摘要:
An electronic apparatus is provided. The electronic apparatus includes: a storage configured to store a plurality of filters each corresponding to a plurality of image patterns; and a processor configured to classify an image block including a target pixel and a plurality of surrounding pixels into one of the plurality of image patterns based on a relationship between pixels within the image block and to obtain a final image block in which the target pixel is image-processed by applying at least one filter corresponding to the classified image pattern from among the plurality of filters to the image block, wherein the plurality of filters are obtained by learning, through an artificial intelligence algorithm, a relationship between a plurality of first sample image blocks and a plurality of second sample image blocks corresponding to the plurality of first sample image blocks based on each of the plurality of image patterns.
摘要:
An electronic apparatus is provided. The electronic apparatus includes: a storage configured to store a plurality of filters each corresponding to a plurality of image patterns; and a processor configured to classify an image block including a target pixel and a plurality of surrounding pixels into one of the plurality of image patterns based on a relationship between pixels within the image block and to obtain a final image block in which the target pixel is image-processed by applying at least one filter corresponding to the classified image pattern from among the plurality of filters to the image block, wherein the plurality of filters are obtained by learning, through an artificial intelligence algorithm, a relationship between a plurality of first sample image blocks and a plurality of second sample image blocks corresponding to the plurality of first sample image blocks based on each of the plurality of image patterns.
摘要:
A method of generating metadata includes: obtaining a first image and a second image respectively having different color gamuts; obtaining at least one of information regarding a white point and information regarding the color gamut of the second image; correcting the first image based on the obtained information; and generating the metadata based on a correspondence relation between color information of the corrected first image and color information of the second image.
摘要:
An image processing method, including: receiving image content and metadata of the image content, the metadata content comprising flag information indicating whether to perform image processing on the image content and image processing information; determining whether to perform the image processing for each frame based on the flag information; performing, in response to determining to perform the image processing for an image frame, the image processing based on the image processing information on the image frame; and outputting the image processed image frame on which the image processing is performed.