Using boundary maps to refine imagery
Various approaches to image enhancement are disclosed. In one approach, a boundary map and an image are received. The boundary map is used to determine that brightness values for a set of pixels included in the image should be regularized. An output image is generated by storing, at both a first and second pixel position in the output image, a set of regularized values. In another approach, an image to be enhanced and an edge map are received. Edge-masked derivative matrices are constructed and used to iteratively solve a series of linear equations, wherein solutions to the linear equations minimize an increasingly accurate quadratic approximation of a penalty function that measures a total amount of variation in a function, and a derivation of the function from the image. A vector result of the iterative solution is transformed into a raster image.
1. A method, comprising:
receiving an image to be enhanced and an edge map;
constructing edge-masked derivative matrices;
using the edge-masked derivative matrices to iteratively solve a series of linear equations, wherein solutions to the linear equations minimize an increasingly accurate quadratic approximation of a penalty function that measures a total amount of variation in a function, and a deviation of the function from the image; and
transforming a vector result of the iterative solution into a raster image.
2. The method of claim 1 wherein the image to be enhanced has a first amount of noise and wherein the raster image has an amount of noise that is less than the first amount of noise.
3. The method of claim 1 wherein the image to be enhanced comprises multi-spectral data.
4. The method of claim 1 wherein the edge map comprises a plurality of fields and wherein each field included in the plurality of fields has a unique identifier.
5. A system, comprising:
a processor configured to:
receive an image to be enhanced and an edge map;
construct edge-masked derivative matrices;
use the edge-masked derivative matrices to iteratively solve a series of linear equations, wherein solutions to the linear equations minimize an increasingly accurate quadratic approximation of a penalty function that measures a total amount of variation in a function, and a deviation of the function from the image; and
transform a vector result of the iterative solution into a raster image; and
a memory coupled to the processor and configured to provide the processor with instructions.
6. The system of claim 5 wherein the image to be enhanced has a first amount of noise and wherein the raster image has an amount of noise that is less than the first amount of noise.
7. The system of claim 5 wherein the image to be enhanced comprises multi-spectral data.
8. The system of claim 5 wherein the edge map comprises a plurality of fields and wherein each field included in the plurality of fields has a unique identifier.
9. The system of claim 5 wherein solving the series of linear equations includes solving [D x T Q(u n )D x +D y T Q(u n )D y +λI]u n+1 =λƒ, where the function Q is defined by Q(u) ii =[(D x u) i 2 +(D x u) i 2 ] p-2 .
10. The system of claim 5 wherein the image to be enhanced includes a plurality of blank pixels and wherein the raster image in-paints at least some of the blank pixels.
11. The system of claim 5 wherein the image to be enhanced has a first resolution and wherein the raster image has a second resolution that is higher than the first resolution.
12. The system of claim 11 wherein the processor is configured to upsample the first image to match a resolution of the edge map.
13. The method of claim 1 wherein solving the series of linear equations includes solving [D x T Q(u n )D x +D y T Q(u n )D y +λI]u n+1 =λƒ, where the function Q is defined by Q(u) ii =[(D x u) i 2 +(D x u) i 2 ] p-2 .
14. The method of claim 1 wherein the image to be enhanced includes a plurality of blank pixels and wherein the raster image in-paints at least some of the blank pixels.
15. The method of claim 1 wherein the image to be enhanced has a first resolution and wherein the raster image has a second resolution that is higher than the first resolution.
16. The method of claim 15 wherein the processor is configured to upsample the first image to match a resolution of the edge map.
17. A computer program embodied in a tangible computer readable storage medium and comprising computer instructions for:
receiving an image to be enhanced and an edge map;
constructing edge-masked derivative matrices;
using the edge-masked derivative matrices to iteratively solve a series of linear equations, wherein solutions to the linear equations minimize an increasingly accurate quadratic approximation of a penalty function that measures a total amount of variation in a function, and a deviation of the function from the image; and
transforming a vector result of the iterative solution into a raster image.
18. The computer program product of claim 17 wherein solving the series of linear equations includes solving [D x T Q(u n )D x +D y T Q(u n )D y +λI]u n+1 =λƒ, where the function Q is defined by Q(u) ii =+(D x u) i 2 +[(D x u) i 2 ] p-2 .
19. The computer program product of claim 17 wherein the image to be enhanced includes a plurality of blank pixels and wherein the raster image in-paints at least some of the blank pixels.
20. The computer program product of claim 17 wherein the image to be enhanced has a first resolution and wherein the raster image has a second resolution that is higher than the first resolution.
21. The computer program product of claim 20 wherein the processor is configured to upsample the first image to match a resolution of the edge map.
22. The computer program product of claim 17 wherein the image to be enhanced has a first amount of noise and wherein the raster image has an amount of noise that is less than the first amount of noise.
23. The computer program product of claim 17 wherein the image to be enhanced comprises multi-spectral data.
24. The computer program product of claim 17 wherein the edge map comprises a plurality of fields and wherein each field included in the plurality of fields has a unique identifier.