Image upscaling technique
A method for interpolation includes receiving an input image having a plurality of pixels. The edge direction proximate a first pixel of the input image is estimated using a first technique from a plurality of discrete potential directions. An edge direction is selected based upon the estimating the edge direction proximate the first pixel of the input image using a second technique. The pixels proximate the first pixel are interpolated based upon the selected edge direction. The pixels proximate the first pixel are interpolated based upon another technique. An output image is determined pixels having more pixels than the plurality of pixels.
1. A method for interpolation comprising:
(a) receiving an input image having a plurality of pixels;
(b) estimating an edge direction proximate a first pixel of said input image from a first technique that uses a finite plurality of stored, predetermined potential directions which includes at least one predetermined direction that is not vertical and is not horizontal;
(c) selecting an edge direction based upon said estimating said edge direction proximate said first pixel of said input image using a second technique;
(d) interpolating respective first values of new pixels proximate said first pixel based upon said selected edge direction;
(e) interpolating respective second values of said new pixels based upon another technique that is not based upon an estimated or selected edge direction;
(f) determining interpolated values of said new pixels for an output image having more pixels than said input image based upon at least one of said respective first values and said respective second values;
(g) wherein said another technique includes a set of filters based upon a low-resolution data set and a high-resolution data set suitable for interpolating said input image, wherein said filters are collectively representative of at least a portion of an image space and a substantial number of said filters are representative of a respectively selected one of a volume and/or a shape within said image space.
2. The method of claim 1 wherein said estimating is based upon a gradient.
3. The method of claim 1 wherein said estimating is based upon a 5 by 5 window of pixels.
4. The method of claim 1 wherein said estimating is performed upon a majority of said plurality of pixels of said image.
5. The method of claim 1 wherein said estimating is based upon the luminance of said image.
6. The method of claim 1 further comprising determining a reliability measure that said edge direction is suitable and where said determining interpolated values of said new pixels for an output image having more pixels than said input image is based upon a linear combination of the respective interpolations produced from step (d) and step(e), each weighted using said reliability measure.
7. The method of claim 6 wherein said reliability measure is a weighted reliability measure.
8. The method of claim 1 wherein said selecting is based upon 3 directions.
9. The method of claim 1 wherein said selecting is based upon the next closest direction to the direction of said estimating.
10. The method of claim 1 wherein said step of determining interpolated values of said new pixels for an output image includes no iterations.
11. The method of claim 1 wherein said plurality of pre-determined directions is comprised of: −45 degrees, −26.6 degrees, −18.4 degrees, 18.4 degrees, 26.6 degrees, 45 degrees, 63.4 degrees, 71.6 degrees, 108.4 degrees and 116.6 degrees, all modulo 180 degrees.
12. The method of claim 1 wherein said estimating is based on a plurality of pixels proximate said first pixel.
13. The method of claim 1 wherein said selecting is based upon the pixels in a 5 by 5 window centered around said first pixel.
14. The method of claim 1 wherein the step of determining interpolated values of said new pixels for an output image is based upon the pixels in a 5 by 5 window centered around said first pixel.
15. The method of claim 1 wherein said estimating, said selecting, and said determining are each based upon the pixels in a 5 by 5 window centered around said first pixel.
16. The method of claim 1 wherein the interpolated respective first values of new pixels proximate said first pixel based upon said selected edge direction are weighted using a reliability measure.
17. The method of claim 1 wherein the interpolated respective second values of said new pixels proximate said first pixel based upon said another technique are weighted using a reliability measure.
18. The method of claim 1 , wherein said step of interpolating respective first values of new pixels proximate said first pixel based upon said selected edge direction is based on pixels in the input image that are near the pixel to be interpolated and near a line through that pixel with an orientation equal to said selected edge direction.
19. The method of claim 18 wherein said interpolating respective first values of new pixels based upon said selected edge direction is based on either 2 pixels in the input image or 4 pixels in the input image.
20. The method of claim 1 wherein said plurality of potential directions is a plurality of discrete directions.
21. The method of claim 1 wherein said filters are generated based upon a classification process.
22. The method of claim 21 wherein said classification process includes regression.
23. The method of claim 1 wherein said filters are based upon minimization of an error of an entire set of said filters for a data set.
24. The method of claim 21 wherein said classification process includes multi-way splits of a predictor variable.
25. The method of claim 1 wherein said filters are based upon using a dimension-wise statistical technique.
26. The method of claim 21 wherein said classification requires no more than N comparisons, where N is the number of pixels in a window used for said generating said high resolution image.