Image adjusting method and image adjusting device
AssigneeRealtek Semiconductor Corp.
InventorTeng-Hsiang Yu
Life of this patent
Estimating the term…
Abstract
An image adjusting method includes: detecting objects in an input image and classifying the objects through a deep learning model, thereby obtaining at least one category included in the input image, a weight value corresponding to each of the categories, and at least one block of the input image corresponding to each of the categories; obtaining a color information and a coordinate information of each of the blocks; and adjusting at least one of the sharpness, dynamic contrast control (DCC), and independent color management (ICM) of each of the block of the input image according to the weight value, the coordinate information, and the color information corresponding to each of the blocks, thereby generating an output image.
Claims20
An image adjusting method, comprising:
- detecting objects in an input image and classifying the objects through a deep learning model, thereby obtaining a plurality of categories included in the input image, a weight value corresponding to each of the categories, and a plurality of blocks of the input image corresponding to each of the categories;
- obtaining a color information and a coordinate information of each of the blocks;
- and
- adjusting at least one of the sharpness, dynamic contrast control (DCC), and independent color management (ICM) of each of the blocks of the input image according to the weight value, the coordinate information, and the color information corresponding to each of the blocks, thereby generating an output image.
An image adjusting device, comprising:
- an image capturing device configured to capture an input image;
- and
- an image processing module electrically connected to the image capturing device, wherein the image processing module is configured to perform the following steps:
- detecting objects in the input image and classifying the objects through a deep learning model, thereby obtaining a plurality of categories included in the input image, a weight value corresponding to each of the categories, and a plurality of blocks of the input image corresponding to each of the categories;
- obtaining a color information and a coordinate information of each of the blocks;
- and
- adjusting at least one of the sharpness, dynamic contrast control (DCC), and independent color management (ICM) of each of the blocks of the input image according to the weight value, the coordinate information, and the color information corresponding to each of the blocks, thereby generating an output image.
Dependencies are inferred from the claim text.