Back to results
US 10,764,563 B2Granted
3D enhanced image correction
AssigneeIntel Corporation
InventorsDavid L. Graumann, Rahuldeva Ghosh, Scott Pfursich
Life of this patent
Estimating the term…
Abstract
A user authentication system and method. A two-dimensional image of a scene is obtained and range information obtained from the scene is aligned with the two-dimensional image. One or more depth regions is identified and image segments corresponding to the one or more depth regions are selected within the two-dimensional image. Brightness operations are performed on one or more of the selected image segments to form a corrected image.
Claims23
A system for enhanced image correction, comprising:
- a 2D camera;
- a 3D camera;
- and
- a processor to:
- receive a two-dimensional image from the 2D camera, wherein the two-dimensional image is not homogeneously illuminated and wherein the two-dimensional image has a first coordinate system;
- receive range information from the 3D camera, wherein the range information has a second coordinate system;
- identify one or more depth regions from range information based on:
- determine contours within the range information that are ascending or descending;
- and
- select regions from the range information that have either an ascending contour or a descending contour and a slope variation over a predefined kernel region of the range information that is within a threshold level;
- align the range information with the two-dimensional image by aligning the first coordinate system and the second coordinate system to a world coordinate system;
- select, within the two-dimensional image, image segments corresponding to world coordinates of the one or more depth regions;
- perform brightness operations on one or more of the image segments to form a corrected image with region-specific pixel brightness for each of the one or more image segments;
- and
- authenticate a user based on a user feature in the corrected image.
12 more elements
A method of enhanced image correction, comprising:
- obtaining a two-dimensional image of a scene, wherein the two-dimensional image is not homogeneously illuminated and wherein the two-dimensional image has a first coordinate system;
- obtaining range information of the scene, wherein the range information has a second coordinate system;
- identifying one or more depth regions from the range information based on:
- determining contours within the range information that are ascending or descending;
- and
- selecting regions from the range information that have either an ascending contour or a descending contour and a slope variation over a predefined kernel region of the range information that is within a threshold level;
- aligning the range information with the two-dimensional image by aligning the first coordinate system and the second coordinate system to a world coordinate system;
- selecting, within the two-dimensional image, image segments corresponding to world coordinates of the one or more depth regions;
- and
- performing brightness operations on one or more of the selected image segments to form a corrected image with region-specific pixel brightness for each of the one or more image segments.
7 more elements
At least one non-transitory machine-readable medium including instructions that, when performed by a machine, cause the machine to:
- obtain a two-dimensional image of a scene, wherein the two-dimensional image is not homogeneously illuminated and wherein the two-dimensional image has a first coordinate system;
- obtain range information of the scene, wherein the range information has a second coordinate system;
- identify one or more depth regions from the range information based on:
- determine contours within the range information that are ascending or descending;
- and
- select regions from the range information that have either an ascending contour or a descending contour and a slope variation over a predefined kernel region of the range information that is within a threshold level;
- align the range information with the two-dimensional image by aligning the first coordinate system and the second coordinate system to a world coordinate system;
- select, within the two-dimensional image, image segments corresponding to world coordinates of the one or more depth regions;
- and
- perform brightness operations on one or more of the selected image segments to form a corrected image with region-specific pixel brightness for each of the one or more image segments.
7 more elements
Dependencies are inferred from the claim text.