Image Matting and Alpha Value Techniques

• US 20140119643A1
• Filed: 10/25/2012
• Published: 05/01/2014
• Est. Priority Date: 10/25/2012
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Price, Brian L., Cohen, Scott D., Miller, Gavin Stuart Peter, Feild, Jacqueline L.
• Granted Patent: US 9,064,318 B2
• Time in Patent Office: Days
• US Class Current: 382/164
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation

Abstract

Image matting and alpha value techniques are described. In one or more implementations, techniques are described in which matting operations are applied to image data that is in a raw or substantially raw image format. This may be used to decompose image data into foreground and background images as well as to generate an alpha value that describes a linear combination of the foreground and background images for a respective pixel. Further, implementations are also described in which a plurality of alpha values is generated for each of a plurality of pixels. These alpha values may be utilized to support a variety of different functionality, such as matting operations and so on.

Claims

1. A method comprising:

obtaining image data in a substantially raw image format that is generated by one or more image sensors; and

performing one or more matting operations on the image data in the substantially raw image format.

2. A method as described in claim 1, wherein the performing of the one or more matting operations is used to decompose the image data into a foreground image, a background image, and one or more alpha values.

3. A method as described in claim 1, wherein the image data is in the substantially raw image format such that gamma correction, sharpening, or de-noising are not performed on the image data.

4. A method as described in claim 1, wherein the image data is in the substantially raw image format such that the image data has been interpolated from a Bayer pattern to a red, green, blue image format.

5. A method as described in claim 1, wherein the image data is in the substantially raw image format such that de-mosaicking has been performed.

6. A method as described in claim 1, wherein the image data is in the substantially raw image format such that non-linear processing is not performed on the image data.

7. A method as described in claim 1, wherein the performing one or more matting operations on the image data includes generating a plurality of alpha values for each of a plurality of pixels from the image data.

8. A method as described in claim 1, further comprising converting the obtained image data to describe a plurality of pixels, each said pixel associated with a respective one of a plurality of color channels and wherein the performing of the one or more mating operations uses the converted image data.

9. A method as described in claim 8, wherein the converting is performed without interpolation.

10. A method as described in claim 8, wherein the converting is performed to convert at least one Bayer pattern described in the obtained image data into a single said pixel.

11. A method comprising:

obtaining image data that is generated by one or more image sensors; and

generating a plurality of alpha values for each of a plurality of pixels from the obtained image data.

12. A method as described in claim 11, wherein each of the plurality of alpha values for a respective said pixel correspond to a responsive one of a plurality of color channels.

13. A method as described in claim 11, wherein the image data is in a substantially raw image format.

14. A method as described in claim 11, wherein the image data is in a red, green, blue image format.

15. A method as described in claim 11, further comprising performing one or more matting operations on the image data using the generated plurality of alpha values.

16. A method as described in claim 11, further comprising determining a likely foreground and background color for at least one of the plurality of pixels based at least in part on an evaluation of how closely a line is fit by the plurality of alpha values for the at least one pixel.

17. A method as described in claim 11, further comprising:

determining a likely foreground and background color for first and one or more other said pixels; and

performing a sharing operation in which the likely foreground and background color for the first said pixel is compared to the likely foreground and background color for the one or more other said pixels to determine whether the likely foreground or background color for the first said pixel is to be replaced with the likely foreground or background color for the one or more other said pixels, the determination based at least in part on an evaluation of how closely a line is fit by a plurality of said alpha values for each of the first and the one or more other said pixels, respectively.

18. One or more computer-readable storage media comprising instructions that are stored thereon that, responsive to execution by a computing device, causes the computing device to perform operations comprising:

obtaining image data in a raw image format that is generated by one or more image sensors; and

performing one or more operations on the obtained image data in the substantially raw image format to decompose the image data into a foreground image, a background image, and one or more alpha values.

19. One or more computer-readable storage media as described in claim 18, wherein the one or more operations include a matting operation.

20. One or more computer-readable storage media as described in claim 18, wherein the performing of the one or more operations includes generating a plurality of alpha values for each of a plurality of pixels from the image data.