  US13/075,978
• Publication Number:
  US 20120250105A1
• Time in Patent Office: 587 Days
• Field of Search: 358/461, 358/474, 382/165, 382/173, 382/190, 382/260, 382/270
• US Class Current: 382/190
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/147 Determination of region of interest
• CPC Class Codes: G06V 30/1607 Correcting image deformation, e.g. trapezoidal deformation caused by perspective
• CPC Class Codes: G06V 30/162 Quantising the image signal
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text

Abstract

Analyzing an input image, the input image being one of a digitized image stored in a memory or a scanned image from a scanner. Forming a feature image from the input image by dividing the input image into a plurality of blocks of pixels, thus associating each block of pixels in the input image with a single pixel in the feature image, and outputting the feature image for further analysis or storage in a memory. Example embodiments extract and analyze features from a document image to detect particular characteristics associated with the page area, the distortion area, and the book spine area. Extracted features can be further analyzed to detect document characteristics at the paragraph, line, word, and character levels.

Claims

1. A method for analyzing an input image x with K₁×

K₂ pixels x_(r,s) where (r,s) denotes the pixel location with r=1, 2, . . . , K₁ indicating the image row, and s=1, 2, . . . , K₂ indicating the image column, the input image being one of a digitized image stored in a memory or a scanned image from a scanner, comprising;

using a processor to form a feature image z from the input image x by;

dividing the input image x into a plurality of blocks of pixels each block having a block size of g₁×

g₂ pixels, where g₁ denotes a number of image rows in a block and g₂ denotes a number of image columns in a block,

associating each block of pixels in the input image x with a single pixel in the feature image z, with the feature image z consisting of K₁/g₁×

K₂/g₂ pixels, and

outputting the feature image z for further analysis or storage in a memory,

wherein the feature image z is a two-channel image with feature pixels z_(m,n)=[f_(m,n), b_(m,n)] , for m=1, 2, . . . , K₁/g₁ and n=1, 2, . . . , K₂ /g₂ , wherein f_(m,n) and b_(m,n) denote, respectively, the foreground and background components of a feature pixel z_(m,n),

wherein the foreground and background components of a feature pixel z_(m,n) are respectively defined as follows;

f_(m,n)=min{x_(r,s);

(m−

1)g₁<

r≦

mg₁,(n−

1)g₂<

s<

ng₂}

b_(m,n)=max{x_(r,s);

(m−

1)g₁<

r≦

mg₁,(n−

1)g₂<

s≦

ng₂}

where min and max are the minimum and maximum operators, and

wherein the processor detects pages according to;

2. A method as in claim 1, wherein the processor detects pages according to:

3. A method as in claim 1, wherein the processor subjects the binary map d to object segmentation by grouping adjacent pixels with d_(m,n)=1.

4. A method as in claim 3, wherein the processor partitions the binary map d into N disjoint objects O_i={(m,n)ε

Φ

_i;

d_(m,n)ⁱ=1}, for i=1, 2, . . . , N, wherein each object is characterized by Φ

_i which is the set of pixel locations (m,n) where d_(m,n)ⁱ=1 and a Φ

_i^y×

Φ

_i^x is a bounding box with height Φ

_i^y and width Φ

_i^x.

5. A method as in claim 4, wherein the processor removes small objects and objects with bounding boxes of irregular aspect ratios as follows:

6. A method as in claim 4 wherein the processor analyzes the objects to detect a page orientation in the input image x by comparing a height of the object to a width of the object.

7. A method as in claim 4 wherein the processor analyzes the objects to detect a book spine in the input image x.

8. A device for analyzing an input image x with K₁ ×

K₂ pixels x_(r,s) where (r,s) denotes the pixel location with r=1, 2, . . . , K₁ indicating the image row, and s=1, 2, . . . , K₂ indicating the image column, comprising;

an image capture unit that captures input image x;

a memory that stores input image x; and

a processor that forms a feature image z from the input image x by;

dividing the input image x into a plurality of blocks of pixels each block having a block size of g₁×

g₂ pixels, where g₁ denotes a number of image rows in a block and g₂ denotes a number of image columns in a block,

associating each block of pixels in the input image x with a single pixel in the feature image z, with the feature image z consisting of K₁/g₁×

K/g₂ pixels, and

outputting the feature image z for further analysis or storage in a memory,

wherein the feature image z is a two-channel image with feature pixels z_(m,n)=[f_(m,n),b_(m,n)], for m=1, 2, . . . , K₁/g₂ and n=1, 2, . . . , K₂/g₂, wherein f_(m,n) and b_(m,n) denote, respectively, the foreground and background components of a feature pixel z_(m,n),

wherein the foreground and background components of a feature pixel z_(m,n) are respectively defined as follows;

f_(m,n)=min{x_(r,s);

(m−

1)g₁<

r≦

mg₁, (n−

1)g₂<

s≦

ng₂}

b_(m,n)=max{x_(r,s);

(m−

1)g₁<

r≦

mg₁,(n−

1)g₂<

s≦

ng₂}

where min and max are the minimum and maximum operators, and

wherein the processor detects pages according to;

9. A device as in claim 8, wherein the image capture unit is a scanning unit.

10. One or more tangible computer-readable media having computer-readable instructions thereon, which, when executed by a processor analyze an input image x with K₁ ×

K₂ pixels x_(r,s) where (r,s) denotes the pixel location with r=1,2, . . . , K₁ indicating the image row, and s=1, 2, . . . , K₂ indicating the image column, the input image being one of a digitized image stored in a memory or a scanned image from a scanner, wherein;

the processor forms a feature image z from the input image x by;

dividing the input image x into a plurality of blocks of pixels each block having a block size of g₁×

g₂ pixels, where g₁ denotes a number of image rows in a block and g₂ denotes a number of image columns in a block,

associating each block of pixels in the input image x with a single pixel in the feature image z, with the feature image z consisting of K₁/g₁×

K₂ /g₂ pixels, and

outputting the feature image z for further analysis or storage in a memory,

wherein the feature image z is a two-channel image with feature pixels z_(m,n)=[f_(m,n),b_(m,n)], for m=1, 2, . . . , K₁/g₂ and n=1, 2, . . . , K₂/g₂, wherein f_(m,n) and b_(m,n) denote, respectively, the foreground and background components of a feature pixel z_(m,n),

wherein the foreground and background components of a feature pixel z_(m,n) are respectively defined as follows;

f_(m,n)=min{x_(r,s);

(m−

1)g₁<

r≦

mg₁, (n−

1)g₂<

s≦

ng₂}

b_(m,n)=max{x_(r,s);

(m−

1)g₁<

r≦

mg₁, (n−

1)g₂<

s≦

ng₂}

where min and max are the minimum and maximum operators, and

wherein the processor detects pages according to;

11. The one or more tangible computer-readable media as in claim 10, wherein the processor detects pages according to: