US2021297646A1PendingUtilityA1
Semiconductor device, display system, and electronic device
Est. expiryMar 24, 2037(~10.7 yrs left)· nominal 20-yr term from priority
G06N 3/045G06N 3/047G06N 3/0499G06N 3/09H10D 30/6755H10D 30/6734H10D 86/441H10D 86/481H10D 86/60H10D 87/00H10D 84/40H10H 29/142H10D 86/423G09G 2354/00G09F 9/33G06N 20/10G09G 3/32H04N 13/332H04N 13/261H10B 99/00H04N 13/128H04N 13/122H04N 13/271G06N 3/08G06N 20/00
65
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
To provide a novel semiconductor device or display system. To provide a semiconductor device or display system that can display stereoscopic images.A signal generation unit has a function of with the use of artificial intelligence, obtaining information on a scene of an image and information on a depth of the image and correcting image data on the basis of the information so that a stereoscopic effect is emphasized. An image signal obtained by the correction of the image data is supplied to a display unit, so that a stereoscopic image can be displayed on a display region
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A semiconductor device comprising:
a first obtaining unit configured to obtain scene information on an image corresponding to data; a second obtaining unit configured to obtain depth information on an image corresponding to the data; and a selection unit configured to select a depth map of an image on the basis of the scene information and the depth information, using a neural network.
2 . A semiconductor device comprising:
a first obtaining unit configured to obtain scene information on an image corresponding to data; a second obtaining unit configured to obtain depth information on an image corresponding to the data; and a selection unit configured to select a depth map of an object included in an image on the basis of the scene information and the depth information, using a neural network.
3 . The semiconductor device according to claim 1 ,
wherein the neural network is selected from a plurality of neural networks on the basis of the scene information, and wherein the depth information is input to the neural network.
4 . The semiconductor device according to claim 2 ,
wherein the neural network is selected from a plurality of neural networks on the basis of the scene information, and wherein the depth information is input to the neural network.
5 . A semiconductor device comprising:
a first obtaining unit configured to obtain first information corresponding to data; a second obtaining unit configured to obtain second information corresponding to the data; and a unit configured to output data by inputting the second information to an input layer of a neural network selected from a plurality of neural networks on the basis of the first information.
6 . A semiconductor device comprising:
a first obtaining unit configured to obtain first information corresponding to data; a second obtaining unit configured to obtain second information corresponding to the data; and a unit configured to output data by inputting the second information to an input layer of a neural network having a weight coefficient based on the first information.Join the waitlist — get patent alerts
Track US2021297646A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.