Metadata-driven method and apparatus for constraining solution space in image processing techniques

• US 8,675,988 B2
• Filed: 11/21/2012
• Issued: 03/18/2014
• Est. Priority Date: 08/29/2008
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Chen, Simon, Chien, Jen-Chan, Jin, Hailin
• Primary Examiner(s): Patel, Jayesh A
• Application Number:
  US13/683,966
• Publication Number:
  US 20130077890A1
• Time in Patent Office: 482 Days
• Field of Search: None
• US Class Current: 382/275
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 3/18 Image warping, e.g. rearranging pixels individually
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: H04N 1/32101 Display, printing, storage or transmission of additional information, e.g. ID code, date and time or title
• CPC Class Codes: H04N 2201/3252 Image capture parameters, e.g. resolution, illumination conditions, orientation of the image capture device H04N2201/3256 and subgroups take precedence
• CPC Class Codes: H04N 23/698 for achieving an enlarged field of view, e.g. panoramic image capture
• CPC Class Codes: H04N 23/73 by influencing the exposure time
• CPC Class Codes: H04N 23/741 by increasing the dynamic range of the image compared to the dynamic range of the electronic image sensors
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof
• CPC Class Codes: H04N 25/60 Noise processing, e.g. detecting, correcting, reducing or removing noise

Abstract

Methods and apparatus for constraining solution space in image processing techniques may use the metadata for a set of images to constrain an image processing solution to a smaller solution space. In one embodiment, a process may require N parameters for processing an image. A determination may be made from metadata that multiple images were captured with the same camera/lens and with the same settings. A set of values may be estimated for the N parameters from data in one or more of the images. The process may then be applied to each of images using the set of values. In one embodiment, a value for a parameter of a process may be estimated for an image. If the estimated value deviates substantially from a value for the parameter in the metadata, the metadata value is used in the process instead of the estimated value.

Claims

1. A computer-implemented method, comprising:

estimating, from image content of an image, a value for a parameter to be used in a digital image processing technique when applied to the image;

obtaining, from metadata corresponding to the image, a value for the parameter determined when capturing the image;

ascertaining by a computing system whether a difference between the estimated value for the parameter and the value for the parameter obtained from the metadata is above or below a threshold;

determining by the computing system that the difference between the estimated value for the parameter and the value for the parameter obtained from the metadata exceeds the threshold; and

applying the digital image processing technique to the image to reduce lens distortions by an image unwarping function to generate an output image, the value for the parameter obtained from the metadata is used in the digital image processing technique instead of the estimated value in response to the determining that the difference exceeds the threshold.

2. The computer-implemented method as described in claim 1, wherein the digital image processing technique is a vignette removal process.

3. The computer-implemented method as described in claim 2, wherein the parameter is exposure.

4. The computer-implemented method as described in claim 1, wherein the applying is performed to drive estimation of other variables in the digital image processing technique.

5. The computer-implemented method as described in claim 1, wherein the digital image processing technique is performable to reduce the lens distortions through use of a fisheye distortion model.

6. The computer-implemented method as described in claim 1, wherein the digital image processing technique is performable to reduce chromatic aberrations.

7. The computer-implemented method as described in claim 6, wherein the chromatic aberrations include longitudinal or transverse chromatic aberrations.

8. The computer-implemented method as described in claim 1, wherein the digital image processing technique employs a sensor noise model usable to reduce noise.

9. A system comprising:

one or more processors; and

a computer-readable storage device storing one or more processing modules that are executable by the one or more processors to cause the system to perform operations including;

ascertaining whether a difference between an estimated value for a parameter estimated from image content of an image and a value for the parameter obtained from metadata corresponding to the image is above or below a threshold;

determining that the difference exceeds the threshold; and

responsive to the determination that the difference between the estimated value and the value obtained from the metadata exceeds the threshold, applying a digital image processing technique that includes a vignette removal process to the image to generate an output image using the value for the parameter obtained from the metadata instead of the estimated value.

10. The system as described in claim 9, wherein the value obtained from the metadata is determined when capturing the image.

11. The system as described in claim 9, wherein the parameter is exposure.

12. The system as described in claim 9, wherein the application of the digital image processing technique using the value is performed to drive estimation of other variables in the digital image processing technique.

13. The system as described in claim 9, wherein the digital image processing technique is performable to:

reduce lens distortions by an image unwarping function or through use of a fisheye distortion model;

reduce chromatic aberrations that include longitudinal or transverse chromatic aberrations;

or reduce noise using a sensor noise model.

14. A computer-implemented method, comprising:

ascertaining whether a difference between an estimated value for a parameter estimated from image content of an image and a value for the parameter obtained from metadata corresponding to the image is above or below a threshold;

determining, based on said ascertaining, that the difference exceeds the threshold; and

applying a digital image processing technique to the image to generate an output image using the value for the parameter obtained from the metadata instead of the estimated value responsive to the determination, the digital image processing technique configured to reduce chromatic aberrations that include longitudinal or transverse chromatic aberrations or reduce noise using a sensor noise model.

15. The computer-implemented method as described in claim 14, wherein the value obtained from the metadata is determined when capturing the image.

16. The computer-implemented method as described in claim 14, wherein the digital image processing technique is a vignette removal process and the parameter is exposure.

17. The computer-implemented method as described in claim 14, wherein the applying of the digital image processing technique using the value is performed to drive estimation of other variables in the digital image processing technique.

18. A computer-implemented method as described in claim 14, wherein the digital image processing technique is performable to reduce lens distortions by an image unwarping function or through use of a fisheye distortion model.