Back to results
US 2020/0051217 A1Published application
Artificial intelligence techniques for image enhancement
AssigneeBlinkAI Technologies, Inc.
InventorsLiying Shen, Bo Zhu, William Scott Lamond
Life of this patent
Estimating the term…
Abstract
An image captured by an imaging device in low light conditions may cause the captured image to have poor contrast, blurring, and otherwise not display one or more objects in the image clearly. According to various aspects, systems and methods are provided for enhancing images that are captured in low light conditions.
Claims23
A system for training a machine learning system to enhance images, the system comprising:
- a processor;
- and
- a non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by the processor, cause the processor to perform:
- obtaining a set of training images to be used for training the machine learning system, the obtaining comprising:
- obtaining an input image of a scene;
- and
- obtaining a target output image of the scene by averaging a plurality of images of the scene, wherein the target output image represents a target enhancement of the input image;
- and
- training the machine learning system using the set of training images.
6 more elements
A system for automatically enhancing an image, the system comprising:
- a processor;
- and
- a machine learning system implemented by the processor, the machine learning system configured to:
- receive an input image;
- and
- generate, based on the input image, an output image comprising at least a portion of the input image that is more illuminated than in the input image;
- wherein the machine learning system is trained based on a set of training images comprising:
- an input image of a scene;
- and
- a target output image of the scene, wherein the target image is obtained by averaging a plurality of images of the scene, wherein the target output image represents a target enhancement of the input image.
7 more elements
A computerized method for training a machine learning system to enhance images, the method comprising:
- obtaining a set of training images to be used for training the machine learning system, the obtaining comprising:
- obtaining an input image of a scene;
- and
- obtaining a target output image of the scene by averaging a plurality of images of the scene, wherein the target output image represents a target enhancement of the input image;
- and
- training the machine learning system using the set of training images.
3 more elements
Dependencies are inferred from the claim text.