Image processing device and operation method therefor

1. An image processing device comprising:

a memory storing one or more instructions; and

a processor configured to execute the one or more instructions stored in the memory,

wherein the processor is further configured to obtain a first image and a classifier that indicates a purpose of image processing, and to process, by using a deep neural network (DNN), the first image according to the purpose indicated by the classifier,

wherein the DNN processes input images according to different purposes, and

wherein pixels included in the classifier have at least one of a first value and a second value that is greater than the first value, the first value indicates a first purpose, and the second value indicates a second purpose.

2. The image processing device of claim 1 , wherein the DNN comprises N convolution layers, and

the processor is further configured to generate an input image based on the first image, extract feature information by performing a convolution operation in which one or more kernels are applied to the input image and the classifier in the N convolution layers, and generate a second image based on the extracted feature information.

3. The image processing device of claim 2 , wherein the processor is further configured to convert R, G, and B channels included in the first image into Y, U, and V channels of a YUV mode and determine, as the input image, an image of the Y channel among the Y, U, and V channels.

4. The image processing device of claim 3 , wherein the processor is further configured to generate the second image based on an image output by processing the image of the Y channel in the DNN and on images of the U and V channels among the Y, U, and V channels.

5. The image processing device of claim 1 , wherein the processor is further configured to process the first image according to the first purpose when all the pixels included in the classifier have the first value and to process the first image according to the second purpose when all the pixels included in the classifier have the second value.

6. The image processing device of claim 1 , wherein, when pixels in a first region included in the classifier have the first value, and pixels in a second region included in the classifier have the second value, a third region corresponding to the first region in the first image is processed according to the first purpose, and a fourth region corresponding to the second region in the first image is processed according to the second purpose.

7. The image processing device of claim 1 , wherein the processor is further configured to process the first image according to a level of image processing according to the first purpose and a level of image processing according to the second purpose, which are determined based on values of the pixels included in the classifier, the first value, and the second value.

8. The image processing device of claim 1 , wherein the processor is further configured to generate the classifier based on a characteristic of the first image.

9. The image processing device of claim 8 , wherein the processor is further configured to generate a map image indicating text and an edge included in the first image and determine a value of pixels included in the classifier based on the map image.

10. The image processing device of claim 1 , wherein the DNN is trained by a first training data set including first image data, a first classifier having the first value as a pixel value, and first label data obtained by processing the first image data according to the first purpose, and by a second training data set including second image data, a second classifier having the second value as a pixel value, and second label data obtained by processing the second image data according to the second purpose.

11. The image processing device of claim 10 , wherein the processor is further configured to adjust weights of one or more kernels included in the DNN to decrease a difference between the first label data and image data output when the first image data and the first classifier are input to the DNN, and adjust the weights of the one or more kernels included in the DNN to decrease a difference between the second label data and image data output when the second image data and the second classifier are input to the DNN.

12. An operating method of an image processing device, the method comprising:

obtaining a first image and a classifier that indicates a purpose of image processing; and

processing the first image according to the purpose indicated by the classifier, by using a deep neural network (DNN),

wherein the DNN processes a plurality of images according to different purposes, and

wherein pixels included in the classifier have at least one of a first value and a second value that is greater than the first value, the first value indicates a first purpose, and the second value indicates a second purpose.

13. The method of claim 12 , wherein the obtaining of the first image and the classifier comprises generating an input image based on the first image,

the DNN comprises N convolution layers, and

the processing of the first image according to the purpose indicated by the classifier, by using the DNN, comprises:

extracting feature information by performing a convolution operation in which one or more kernels are applied to the input image and the classifier in the N convolution layers; and

generating a second image based on the extracted feature information.

14. The method of claim 13 , wherein the generating of the input image based on the first image comprises:

converting R, G, and B channels included in the first image into Y, U, and V channels of a YUV mode; and

determining, as the input image, an image of the Y channel among the Y, U, and V channels.