Image processing device and image processing method of same

1. An image processing apparatus comprising:

an input unit; and

a processor configured to retarget an image frame input through the input unit and acquire an output image frame,

wherein the processor is configured to:

identify an area, in which pixel values are to be padded, based on the input image frame and information on the output image frame,

identify a first pixel block based on a target pixel area included in the identified area,

identify a second pixel block based on pixel values included in the first pixel block and acquire the output image frame by padding the target pixel area based on pixel values included in the second pixel block,

wherein the processor is further configured to:

identify the second pixel block by searching pixel values included in the first pixel block and a pixel block having similarity greater than or equal to a threshold value,

identify a foreground area in the input image frame, and perform re-research based on the second pixel block being searched in at least one of the foreground area or an adjacent area, and

wherein the processor is further configured to:

sum pixel values of some pixels among pixels included in the first pixel block and pixel values of corresponding pixel among the second pixel block and divide a value of the sum by a number of sums to obtain a calculated pixel value, and

replace the some pixels with the calculated pixel value.

2. The apparatus of claim 1 , wherein the processor is configured to scale the input image frame based on an aspect ratio of the input image frame, identify the area to be padded based on the scaled image frame and information about the output image frame, and identify the second pixel block in the scaled image frame.

3. The apparatus of claim 1 , wherein the processor is configured to pad pixels included in the target pixel area with pixel values of corresponding pixel among the pixels included in the second pixel block.

4. The apparatus of claim 1 , wherein the processor is configured to acquire motion information of the input image frame, and blur the area in which the pixel values are padded based on the motion information.

5. The apparatus of claim 4 , wherein the processor is configured to, based on the foreground area of the input image frame being included in the area in which the pixel values are padded, blur the area in which the pixel values are padded based on the motion information being equal to or greater than a threshold value, and maintain the area in which the pixel values are padded based on the motion information being less than the threshold value.

6. The apparatus of claim 1 , wherein the processor is configured to pad the target pixel area of each of a plurality of fames included in a predetermined frame section with pixel values included in the second pixel block.

7. The apparatus of claim 1 , further comprising:

a display,

wherein the processor is configured to control the display to display the acquired output image frame.

8. An image processing method of retargeting an input image frame to acquire an output image frame, the method comprising:

identifying an area, in which pixel values are to be padded, based on the input image frame and information on the output image frame, identify a first pixel block based on a target pixel area included in the identified area;

identifying a second pixel block based on pixel values included in the first pixel block; and

acquiring the output image frame by padding the target pixel area based on pixel values included in the second pixel block,

wherein the identifying the second pixel comprises:

identifying the second pixel block by searching pixel values included in the first pixel block and a pixel block having similarity greater than or equal to a threshold value, and

identifying a foreground area in the input image frame, and perform re-research based on the second pixel block being searched in at least one of the foreground area or an adjacent area, and

wherein the acquiring the output image comprises:

summing pixel values of some pixels among pixels included in the first pixel block and pixel values of corresponding pixel among the second pixel block and dividing a value of the sum by a number of sums to obtain a calculated pixel value, and

replacing the some pixels with the calculated pixel value.

9. The method of claim 8 , wherein the identifying the second pixel block is configured to scale the input image frame based on an aspect ratio of the input image frame, identify the area to be padded based on the scaled image frame and information about the output image frame, and identify the second pixel block in the scaled image frame.

10. The method of claim 8 , wherein the identifying the second pixel block is configured to identify the second pixel block by searching pixel values included in the first pixel block and a pixel block having similarity greater than or equal to the threshold value.

11. A non-transitory computer-readable medium, when executed by a processor of an image processing apparatus that retargets an image frame to acquire an output image frame, storing computer instructions such that the image processing apparatus performs an operation, the operation comprising:

identifying an area, in which pixel values are to be padded, based on the input image frame and information about the output image frame, identify a first pixel block based on a target pixel area included in the identified area;

identifying a second pixel block based on pixel values included in the first pixel block; and

padding the target pixel area based on pixel values included in the second pixel block to acquire the output image frame,

wherein the identifying the second pixel comprises:

identifying the second pixel block by searching pixel values included in the first pixel block and a pixel block having similarity greater than or equal to a threshold value, and

identifying a foreground area in the input image frame, and perform re-research based on the second pixel block being searched in at least one of the foreground area or an adjacent area, and

wherein the acquiring the output image comprises:

summing pixel values of some pixels among pixels included in the first pixel block and pixel values of corresponding pixel among the second pixel block and dividing a value of the sum by a number of sums to obtain a calculated pixel value, and

replacing the some pixels with the calculated pixel value.

12. The apparatus of claim 1 , wherein the processor is further configured to:

based on the foreground being identified on both ends of a first image frame after a scene is changed, apply uniform scaling using a fallback technique instead of the retargeting of image frames included in the changed scene.

13. The apparatus of claim 1 , wherein the processor is further configured to:

identify the second pixel block in a first frame among a plurality of frames included in a same scene section; and

pad remaining frames among the plurality of frames with a pixel value at a relative position of the first pixel in the second pixel block determined in the first frame.

14. The apparatus of claim 13 , wherein the processor is further configured to:

based on pixel values of a pixel padding area included in the first frame being determined in the same scene section, determining pixel values of a subsequent frame by applying a weight to the pixel values of the pixel padding area.

15. The apparatus of claim 1 , wherein the processor is further configured to:

perform a pixel padding in a current scene by using a relative position of pixels used for padding in the previous scene or perform a pixel padding using a value of pixel position moved to padding in a plurality of previous scenes according to image characteristics of each scene in the current scene in order to maintain temporal coherency.