US 12,118,916 B2
Image display apparatus with AI-based image processing
Jeonghyu Yang, Seoul (KR); Seoksoo Lee, Seoul (KR); and Jingyeong Kim, Seoul (KR)
Assigned to LG ELECTRONICS INC., Seoul (KR)
Appl. No. 17/599,385
Filed by LG ELECTRONICS INC., Seoul (KR)
PCT Filed Mar. 27, 2020, PCT No. PCT/KR2020/004162
§ 371(c)(1), (2) Date Sep. 28, 2021,
PCT Pub. No. WO2020/204472, PCT Pub. Date Oct. 8, 2020.
Claims priority of application No. 10-2019-0037434 (KR), filed on Mar. 29, 2019.
Prior Publication US 2022/0198994 A1, Jun. 23, 2022
Int. Cl. G09G 3/30 (2006.01); G06F 3/00 (2006.01); G06F 3/147 (2006.01); G06F 3/16 (2006.01); G09G 3/20 (2006.01); G09G 3/36 (2006.01)
CPC G09G 3/2096 (2013.01) [G06F 3/005 (2013.01); G06F 3/147 (2013.01); G06F 3/162 (2013.01); G06F 3/167 (2013.01); G09G 2320/08 (2013.01); G09G 2370/12 (2013.01)] 19 Claims
OG exemplary drawing
 
1. An image display apparatus comprising:
a signal processor configured to perform image processing of an input image, and audio processing of audio corresponding to the input image;
a virtual sensor device configured to receive image and audio information processed by the signal processor;
a sensor device configured to collect externally captured image information or sound information; and
an artificial intelligence (AI) processor configured to:
perform the image processing of the input image or the audio processing based on AI using the image and audio information from the virtual sensor device, and the image or sound information from the sensor device, and
when recognition of an ambient illumination value, ambient noise, and speech is performed based on an activation of an illumination sensor and a microphone after the image display apparatus is turned on, perform a preferred picture quality setting corresponding to the ambient illuminance value and perform a preferred volume setting corresponding to the ambient noise and viewer identification based on the speech,
wherein the signal processor or the AI processor is configured to:
in response to a resolution of the input image being changed, calculate an original resolution and a compression level of the input image based on learning using a neural network, and perform image quality processing corresponding to the calculated original resolution of the input image,
as the calculated original resolution increases, increase an enhancement intensity for the input image,
as the calculated compression level increases, increase a blurring intensity for the input image, and
in response to the original resolution of the input image being changed while reproducing the input image, sequentially change an image quality setting of the input image from a first setting to a second setting.