Preprocessing for information pattern analysis

• US 7,920,753 B2
• Filed: 06/12/2008
• Issued: 04/05/2011
• Est. Priority Date: 05/25/2005
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Dang, Yingnong, Wang, Jian, Chen, Liyong
• Primary Examiner(s): Kassa; Yosef
• Application Number:
  US12/138,339
• Publication Number:
  US 20090067743A1
• Time in Patent Office: 1,027 Days
• Field of Search: 382/260, 382/274, 382/275, 358/3.26, 358/3.27, 358/463
• US Class Current: 382/254
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments
• CPC Class Codes: G06V 30/162 Quantising the image signal

Abstract

Pre-processing techniques for processing an image to improve the distinctiveness of an information pattern captured in the image before the information pattern is analyzed in a decoding process. The brightness of an image first is normalized by dividing the image into blocks of areas, such as pixels. A brightness distribution value then is determined for each area of the image by fitting the brightness of its surrounding blocks using bilinear interpolation and extrapolation, and a normalized brightness value for each area can then be obtained by dividing the original brightness value by the brightness distribution value. Next, masks are created to distinguish the information pattern from content captured in the image. The masks may be generated based upon contrast differences between the brightness of pixels representing the information pattern, the brightness of pixels representing content, and the brightness of pixels representing the background of the writing medium.

Claims

1. A method performed by a computing device having a memory and a processor for identifying an information pattern containing embedded position information in an image of a document, the method comprising:

identifying high-contrast regions in an image of a document;

obtaining a first threshold brightness value for distinguishing areas of the image that represent content;

analyzing each area in the image to determine if a brightness value for the area is below the first threshold;

designating areas in the high-contrast regions having a brightness value below the first threshold as areas representing content so as to identify content areas and non-content areas;

obtaining a second threshold brightness value for distinguishing areas of the image that represent an information pattern;

analyzing each non-content area in the image to determine if a brightness value for the area is below the second threshold; and

designating non-content areas having a brightness value below the second threshold as pattern areas representing the information pattern

wherein the information pattern contains embedded position information and is used to determine the position of the image relative to the document and

wherein the identifying, analyzing, and designating are performed by the processor executing instructions stored in the memory.

2. The method recited in claim 1, further comprising applying an average filter to each area of the image before identifying high-contrast areas in the image.

3. The method recited in claim 1, further comprising

organizing neighboring content areas into regions, and

if a region has fewer than a specified number of areas, designating each of the areas in the region as non-content areas.

4. The method recited in claim 1, further comprising:

analyzing each pattern area to determine if the pattern area is adjacent to a content area; and

if the pattern area is adjacent to a content area, changing the designation of the pattern area to a blank area.

5. The method recited in claim 1, wherein

the image is a black-and-white image;

and

the brightness values are gray level values

6. The method recited in claim 1, wherein

the image is a color image, and

the brightness level values are color brightness values.

7. A system, having a memory and a processor, comprising:

a module that identifies high-contrast regions in an image of a document;

a module that obtains a first threshold brightness value for distinguishing areas of the image that represent content;

a module that analyzes each area in the image to determine if a brightness value for the area is below the first threshold;

a module that designates areas in the high-contrast regions having a brightness value below the first threshold as areas representing content so as to identify content areas and non-content areas;

a module that obtains a second threshold brightness value for distinguishing areas of the image that represent an information pattern;

a module that analyzes each non-content area in the image to determine if a brightness value for the area is below the second threshold; and

a module that designates non-content areas having a brightness value below the second threshold as pattern areas representing the information pattern

wherein at least one of the modules comprises computer-executable instructions stored in the memory for execution by the computer.

8. The system of claim 7, further comprising:

a module that applies an average filter to each area of the image before the high-contrast areas in the image are identified.

9. The system of claim 7, further comprising:

a module that organizes neighboring content areas into regions and, if a region has fewer than a specified number of areas, designates each of the areas in the region as non-content areas.

10. The system of claim 7, further comprising:

a module that analyzes each pattern area to determine if the pattern area is adjacent to a content area; and

a module that, if the pattern area is adjacent to a content area, changes the designation of the pattern area to a blank area.

11. The system of claim 7, wherein

the image is a black-and-white image;

and

the brightness values are gray level values

12. The system of claim 7, wherein

the image is a color image, and

the brightness level values are color brightness values.