System and method for optimizing image quality in a digital camera
First Claim
Patent Images
1. A computer-implemented method for rendering an optimized image, comprising:
- capturing a raw image via an optical sensor included in a digital camera;
processing the raw image to generate raw image statistics related to the raw image, wherein the raw image statistics comprise a plurality of values, each value corresponding to a different statistic that can be computed for an image;
causing a first machine learning engine to generate derived image statistics for the raw image based on the raw image statistics, wherein the derived image statistics comprise qualities of the raw image;
causing a second machine learning engine to generate a set of rendering control parameters based on the raw image statistics and the derived image statistics, wherein the rendering control parameters select a rendering algorithm and a set of rendering algorithm arguments that correspond to the selected rendering algorithm; and
rendering the optimized image by processing the raw image with the rendering algorithm and the set of rendering algorithm arguments.
1 Assignment
0 Petitions
Accused Products
Abstract
A digital camera includes an image optimization engine configured to generate an optimized image based on a raw image captured by the digital camera. The image optimization engine implements one or more machine learning engines in order to select rendering algorithms and rendering algorithm arguments that may then be used to render the raw image.
37 Citations
25 Claims
-
1. A computer-implemented method for rendering an optimized image, comprising:
-
capturing a raw image via an optical sensor included in a digital camera; processing the raw image to generate raw image statistics related to the raw image, wherein the raw image statistics comprise a plurality of values, each value corresponding to a different statistic that can be computed for an image; causing a first machine learning engine to generate derived image statistics for the raw image based on the raw image statistics, wherein the derived image statistics comprise qualities of the raw image; causing a second machine learning engine to generate a set of rendering control parameters based on the raw image statistics and the derived image statistics, wherein the rendering control parameters select a rendering algorithm and a set of rendering algorithm arguments that correspond to the selected rendering algorithm; and rendering the optimized image by processing the raw image with the rendering algorithm and the set of rendering algorithm arguments. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. A non-transitory computer-readable medium storing program instructions that, when executed by a processing unit, cause the processing unit to render an optimized image by performing the steps of:
-
capturing a raw image via an optical sensor included in a digital camera; processing the raw image to generate raw image statistics related to the raw image, wherein the raw image statistics comprise a plurality of values, each value corresponding to a different statistic that can be computed for an image; causing a first machine learning engine to generate derived image statistics for the raw image based on the raw image statistics, wherein the derived image statistics comprise qualities of the raw image; causing a second machine learning engine to generate a set of render control parameters based on the raw image statistics and the derived image statistics, wherein the rendering control parameters select a rendering algorithm and a set of rendering algorithm arguments that correspond to the selected rendering algorithm; and rendering the optimized image by processing the raw image with the rendering algorithm and the set of rendering algorithm arguments. - View Dependent Claims (16, 17, 18, 19, 20)
-
-
21. A computing device configured to render an optimized image, including:
a processing unit configured to; capture a raw image via an optical sensor included in a digital camera, process the raw image to generate raw image statistics related to the raw image, wherein the raw image statistics comprise a plurality of values, each value corresponding to a different statistic that can be computed for an image, cause a first machine learning engine to generate derived image statistics for the raw image based on the raw image statistics, wherein the derived image statistics comprise qualities of the raw image, cause a second machine learning engine to generate a set of rendering control parameters based on the raw image statistics and the derived image statistics, wherein the rendering control parameters select a rendering algorithm and a set of rendering algorithm arguments that correspond to the selected rendering algorithm, and render the optimized image by processing the raw image with the rendering algorithm and the set of rendering algorithm arguments. - View Dependent Claims (22, 23, 24, 25)
Specification