Cross Device Image Recognition Improvement

• US 20110249893A1
• Filed: 04/12/2010
• Published: 10/13/2011
• Est. Priority Date: 04/12/2010
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Marle, Christophe, Bamidele, Adetokunbo, Jacob, Matthias, Gao, Jiang, Schloter, Philipp
• Granted Patent: US 8,369,617 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06T 5/90 Dynamic range modification of images or parts thereof
• CPC Class Codes: H04N 1/6052 Matching two or more picture signal generators or two or more picture reproducers

Abstract

A method includes modifying values of image data of a first image of an object, the first image taken by a user using a user equipment. The modifying is performed to map one or more color characteristics of one or more color components of the user equipment to corresponding one or more color characteristics for the one or more color components of a reference device. The modifying creates a modified image. On the user equipment, comparisons are performed between the modified image and a number of second images of objects taken by the reference device. Apparatus and program products are also disclosed. Additionally, a user interface is disclosed that provides for training a device model that is used during the mapping.

Claims

1. A method, comprising:

modifying values of image data of a first image of an object, the first image taken by a user using a user equipment, the modifying performed to map at least one color characteristic of at least one color component of the user equipment to a corresponding at least one color characteristic for the at least one color component of a reference device, the modifying creating a modified image; and

on the user equipment, performing comparisons between the modified image and a plurality of second images of objects taken by the reference device.

2. The method of claim 1, wherein performing comparisons further comprises:

selecting an image for presentation to the user based on the comparisons; and

allowing the user to confirm if the presented image is an image of the object in the first image.

3. The method of claim 2, further comprising, in response to the user confirming the presented image is an image of the object in the first image, presenting information related to the object to the user.

4. The method of claim 2:

further comprising, in response to the user confirming that the presented image is an image of the object in the first image, creating a transformation that maps the at least one color characteristic of the at least one color component of the first image to a corresponding the at least one color characteristic for the at least one color component of the reference device; and

wherein modifying values further comprises applying the transformation to the values of the image data corresponding to the at least one color component.

5. The method of claim 1, wherein modifying further comprises applying a mapping to the values, the mapping converting white balance of the at least one color component of the user equipment to a corresponding white balance for the at least one color component of the reference device.

6. The method of claim 5, wherein the mapping is a first mapping and modifying further comprises applying a second mapping to the values, the second mapping converting contrast, saturation, or both contrast and saturation of the at least one color component of the user equipment to a corresponding contrast, saturation, or both contrast and saturation for the at least one color component of the reference device.

7. The method of claim 1, wherein each value of image data has a component corresponding to each of the at least one color components, and wherein there are three color components:

one color component for red, one color component for blue, and one color component for green.

8. The method of claim 1:

further comprising creating a transformation that maps the at least one color characteristic of the at least one color component of the user equipment to a corresponding at least one color characteristic for the at least one color component of the reference device; and

wherein modifying values further comprises applying the transformation to the values of the image data corresponding to the at least one color component.

9. The method of claim 8, wherein creating a transformation further comprises for each of the at least one color components:

computing a histogram for the color component on the user equipment and on the reference device;

transforming the color component of the user equipment if histogram distortion exceeds a preset threshold;

determining a piece-wise linear mapping of the color component for the user equipment being transformed, the piece-wise linear mapping converting color component values of the user equipment to color component values of the reference device; and

for each interval of the piece-wise mapping function, setting endpoints of the interval to be the threshold points.

10. The method of claim 9, wherein creating a transformation further comprises, for each of the at least one color components on the user equipment:

defining a reference dynamic range of pixel intensity values;

sorting pixel intensity values in the first image;

selecting the highest M values and the lowest M values;

averaging the highest M values;

averaging the lowest M values;

determining a true dynamic range based on the averages;

calculating, using a piece-wise transform, a mapping of the true dynamic range to a reference dynamic range of the reference device.

11. The method of claim 10, wherein each of the true dynamic ranges is used for corresponding at least one color components when transforming the corresponding at least one color components of the user equipment if histogram distortion exceeds a preset threshold.

12. An apparatus comprising:

at least one processor configured to cause the apparatus to perform at least the following;

modifying values of image data of a first image of an object, the first image taken by a user using the apparatus, the modifying performed to map at least one color characteristic of at least one color component of the apparatus to a corresponding at least one color characteristic for the at least one color component of a reference device, the modifying creating a modified image; and

performing comparisons between the modified image and a plurality of second images of objects taken by the reference device.

13. The apparatus of claim 12, wherein performing comparisons further comprises:

selecting an image for presentation to the user based on the comparisons; and

allowing the user to confirm if the presented image is an image of the object in the first image.

15. The apparatus of claim 13:

wherein the at least one processor is further configured to cause the apparatus to perform, in response to the user confirming that the presented image is an image of the object in the first image, creating a transformation that maps the at least one color characteristic of the at least one color component of the first image to a corresponding the at least one color characteristic for the at least one color component of the reference device; and

wherein modifying values further comprises applying the transformation to the values of the image data corresponding to the at least one color component.

16. The apparatus of claim 12, wherein modifying further comprises applying a mapping to the values, the mapping converting white balance of the at least one color component of the apparatus to a corresponding white balance for the at least one color component of the reference device.

17. The apparatus of claim 16, wherein the mapping is a first mapping and modifying further comprises applying a second mapping to the values, the second mapping converting contrast, saturation, or both contrast and saturation of the at least one color component of the apparatus to a corresponding contrast, saturation, or both contrast and saturation for the at least one color component of the reference device.

18. The apparatus of claim 12, wherein each value of image data has a component corresponding to each of the at least one color components, and wherein there are three color components:

one color component for red, one color component for blue, and one color component for green.

19. The apparatus of claim 12:

wherein the at least one processor is further configured to cause the apparatus to perform creating a transformation that maps the at least one color characteristic of the at least one color component of the apparatus to a corresponding at least one color characteristic for the at least one color component of the reference device; and

wherein modifying values further comprises applying the transformation to the values of the image data corresponding to the at least one color component.

23. The apparatus of claim 12, further comprising at least one memory comprising computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform the modifying the values and the performing the comparisons.

14. (canceled)

20. (canceled)

21. (canceled)

22. (canceled)

24. A computer program product comprising a computer-readable storage medium bearing computer program code embodied therein for use with an apparatus, the computer program code comprising:

code for modifying values of image data of a first image of an object, the first image taken by a user using the apparatus, the modifying performed to map at least one color characteristic of at least one color component of the apparatus to a corresponding at least one color characteristic for the at least one color component of a reference device, the modifying creating a modified image; and

code for performing comparisons between the modified image and a plurality of second images of objects taken by the reference device.