Methods and systems for identifying digital image characteristics

• US 8,340,430 B2
• Filed: 07/10/2007
• Issued: 12/25/2012
• Est. Priority Date: 07/10/2007
• Status: Active Grant

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Laboratories of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Campbell, Richard John
• Primary Examiner(s): Le, Vu
• Assistant Examiner(s): Allison, Andrae S
• Application Number:
  US11/775,773
• Publication Number:
  US 20090016611A1
• Time in Patent Office: 1,995 Days
• Field of Search: 382/289, 382/290, 382/291, 382/293, 382/295, 382/296, 382/297, 382/135, 382/137, 382/151, 382/170, 382/173, 382/157, 382/176, 382/177, 382/178, 382/179, 382/180, 382/185, 382/186, 382/187, 382/190, 382/209, 382/215, 382/216, 382/218, 382/219, 382/229, 382/231, 382/278, 382/282, 382/287, 358/453, 358/462, 358/488, 358/496, 358/648, 358/649, 358/657, 358/659
• US Class Current: 382/190
• CPC Class Codes: G06V 10/242 by image rotation, e.g. by 90 degrees

Abstract

Aspects of the present invention relate to methods and systems for determining image characteristics in a digital image.

Claims

1. A method for determining an image characteristic in a digital image, said method comprising:

forming a binary image from a digital image;

determining a first glyph component in said binary image;

determining a first reference location for said first glyph component;

determining a first feature location, in said first glyph component, associated with a first feature, wherein said first feature is associated with a first pattern comprising a plurality of glyph pixels, a plurality of non-glyph pixels and at least one don'"'"'t care pixel, and wherein said determining a first feature location comprises matching a pixel region comprising a pixel in said first glyph component and a plurality of pixels surrounding said pixel to said first pattern, wherein said pixel is a first feature location when all glyph pixels in said plurality of glyph pixels correspond to glyph pixels in said pixel region and all non-glyph pixels in said plurality of non-glyph pixels correspond to non-glyph pixels in said pixel region;

determining a first position, relative to said first reference location, of said first feature location, wherein said first position indicates in which quadrant, relative to said first reference location, said first feature location is located;

accumulating, in a first distribution counter, a frequency-of-occurrence count related to said first feature and said first position; and

determining an image characteristic based on a distribution feature, wherein said distribution feature is based on said first distribution counter.

2. A method according to claim 1 further comprising determining a confidence level associated with said image characteristic.

3. A method according to claim 1, wherein said determining an image characteristic comprises inputting said distribution feature to a classifier which has been previously trained.

4. A method according to claim 1 further comprising:

determining a second feature location, in said first glyph component, associated with a second feature, wherein said second feature is associated with a second pattern;

determining a second position, relative to said first reference location, of said second feature location, wherein said second position indicates in which quadrant, relative to said first reference location, said second feature location is located; and

accumulating, in said first distribution counter, a frequency-of-occurrence count related to said second feature and said second position.

5. A method according to claim 1, wherein said first reference location is the centroid of said first glyph component.

6. A method according to claim 1, wherein said determining a first reference location comprises:

determining a first bounding box for said first glyph component; and

determining the center of said first bounding box.

7. A method according to claim 1, wherein said determining a first position comprises a quadrant decomposition based on said first reference location.

8. A method according to claim 1, wherein said image characteristic is an orientation characteristic.

9. A method according to claim 1, wherein said image characteristic is a language characteristic.

10. A method according to claim 1 further comprising:

determining a second glyph component in said binary image;

determining a second reference location for said second glyph component;

determining a second feature location, in said second glyph component, associated with said first feature;

determining a second position, relative to said second reference location, of said second feature location, wherein said second position indicates in which quadrant, relative to said second reference location, said second feature location is located; and

accumulating, in a second distribution counter, a frequency-of-occurrence count related to said first feature and said second position.

11. A method according to claim 10 further comprising combining said second distribution counter and said first distribution counter to form said distribution feature.