Apparatus and method for image region detection of object based on seed regions and region growing

1. An image processing apparatus, comprising:

a memory configured to store first region detection information corresponding to at least one object of a first frame; and

a processor configured to:

perform region growing processing based on a seed region identified from a second frame and a first pixel region corresponding to the first region detection information,

obtain second region detection information corresponding to at least one object of the second frame, based on the region growing processing, and

perform image processing on the second frame based on the second region detection information,

wherein the processor is further configured to perform region growing processing on the first pixel region based on a second adjacent pixel region adjacent to the first pixel region.

2. The image processing apparatus as claimed in claim 1 , wherein the processor is further configured to:

identify the second adjacent pixel region and a first adjacent pixel region that is adjacent to the seed region,

perform region growing processing on the seed region based on a similarity between the seed region and the first adjacent pixel region, and

perform the region growing processing on the first pixel region based on a similarity between the first pixel region and the second adjacent pixel region.

3. The image processing apparatus as claimed in claim 2 , wherein the processor is further configured to:

add a third pixel region in which the similarity between the seed region and the first adjacent pixel region is a threshold value or more to a detection region,

add a fourth pixel region in which the similarity between a third adjacent pixel region that is adjacent to the third pixel region and the third pixel region is a threshold value or more to the detection region,

add a fifth pixel region in which the similarity between the first pixel region and the second adjacent pixel region is a threshold value or more to the detection region, and

add a pixel region in which a similarity between a sixth adjacent pixel region that is adjacent to the fifth pixel region and the fifth pixel region is a threshold value or more to the detection region.

4. The image processing apparatus as claimed in claim 2 , wherein the processor is further configured to:

identify the second frame as a plurality of pixel blocks,

identify whether each of pixel blocks in a first line among the plurality of pixel blocks corresponds to the seed region,

identify whether each of the pixel blocks is an adjacent pixel block of the seed region or an adjacent pixel block of the first pixel region to perform region detection, and

perform region detection on each of pixel blocks in a second line after region detection on the first line is completed.

5. The image processing apparatus as claimed in claim 4 , wherein the processor is further configured to:

perform region detection on the pixel blocks in the first line sequentially in a first direction, and

perform region detection on the pixel blocks in the second line sequentially in a second direction different from the first direction.

6. The image processing apparatus as claimed in claim 1 , wherein the first region detection information includes first probability information in which each of a plurality of pixel blocks in the first frame is included in a detection region,

wherein the second region detection information includes second probability information in which each of a plurality of pixel blocks in the second frame is included in the detection region, and

wherein the processor is further configured to obtain the second probability information based on the first probability information and the seed region.

7. The image processing apparatus as claimed in claim 1 , wherein the first region detection information includes first identification information indicating whether each of a plurality of pixel blocks in the first frame is a detection region,

wherein the second region detection information includes second identification information indicating whether each of a plurality of pixel blocks in the second frame is the detection region, and

wherein the processor is further configured to obtain the second identification information based on the first identification information and the seed region.

8. The image processing apparatus as claimed in claim 1 , wherein the processor is further configured to identify the second frame as a plurality of pixel blocks, and sequentially perform region detection on the plurality of pixel blocks, and

wherein the second region detection information includes a region detection result of the second frame with respect to a previously processed pixel block based on a present pixel block included in the second frame, and a region detection result of the first frame with respect to a pixel block to be processed.

9. The image processing apparatus as claimed in claim 1 , wherein the processor is further configured to:

based on obtaining the first region detection information, perform image processing on the first frame based on the first region detection information, and store the first region detection information in the memory, and

perform image processing on the second frame based on the second region detection information and store the second region detection information in the memory.

10. The image processing apparatus as claimed in claim 1 , wherein the second region detection information is obtained by updating the first region detection information stored in the memory based on a region detection result of the second frame.

11. The image processing apparatus as claimed in claim 1 , further comprising:

a display,

wherein the processor is further configured to control the display to sequentially display the first frame and the second frame on which image processing is performed,

wherein the first frame on which image processing is performed includes an image-processed first region,

wherein the second frame on which image processing is performed includes an image-processed second region, and

wherein the image-processed second region includes the image-processed first region and a third region other than the image-processed first region.

12. The image processing apparatus as claimed in claim 1 , wherein the first frame and the second frame are 4K Ultra High Definition (UHD) images or 8K UHD image frames.

13. The image processing apparatus as claimed in claim 1 , wherein the processor is further configured to:

perform region expansion based on each seed region identified based on different color information, and

perform image processing for each object region of a different color included in the second region detection information.

14. The image processing apparatus as claimed in claim 13 , wherein the processor is further configured to obtain an output image that is image processed by applying the second frame and the second region detection information into a training network model, and

wherein the training network model is a model trained to apply an image processing for each object region of a different color.

15. The image processing apparatus as claimed in claim 14 , wherein the training network model is a model trained to perform contrast adjustment for each object region of a different color.

16. An image processing method for an image processing apparatus, the image processing method comprising:

storing first region detection information corresponding to at least one object of a first frame;

performing region growing processing based on a seed region identified from a second frame and a first pixel region corresponding to the first region detection information,

obtaining second region detection information corresponding to at least one object of the second frame, based on performing the region growing processing; and

performing image processing on the second frame based on the second region detection information,

wherein the image processing method further comprises performing region growing processing on the first pixel region based on a second adjacent pixel region adjacent to the first pixel region.

17. The image processing method as claimed in claim 16 , wherein the obtaining of the second region detection information comprises:

identifying the second adjacent pixel region and a first adjacent pixel region that is adjacent to the seed region,

performing region growing processing on the seed region based on a similarity between the seed region and the first adjacent pixel region, and

performing the region growing processing on the first pixel region based on a similarity between the first pixel region and the second adjacent pixel region.

18. The image processing method as claimed in claim 17 , wherein the obtaining of the second region detection information comprises:

adding a third pixel region in which a similarity between the seed region and the first adjacent pixel region is a threshold value or more to a detection region,

adding a fourth pixel region in which a similarity between a third adjacent pixel region that is adjacent to the third pixel region and the third pixel region is a threshold value or more to the detection region,

adding a fifth pixel region in which a similarity between the first pixel region and the second adjacent pixel region is a threshold value or more to the detection region, and

adding a pixel region in which a similarity between a sixth adjacent pixel region that is adjacent to the fifth pixel region and the fifth pixel region is a threshold value or more to the detection region.

19. The image processing method as claimed in claim 17 , wherein the obtaining of the second region detection information comprises:

identifying the second frame as a plurality of pixel blocks,

identifying whether each of pixel blocks in a first line among the plurality of pixel blocks corresponds to the seed region,

identifying whether each of the pixel blocks is an adjacent pixel block of the seed region or an adjacent pixel block of the first pixel region to perform region detection, and

performing region detection on each of pixel blocks in a second line after region detection on the first line is completed.

20. A non-transitory computer readable recording medium having stored thereon a computer command which, when executed by a processor of an image processing apparatus, causes the image processing apparatus to perform operations including:

storing first region detection information corresponding to at least one object of a first frame;

performing region growing processing based on a seed region identified from a second frame and a first pixel region corresponding to the first region detection information;

obtaining second region detection information corresponding to at least one object of the second frame, based on performing the region growing processing; and

performing image processing on the second frame based on the obtained second region detection information,

wherein the operations further include performing region growing processing on the first pixel region based on a second adjacent pixel region adjacent to the first pixel region.