Automatic zoom on device screen to improve artificial intelligence identification rate

1. A system, comprising:

a microprocessor; and

a computer readable medium, coupled with the microprocessor and comprising microprocessor readable and executable instructions that, when executed by the microprocessor, cause the microprocessor to:

determine a type of user interface for different types of devices;

capture a first image of a user interface for one of the different types of devices;

identify, from the first image of the user interface, a graphical object in the user interface;

use a first Artificial Intelligence (AI) process to determine a first confidence score for the graphical object, wherein the first confidence score identifies a confidence of how likely a type of the graphical object can be identified;

select the first AI process from a plurality of AI processes based on the type of user interface for the different types of devices;

in response to the first confidence score not meeting a threshold, doing at least one of:

zoom in on the graphical object; and

zoom out from the graphical object.

2. The system of claim 1 , wherein zooming in on the graphical object is completed and wherein the microprocessor readable and executable instructions further cause the microprocessor to:

capture a second image of the user interface, where the captured second image is a zoomed in image of the graphical object;

use the first AI process to determine a second confidence score for the graphical object, wherein the second confidence score identifies a confidence of how likely the graphical object can be properly identified and wherein the second confidence score meets the threshold; and

identify the type of the graphical object.

3. The system of claim 1 , wherein zooming out on the graphical object is completed and wherein the microprocessor readable and executable instructions further cause the microprocessor to:

capture a second image of the user interface, where the captured second image is a zoomed-out image of the graphical object;

use the first AI process to determine a second confidence score for the graphical object, wherein the second confidence score identifies a confidence of how likely the graphical object can be properly identified and wherein the second confidence score meets the threshold; and

identify the type of the graphical object.

4. The system of claim 1 , wherein the graphical object comprises a plurality of graphical objects and wherein the microprocessor readable and executable instructions further cause the microprocessor to:

identify a first sub-group of graphical objects that are part of the plurality of graphical objects, wherein the first sub-group of graphical objects do not meet the threshold; and

zoom in on the first sub-group of graphical objects that do not meet the threshold.

5. The system of claim 4 , wherein the plurality of graphical objects comprises a second sub-group of one or more graphical objects and wherein the second sub-group of one or more graphical objects meets the threshold.

6. The system of claim 1 , wherein the first confidence score is based on a size of the graphical object and a spell check of text within the graphical object.

7. The system of claim 1 , wherein zooming in on the graphical object and zooming out from the graphical object are based on identifying a zoom area that is identified around the graphical object.

8. A method, comprising:

determining, by a microprocessor, a type of user interface for different types of devices capturing, by the microprocessor, a first image of a user interface for one of the different types of devices;

identifying, by the microprocessor, from the first image of the user interface, a graphical object in the user interface;

using, by the microprocessor, a first Artificial Intelligence (AI) process to determine a first confidence score for the graphical object, wherein the first confidence score identifies a confidence of how likely a type of the graphical object can be identified;

selecting, by the microprocessor, the first AI process from a plurality of AI processes based on the type of user interface for the different types of devices;

in response to the first confidence score not meeting a threshold, doing at least one of:

zooming in on the graphical object; and

zooming out from the graphical object.

9. The method of claim 8 , wherein zooming in on the graphical object is completed and further comprising:

capturing a second image of the user interface, where the captured second image is a zoomed in image of the graphical object;

using the first AI process to determine a second confidence score for the graphical object, wherein the second confidence score identifies a confidence of how likely the graphical object can be properly identified and wherein the second confidence score meets the threshold; and

identifying the type of the graphical object.

10. The method of claim 8 , wherein zooming out on the graphical object is completed and further comprising:

capturing a second image of the user interface, where the captured second image is a zoomed-out image of the graphical object;

using the first AI process to determine a second confidence score for the graphical object, wherein the second confidence score identifies a confidence of how likely the graphical object can be properly identified and wherein the second confidence score meets the threshold; and

identifying the type of the graphical object.

11. The method of claim 8 , wherein the graphical object comprises a plurality of graphical objects and further comprising:

identifying a first sub-group of graphical objects that are part of the plurality of graphical objects, wherein the first sub-group of graphical objects do not meet the threshold; and

zooming in on the first sub-group of graphical objects that do not meet the threshold.

12. The method of claim 11 , wherein the plurality of graphical objects comprises a second sub-group of one or more graphical objects and wherein the second sub-group of one or more graphical objects meets the threshold.

13. The method of claim 8 , wherein the first confidence score is based on a size of the graphical object and a spell check of text within the graphical object.

14. The method of claim 8 , wherein zooming in on the graphical object and zooming out from the graphical object are based on identifying a zoom area that is identified around the graphical object.

15. A non-transient computer readable medium having stored thereon instructions that cause a microprocessor to execute a method, the method comprising instructions to:

determine a type of user interface for different types of devices;

capture a first image of a user interface for one of the different types of devices;

identify, from the first image of the user interface, a graphical object in the user interface;

use a first Artificial Intelligence (AI) process to determine a first confidence score for the graphical object, wherein the first confidence score identifies a confidence of how likely a type of the graphical object can be identified;

select the first AI process from a plurality of AI processes based on the type of user interface for the different types of devices;

in response to the first confidence score not meeting a threshold, doing at least one of:

zoom in on the graphical object; and

zoom out from the graphical object.

16. The non-transient computer readable medium of claim 15 , wherein zooming in on the graphical object is completed and wherein the method further comprises instructions to:

capture a second image of the user interface, where the captured second image is a zoomed in image of the graphical object;

use the first AI process to determine a second confidence score for the graphical object, wherein the second confidence score identifies a confidence of how likely the graphical object can be properly identified and wherein the second confidence score meets the threshold; and

identify the type of the graphical object.

17. The non-transient computer readable medium of claim 15 , wherein zooming out on the graphical object is completed and wherein the method further comprises instructions to:

capture a second image of the user interface, where the captured second image is a zoomed-out image of the graphical object;

use the first AI process to determine a second confidence score for the graphical object, wherein the second confidence score identifies a confidence of how likely the graphical object can be properly identified and wherein the second confidence score meets the threshold; and

identify the type of the graphical object.

18. The non-transient computer readable medium of claim 15 , wherein the first confidence score is based on a size of the graphical object and a spell check of text within the graphical object.

19. The non-transient computer readable medium of claim 15 , wherein the graphical object comprises a plurality of graphical objects and wherein the method further comprises instructions to:

identify a first sub-group of graphical objects that are part of the plurality of graphical objects, wherein the first sub-group of graphical objects do not meet the threshold; and

zoom in on the first sub-group of graphical objects that do not meet the threshold.

20. The non-transient computer readable medium of claim 19 , wherein the plurality of graphical objects comprises a second sub-group of one or more graphical objects and wherein the second sub-group of one or more graphical objects meets the threshold.