Method for processing image based on scene recognition of image and electronic device therefor

1. An electronic device comprising:

a camera;

a memory; and

a processor operatively connected with the camera and the memory,

wherein the processor is configured to:

obtain, using the camera, a plurality of images for one or more external objects,

identify a region of interest and a background region by using one or more images of the plurality of images, while obtaining the plurality of images,

recognize a first object included in the region of the interest,

identify a type of the background region by recognizing a second object included in the background region,

determine a similarity between a previous image and the one or more images, and

if the similarity is less than a specified value, determine a scene corresponding to the one or more images based on the recognized first object and the identified type of the background region, and adjust at least one of an image quality setting associated with the camera or an image quality setting associated with the one or more images by using a specified image quality setting corresponding to the determined scene.

2. The electronic device of claim 1 , wherein the processor is further configured to:

identify the region of interest and the background region by using the one or more images, when the similarity falls within a specified first range,

wherein the previous image is used to determine the scene before obtaining the one or more images.

3. The electronic device of claim 2 , wherein the processor is further configured to:

adjust the at least one of the image quality setting associated with the camera or the image quality setting associated with the one or more images, by using an image quality setting set for the previous image, when the similarity between the previous image and the one or more images falls within a specified second range, which is different from the first range.

4. The electronic device of claim 1 , wherein the processor is further configured to determine the scene corresponding to the one or more images based on a reliability of the recognized first object.

5. The electronic device of claim 4 , wherein the processor is further configured to determine the scene corresponding to the one or more images based on a reliability of the type, when the reliability of the recognized first object is less than a first value.

6. The electronic device of claim 5 , wherein the processor is further configured to:

determine, when the reliability of the type is less than a specified second value, an upper-level category including at least one type corresponding to the second object included in the background region, based on a sum of reliability of the at least one type, and

determine the determined upper-level category as the scene corresponding to the one or more images.

7. The electronic device of claim 5 , wherein the processor is further configured to determine a validity of the scene, which is determined based on the reliability of the type, based on at least one of time information or position information of the electronic device.

8. The electronic device of claim 1 , wherein the image quality setting associated with the one or more images comprises at least one of brightness, contrast, gamma, hue, sharpness, blur, or color temperature.

9. The electronic device of claim 1 , wherein the image quality setting associated with the camera comprises at least one of photosensitivity, a lens diameter, an aperture size, a shutter speed, exposure, focus, hue, a color temperature, or white balance.

10. The electronic device of claim 9 , further comprising a display,

wherein the processor is further configured to display an image obtained using the camera adjusted with the image quality setting as a preview on the display.

11. An electronic device, comprising:

a camera;

a display;

a processor operatively connected with the camera and the display; and

a memory operatively connected with the processor,

wherein the memory comprises instructions, which when executed, cause the processor to:

obtain an image,

identify an object from a partial region of the obtained image,

identify a first tag corresponding to the identified object,

identify a second tag corresponding to an entire region of the obtained image,

identify a scene tag corresponding to the obtained image based on reliabilities of the first tag and the second tag, and

adjust an image quality setting parameter of the camera using an image quality setting parameter corresponding to the identified scene tag that is based on the reliabilities of the first tag and the second tag,

wherein the instructions, when executed, further cause the processor to identify, as the scene tag, a tag corresponding to one upper-level category in an upper-level category, based on a sum of reliabilities of second tags, which belong to a same upper-level category in the upper-level category of the second tag, when a reliability of the first tag and a reliability of the second tag are less than a specified reliability.

12. The electronic device of claim 11 , wherein the instructions, when executed, further cause the processor to identify the object, the first tag, and the second tag, when a similarity between a previous image obtained before the obtained image and the obtained image falls within a specified range.

13. The electronic device of claim 12 , wherein the instructions, when executed, further cause the processor to adjust the image quality setting parameter of the camera by using an image quality setting parameter set for the previous image, when the similarity between the previous image and the obtained image falls within the specified range.

14. The electronic device of claim 11 , wherein the instructions, when executed, further cause the processor to:

determine a validity of the scene tag, based on time information or position information of the electronic device, and

adjust the image quality setting parameter of the camera by using the image quality setting parameter corresponding to the scene tag, when the scene tag is determined as being valid.

15. The electronic device of claim 11 , wherein the instructions, when executed, further cause the processor to identify, when a specified tag is included in the first tag, the scene tag based on the specified tag, without identifying the second tag.

16. The electronic device of claim 11 , wherein the image quality setting parameter of the camera comprises at least one of photosensitivity, a lens diameter, an aperture size, a shutter speed, exposure, focus, hue, a color temperature, or white balance.

17. The electronic device of claim 11 , wherein the instructions, when executed, further cause the processor to display, on the display, in a preview form, an image obtained using the camera adjusted with the image quality setting parameter.

18. A method for setting image quality in an electronic device, the method comprising:

obtaining an image;

identifying an object from a partial region of the obtained image;

identifying a first tag corresponding to the identified object;

identifying a second tag corresponding to an entire region of the obtained image;

identifying a scene tag corresponding to the obtained image, based on reliabilities of the first tag and the second tag; and

adjusting an image quality setting parameter of a camera of the electronic device by using an image quality setting parameter corresponding to the scene tag that is based on the reliabilities of the first tag and the second tag,

wherein, if the reliabilities of the first tag and the second tag are less than a specified value, a tag corresponding to one upper-level category in an upper-level category is identified as the scene tag based on a sum of reliabilities of second tags, which belong to a same upper-level category in the upper-level category of the second tag.

19. The method of claim 18 , wherein the image quality setting parameter of the camera of the electronic device comprises at least one of photosensitivity, a lens diameter, an aperture size, a shutter speed, exposure, focus, hue, a color temperature, or white balance.