Face region detection and local reshaping enhancement
US-2024428612-A1 · Dec 26, 2024 · US
US9986183B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9986183-B2 |
| Application number | US-201715405613-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jan 13, 2017 |
| Priority date | Jun 11, 2014 |
| Publication date | May 29, 2018 |
| Grant date | May 29, 2018 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A lens distortion correction device and an application processor having the same include a distortion correction unit configured to correct a distorted image into an undistorted image and an image enhancement unit configured to improve the undistorted image using a high-frequency component of the distorted image.
Opening claim text (preview).
What is claimed is: 1. An image sensor module, comprising: an image sensor configured to receive an image through a lens; and a lens distortion correction device configured to receive a distorted image from the image sensor, wherein the lens distortion correction device comprises: a distortion correction unit configured to correct the distorted image into an undistorted image; and an image enhancement unit configured to enhance the undistorted image using a high-frequency component of the distorted image, wherein the distortion correction unit corrects the distorted image applying a bilinear interpolation method controlled according to a degree of distortion determined based on a distance from a center of a image, wherein a plurality of patches in the distorted image and a plurality of patches in the undistorted image each include a low-frequency component and a high-frequency component, and wherein the image enhancement unit is configured to enhance the undistorted image by combining a low-frequency component of a patch in the undistorted image with a high-frequency component of a searched patch from a localized region in the distorted image. 2. The image sensor module according to claim 1 , wherein the distortion correction unit determines a degree of distortion according to a distortion ratio of a distance from a center of the distorted image to a distance from a center of the undistorted image. 3. The image sensor module according to claim 2 , wherein the distortion correction unit corrects the distorted image into the undistorted image using a Gaussian interpolation kernel, controls a size of the Gaussian interpolation kernel according to the degree of distortion, increases the size of the Gaussian interpolation kernel when the distortion ratio is greater than 1, and reduces the size of the Gaussian interpolation kernel when the distortion ratio is smaller than 1. 4. The image sensor module according to claim 1 , wherein the image enhancement unit is configured to search for a patch having a closest integration value to an integration value of a patch in the undistorted image in a localized region in the distorted image, and enhance the undistorted image using a high-frequency component of the searched patch of the distorted image. 5. The image sensor module according to claim 4 , wherein the image enhancement unit combines the low-frequency component of a patch in the undistorted image with the high-frequency component of the searched patch of the distorted image and removes a blurring artifact from the undistorted image. 6. An application processor, comprising: a distortion correction unit configured to correct a distortion in a distorted image using a Gaussian interpolation kernel controlled according to a degree of distortion determined based on a distance from a center of a image and generate an undistorted image; and an image enhancement unit configured to improve the undistorted image by combining a low-frequency component of a patch in the undistorted image with a high-frequency component of a searched patch from a localized region in the distorted image. 7. The application processor according to claim 6 , wherein the distortion correction unit determines a degree of distortion according to a distortion ratio of a distance from a center of the distorted image to a distance from a center of the undistorted image. 8. The application processor according to claim 7 , wherein the distortion correction unit corrects the distorted image into the undistorted image using a Gaussian interpolation kernel, controls a size of the Gaussian interpolation kernel according to the degree of distortion, increases the size of the Gaussian interpolation kernel when the distortion ratio is greater than 1, and reduces the size of the Gaussian interpolation kernel when the distortion ratio is smaller than 1. 9. The application processor according to claim 6 , wherein a plurality of patches in the distorted image and a plurality of patches in the undistorted image each include a low-frequency component and a high-frequency component and wherein the image enhancement unit is configured to search for a patch having a closest integration value to an integration value of a patch in the undistorted image in a localized region in the distorted image, and improve the undistorted image using a high-frequency component of the searched patch of the distorted image. 10. The application processor according to claim 9 , wherein the image enhancement unit configured to decompose a patch in the distorted image and divide into a low-frequency component and a high-frequency component.
using local operators · CPC title
the noise originating only from the lens unit, e.g. flare, shading, vignetting or "cos4" · CPC title
Physics · mapped topic
Physics · mapped topic
Electricity · mapped topic
Related publications grouped by family.
Answers are generated from the same data shown on this page.