Electronic device and method of training a learning model for contrast ratio of an image
An electronic device is provided. The electronic device may include at least one processor, and at least one memory. The at least one processor may be configured to execute the instructions stored in the at least one memory, to: acquire an input image, predict an inverse function of a monotonically increasing function for decreasing an image contrast ratio by applying the input image to a learning model trained by using an artificial intelligence algorithm, and acquire an output image based on the input image and the predicted inverse function of the monotonically increasing function. The learning model may be trained to predict the inverse function of the monotonically increasing function for decreasing the an image contrast ratio by using a training image generated by applying a target image having a high contrast ratio to the monotonically increasing function and the inverse function of the monotonically increasing function as training data.
1. An electronic device comprising:
at least one processor; and
at least one memory configured to store instructions,
wherein the at least one processor is configured to execute the instructions stored in the at least one memory, to:
obtain an input image,
predict an inverse function of a monotonically increasing function for decreasing an image contrast ratio by applying the input image to a learning model trained by using an artificial intelligence algorithm, and
obtain an output image based on the input image and the predicted inverse function of the monotonically increasing function, and
wherein the learning model is trained to predict the inverse function of the monotonically increasing function for decreasing the image contrast ratio based on a training image generated by applying the monotonically increasing function to a target image having a high contrast ratio and the inverse function of the monotonically increasing function as training data.
2. The electronic device according to claim 1 , wherein the at least one processor is further configured to generate the output image having an increased contrast ratio by applying the input image to the predicted inverse function of the monotonically increasing function.
3. The electronic device according to claim 2 , further comprising:
a display,
wherein the at least one processor is further configured to control the display to display the output image and an object for adjusting a contrast ratio of the output image.
4. The electronic device according to claim 3 , wherein the at least one processor is further configured to control the display to display the output image by adjusting the contrast ratio of the output image based on receiving an external input by using the object.
5. The electronic device according to claim 4 , wherein the at least one processor is further configured to:
reflect the adjusted contrast ratio to the predicted inverse function of the monotonically increasing function, and
use the input image and the inverse function of the monotonically increasing function for the adjusted contrast ratio as the training data.
6. The electronic device according to claim 1 , wherein the at least one processor is further configured to train the learning model by inputting the training image, the inverse function of the monotonically increasing function, and the learning model to a learning machine.
7. The electronic device according to claim 1 , wherein the monotonically increasing function comprises at least one constant value, and
wherein the at least one processor is further configured to obtain a plurality of monotonically increasing functions by changing the at least one constant value.
8. The electronic device according to claim 7 , wherein the at least one processor is further configured to obtain a plurality of training images by applying the target image to the plurality of monotonically increasing functions.
9. The electronic device according to claim 1 , wherein the at least one processor is further configured to adjust a brightness value of pixels having a higher brightness value than an average brightness value of pixels included in the input image to be lower by using the monotonically increasing function.
10. The electronic device according to claim 1 , wherein the at least one processor is further configured to adjust a brightness value of pixels having a lower brightness value than an average brightness value of pixels included in the input image to be higher by using the monotonically increasing function.
11. A method for controlling an electronic device, the method comprising:
based on a target image having a high contrast ratio being obtained, obtaining a monotonically increasing function for decreasing an image contrast ratio;
obtaining a training image having a low contrast ratio by applying the monotonically increasing function to the target image; and
using the training image and an inverse function of the monotonically increasing function as training data for a learning model for increasing a contrast ratio of an input image.
12. The method according to claim 11 , further comprising:
predicting the inverse function of the monotonically increasing function for decreasing the image contrast ratio by applying the input image to the learning model trained using the training data.
13. The method according to claim 12 , further comprising:
generating an output image having an increased contrast ratio by applying the input image to the predicted inverse function of the monotonically increasing function.
14. The method according to claim 13 , further comprising:
displaying an object for adjusting a contrast ratio of the output image together with the output image.
15. The method according to claim 14 , further comprising:
providing the output image by adjusting the contrast ratio of the output image based on receiving an external input by using the object.
16. The method according to claim 15 , further comprising:
reflecting the adjusted contrast ratio to the predicted inverse function of the monotonically increasing function; and
using the input image and the inverse function of the monotonically increasing function for the adjusted contrast ratio as the training data.
17. The method according to claim 11 , further comprising:
training the learning model by inputting the training image, the inverse function of the monotonically increasing function, and the learning model to a learning machine.
18. The method according to claim 11 , wherein the monotonically increasing function comprises at least one constant value, and
wherein the method further comprises obtaining a plurality of monotonically increasing functions by changing the at least one constant value.
19. The method according to claim 18 , further comprising:
obtaining a plurality of training images by applying the target image to the plurality of monotonically increasing functions.
20. The method according to claim 11 , further comprising:
adjusting a brightness value of pixels having a higher brightness value than an average brightness value of pixels included in the input image to be lower or adjusting a brightness value of pixels having a lower brightness value than the average brightness value of pixels included in the input image to be higher by using the monotonically increasing function.