Image retrieval

• US 7,519,236 B2
• Filed: 04/09/2003
• Issued: 04/14/2009
• Est. Priority Date: 04/09/2003
• Status: Active Grant

• Current Assignee: ArcSoft, Inc.
• Original Assignee: ArcSoft, Inc.
• Inventors: Xiong, Wei, Cheng, Min, Zhou, Lingxiang
• Primary Examiner(s): Bella; Matthew C.
• Assistant Examiner(s): LIEW, ALEX KOK SOON
• Application Number:
  US10/411,532
• Publication Number:
  US 20040202385A1
• Time in Patent Office: 2,197 Days
• Field of Search: 382/305
• US Class Current: 382/305
• CPC Class Codes: G06V 10/32 Normalisation of the pattern dimensions

Abstract

A method for searching an image database includes capturing an image of a photograph and a background, determining a boundary of the photograph in the image, cropping the photograph from the image, correcting the perspective of the photograph, compensating colors of the photograph, and matching the photograph with an image in the image database.

Claims

1. A method for retrieving an image from an image database, comprising:

capturing a first image of a printed photograph against a background using an image input device;

determining a boundary of the printed photograph from the background in the first image, using a processor, comprising;

capturing a second image of the background without the printed photography using the image input device;

determining differences between the first and the second images, the differences defining a region;

determining a perimeter of the region; and

determining boundary lines from the perimeter, the boundary lines defining the boundary of the printed photograph from the background in the first image, said determining boundary lines comprising;

performing Hough Transformation to detect the boundary lines from the perimeter;

invalidating a boundary line when the boundary line is too close to a corresponding edge of the first image, the boundary line is substantially parallel to the corresponding edge, and a confidence in the boundary line'"'"'s subtense is high; and

searching for another boundary line to replace the boundary line after said invalidating;

cropping the printed photograph from the first image to form a third image of the printed photograph; and

matching the third image with a fourth image in the image database.

2. The method of claim 1, wherein said determining a perimeter of the region comprises:

scanning each of horizontal and vertical lines that comprise the region; and

reserving a first pixel and a last pixel in each of the horizontal and the vertical lines as pixels that comprise the perimeter of the region.

3. The method of claim 1, wherein said searching for another boundary line comprises:

using Hough Transformation to detect said another boundary line, wherein the angle of said another boundary line is limited within a range of the angle of the invalid boundary line'"'"'s subtense.

4. The method of claim 1, further comprising rotating the third image after said cropping and before said matching.

5. The method of claim 4, wherein said rotating the third image comprises performing an Affine Transformation.

6. The method of claim 4, further comprising, resizing the third image before said matching.

7. The method of claim 1, wherein said matching comprises using at least one of edge feature matching, texture feature matching, and color feature matching to match the third image to images in the image database.

8. The method of claim 1, further comprising compensating colors of the third image before said matching.

9. The method of claim 8, wherein said compensating colors of the third image comprises performing histogram equalization to the third image.

10. The method of claim 8, wherein said compensating colors of the third image comprises performing color constancy to the third image.

14. The method of claim 1, wherein the image input device is selected from the group consisting a digital video camera, a digital still camera, and a scanner.

15. The method of claim 6, further comprising, transmitting the first image from a client computer over a network to a sewer computer, wherein said capturing and said transmitting are performed by the client computer.

11. A method for searching an image database, comprising:

capturing a first image of a printed photograph against a background using an image input device;

determining a boundary of the printed photograph from the background in the first image, using a processor;

cropping the printed photograph from the first image to form a second image of the printed photograph;

compensating colors of the second image of the printed photograph, said compensating colors comprising performing color constancy to the second image of the printed photograph, said performing color constancy comprising transforming the second image of the printed photograph using an inverse homography matrix to approximate RGB values of the second image under a first lighting condition; and

matching the second image with a third image in the image database.

12. The method of claim 11, wherein said performing color constancy further comprises:

generating a physical copy of a reference image, wherein the reference image is assumed to be captured under the first lighting condition;

capturing a test image of the physical copy under a second lighting condition with the image input device;

determining a homography matrix that transforms RGB values of the reference image under the first lighting condition to RGB values of the physical copy under the second lighting condition; and

inverting the homography matrix to generate the inverse homography matrix.

13. The method of claim 12, wherein the reference image comprises a plurality of blocks having different colors.

16. The method of 15, wherein said determining a boundary, said cropping, said rotating, said resizing, and said matching are performed by the server computer.

17. The method of claim 16, further comprising:

transmitting by the server computer the fourth image to the client computer; and

displaying by the client computer the fourth image.