Display device and operating method of the same
A display device for performing image processing by using a neural network including a plurality of layers, may obtain a plurality of pieces of model information respectively corresponding to pixels included in a first image based on object features respectively corresponding to the pixels; identify the plurality of pieces of model information respectively corresponding to the plurality of layers and the pixels input to the neural network based on information about a time point at which each of the pixels is processed in the neural network; update parameters of the plurality of layers, based on the plurality of pieces of model information; and obtain a second image by processing the first image via the plurality of layers to which the updated parameters are applied; and display the second image.
1. A display device for performing image processing by using a neural network including a plurality of layers, the display device comprising:
a display;
a memory storing one or more instructions; and
a processor configured to execute the one or more instructions stored in the memory to:
obtain a plurality of pieces of model information respectively corresponding to pixels included in a first image based on object features respectively corresponding to the pixels;
identify the plurality of pieces of model information respectively corresponding to the plurality of layers based on the plurality of pieces of model information respectively corresponding to the pixels input to the neural network and information about a time point at which each of the pixels is processed in the neural network;
update parameters of the plurality of layers, based on the plurality of pieces of model information;
obtain a second image by processing the first image via the plurality of layers to which the updated parameters are applied; and
control the display to display the second image.
2. The display device of claim 1 , wherein the information about the time point comprises at least one of information about a data input time at which each of the pixels is input to each of the plurality of layers or information about a data processing time at which each of the pixels is processed in each of the plurality of layers.
3. The display device of claim 2 , wherein at least one of the data input time or the data processing time has a predetermined period.
4. The display device of claim 1 , wherein the information about the time point is determined based on location of each of the pixels in the first image.
5. The display device of claim 1 , wherein the plurality of layers are connected in series, and
the processor is further configured to sequentially input each pixel value of the pixels included in the first image to the plurality of layers.
6. The display device of claim 1 , wherein the plurality of layers comprises a first layer and a second layer that follows the first layer, and the pixels of the first image comprise a first pixel and a second pixel, and
wherein the processor is further configured to execute the one or more instructions to:
update a parameter of the first layer to a parameter included in first model information corresponding to the first pixel based on a first pixel value of the first pixel that is input to the first layer; and
update the parameter of the first layer to a parameter included in second model information corresponding to the second pixel and update a parameter of the second layer to a parameter included in the first model information, based on the first pixel value of the first pixel input to the second layer and a second pixel value of the second pixel input to the first layer.
7. The display device of claim 6 , wherein the plurality of layers comprises a third layer that follows the second layer, and the pixels of the first image further comprise a third pixel, and
wherein the processor is further configured to execute the one or more instructions to update the parameter of the first layer to a parameter included in third model information corresponding to the third pixel, update the parameter of the second layer to a parameter included in the second model information, and update a parameter of the third layer to a parameter included in the first model information, based on the first pixel value of the first pixel input to the third layer, the second pixel value of the second pixel input to the second layer, and a third pixel value of the third pixel input to the first layer.
8. The display device of claim 1 , wherein the processor is further configured to execute the one or more instructions to:
detect object regions included in the first image; and
obtain the plurality of pieces of model information respectively corresponding to the pixels included in the first image based on a plurality of pieces of model information corresponding to the object regions.
9. The display device of claim 8 , wherein the processor is further configured to execute the one or more instructions to obtain the plurality of pieces of model information respectively corresponding to the pixels based on a weighted sum of the plurality of pieces of model information corresponding to the object regions.
10. The display device of claim 9 , wherein the processor is further configured to execute the one or more instructions to:
determine weights of the plurality of pieces of model information respectively corresponding to the object regions based on a distance between a first pixel included in the first image and a center of each of the object regions; and
obtain model information corresponding to the first pixel based on the plurality of pieces of model information respectively corresponding to the object regions and the determined weights.
11. An operating method of a display device for performing image processing by using a neural network including a plurality of layers, the operating method comprising:
receiving a first image;
obtaining a plurality of pieces of model information respectively corresponding to pixels included in the first image based on object features respectively corresponding to the pixels;
identifying the plurality of pieces of model information respectively corresponding to the plurality of layers based on the plurality of pieces of model information respectively corresponding to the pixels input to the neural network and information about a time point at which each of the pixels is processed in the neural network;
updating parameters of the plurality of layers based on the plurality of pieces of model information;
generating a second image by processing the first image via the plurality of layers to which the updated parameters are updated; and
displaying the second image.
12. The operating method of claim 11 , wherein the information about the time point comprises at least one of information about a data input time at which each of the pixels is input to each of the plurality of layers or information about a data processing time at which each of the pixels is processed in each of the plurality of layers.
13. The operating method of claim 12 , wherein at least one of the data input time or the data processing time has a uniform period.
14. The operating method of claim 11 , wherein the information about the time point is determined based on location of each of the pixels in the first image.
15. The operating method of claim 11 , wherein the plurality of layers are connected in series, and
pixel values of the pixels included in the first image are sequentially input to the plurality of layers and sequentially output.
16. The operating method of claim 11 , wherein the plurality of layers comprises a first layer and a second layer that follows the first layer, and the pixels of the first image comprise a first pixel and a second pixel, and
wherein the updating of the parameters of the plurality of layers comprises:
updating a parameter of the first layer to a parameter included in first model information corresponding to the first pixel based on a first pixel value of the first pixel that is input to the first layer; and
updating the parameter of the first layer to a parameter included in second model information corresponding to the second pixel and updating a parameter of the second layer to a parameter included in the first model information, based on the first pixel value of the first pixel input to the second layer and a second pixel value of the second pixel input to the first layer.
17. The operating method of claim 16 , wherein the plurality of layers comprises a third layer that follows the second layer, and the pixels of the first image further comprise a third pixel, and
the updating of the parameters of the plurality of layers comprises updating the parameter of the first layer to a parameter included in third model information corresponding to the third pixel, updating the parameter of the second layer to a parameter included in the second model information, and updating a parameter of the third layer to a parameter included in the first model information, based on the first pixel value of the first pixel input to the third layer, the second pixel value of the second pixel input to the second layer, and a third pixel value of the third pixel input to the first layer.
18. The operating method of claim 11 , further comprising detecting object regions included in the first image,
wherein the obtaining of the plurality of pieces of model information respectively corresponding to the pixels comprises obtaining the plurality of pieces of model information respectively corresponding to the pixels included in the first image based on a plurality of pieces of model information corresponding to the object regions.
19. The operating method of claim 18 , wherein the obtaining of the plurality of pieces of model information respectively corresponding to the pixels comprises obtaining the plurality of pieces of model information respectively corresponding to the pixels based on a weighted sum of the plurality of pieces of model information corresponding to the object regions.
20. A non-transitory computer-readable recording medium having stored therein a program including instructions causing to execute a method of performing image processing via a neural network comprising a plurality of layers, the method comprising:
obtaining a first image;
obtaining a plurality of pieces of model information respectively corresponding to pixels included in the first image based on object features respectively corresponding to the pixels;
identifying the plurality of pieces of model information respectively corresponding to the plurality of layers based on the plurality of pieces of model information respectively corresponding to the pixels input to the neural network and information about a time point at which each of the pixels is processed in the neural network;
updating parameters of the plurality of layers based on the plurality of pieces of model information; and
generating a second image by processing the first image via the plurality of layers to which the updated parameters are updated.