Removal of image artifacts from sensor dust
View Patent ↗Removal of the effects of dust or other impurities on image data is described. In one example, a model of artifact formation from sensor dust is determined. From the model of artifact formation, contextual information in the image and a color consistency constraint may be applied on the dust to remove the dust artifacts. Artifacts may also be removed from multiple images from the same or different cameras or camera settings.
1. A system comprising a computing device and at least one program module that are together configured for performing actions, the computing device including at least one processor and memory, the actions comprising:
detecting, by the computing device, an artifact in a digital image, where the detecting comprises partitioning the digital image into overlapping regions; and
removing, by the computing device from the digital image, the detected artifact that results from a physical impurity, where the removing is based on projection characteristics of the physical impurity and on correlations in colors identified in the physical impurity, and where the removing results in an impurity-free appearance in the digital image.
2. The system of claim 1 where the physical impurity is located on or near a lens, sensor, or other component of an image capturing system producing the digital image.
3. The system of claim 1 where an amount of overlap of the overlapping regions is selected to avoid missing any artifacts located on region boundaries.
4. The system of claim 1 where the detecting further comprises estimating a projection geometry factor.
5. The system of claim 4 where an actual projection geometry factor is unknown to the system.
6. The system of claim 1 where each of the overlapping regions comprises a number of pixels of the digital image.
7. A method performed on a computing device that includes at least one processor and memory, the method comprising:
detecting, by the computing device, an artifact in a digital image, where the detecting comprises partitioning the digital image into overlapping regions; and
removing, by the computing device from the digital image, the detected artifact that results from a physical impurity, where the removing is based on projection characteristics of the physical impurity and on correlations in colors identified in the physical impurity, and where the removing results in an impurity-free appearance in the digital image.
8. The method of claim 7 where the physical impurity is located on or near a lens, sensor, or other component of an image capturing system producing the digital image.
9. The method of claim 7 where an amount of overlap of the overlapping regions is selected to avoid missing any artifacts located on region boundaries.
10. The method of claim 7 where the detecting further comprises estimating a projection geometry factor.
11. The method of claim 10 where an actual projection geometry factor is unknown to the system.
12. The method of claim 7 where each of the overlapping regions comprises a number of pixels of the digital image.
13. At least one computer-readable storage device storing computer-executable instructions that, when executed by at least one processor of a computing device that includes memory, cause the computing device to perform actions comprising:
detecting, by the computing device, an artifact in a digital image, where the detecting comprises partitioning the digital image into overlapping regions; and
removing, by the computing device from the digital image, the detected artifact that results from a physical impurity, where the removing is based on projection characteristics of the physical impurity and on correlations in colors identified in the physical impurity, and where the removing results in an impurity-free appearance in the digital image.
14. The at least one computer-readable storage device of claim 13 where the physical impurity is located on or near a lens, sensor, or other component of an image capturing system producing the digital image.
15. The at least one computer-readable storage device of claim 13 , where each of the overlapping regions comprises a number of pixels of the digital image.
16. The at least one computer-readable storage device of claim 13 where an amount of overlap of the overlapping regions is selected to avoid missing any artifacts located on region boundaries.
17. The at least one computer-readable storage device of claim 13 where the detecting further comprises estimating a projection geometry factor.
18. The at least one computer-readable storage device of claim 17 where an actual projection geometry factor is unknown to the system.