Object recognizer emulation

1. A computer-implemented method for emulating an object recognizer, comprising:

receiving, by an emulator associated with a computer system, testing image data;

emulating, by the emulator employing a first object recognizer, a second object recognizer, including:

using the first object recognizer to perform object recognition on a testing object from the testing image data to generate data, the data including a feature representation for the testing object; and

classifying the testing object based on the feature representation and a machine learning model configured to predict whether the testing object would be recognized by a second object recognizer;

implementing a training stage, including:

receiving training image data;

using the first object recognizer to perform object recognition on a training object from the training image data to generate first data including a feature representation for the training object;

using the second object recognizer to perform object recognition on the training object to generate second data including a label assigned to the training object; and

building the machine learning model based on the first and second data; and

triggering, by the emulator, an action to be performed based on the classification.

2. The method of claim 1 , wherein the machine learning model is a binary classification model used to classify the testing object as a common object or an uncommon object.

3. The method of claim 1 , wherein the data further includes a thumbnail of the testing object and a timestamp corresponding to when the testing object was detected.

4. The method of claim 1 , wherein the first data further includes a thumbnail of the training object and a timestamp corresponding to when the training object was detected.

5. The method of claim 1 , wherein the computer system includes a facial recognition system.

6. The method of claimed 5 , wherein performing the action includes performing an action selected from the group consisting of: granting access to a service, denying access to a service, registering a user profile, prompting a user to submit a new image to complete registration, and combinations thereof.

7. A computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method for emulating an object recognizer, the method performed by the computer comprising:

receiving, by an emulator associated with a computer system, testing image data;

emulating, by the emulator employing a first object recognizer, a second object recognizer, including:

using the first object recognizer to perform object recognition on a testing object from the testing image data to generate data, the data including a feature representation for the testing object; and

classifying the testing object based on the feature representation and a machine learning model configured to predict whether the testing object would be recognized by a second object recognizer;

implementing a training stage, including:

receiving training image data;

using the first object recognizer to perform object recognition on a training object from the training image data to generate first data including a feature representation for the training object;

using the second object recognizer to perform object recognition on the training object to generate second data including a label assigned to the training object; and

building the machine learning model based on the first and second data; and

triggering, by the emulator, an action to be performed based on the classification.

8. The computer program product of claim 7 , wherein the machine learning model is a binary classification model used to classify the testing object as a common object or an uncommon object.

9. The computer program product of claim 7 , wherein the data further includes a thumbnail of the testing object and a timestamp corresponding to when the testing object was detected.

10. The computer program product of claim 7 , wherein the first data further includes a thumbnail of the training object and a timestamp corresponding to when the training object was detected.

11. The computer program product of claim 7 , wherein the computer system includes a facial recognition system.

12. The computer program product of claim 11 , wherein performing the action includes performing an action selected from the group consisting of: granting access to a service, denying access to a service, registering a user profile, prompting a user to submit a new image to complete registration, and combinations thereof.

13. A system for emulating an object recognizer, comprising:

an emulator including at least one processor device operatively coupled to a memory device and configured to execute program code stored on the memory device to:

receive testing image data;

emulate, by employing a first object recognizer, a second object recognizer by:

using the first object recognizer to perform object recognition on a testing object from the testing image data to generate data, the data including a feature representation for the testing object;

implement a training stage by:

receiving training image data;

using the first object recognizer to perform object recognition on a training object from the training image data to generate first data including a feature representation for the training object;

using the second object recognizer to perform object recognition on the training object to generate second data including a label assigned to the training object; and

building the machine learning model based on the first and second data; and

classify the testing object based on the feature representation and a machine learning model configured to predict whether the testing object would be recognized by a second object recognizer; and

trigger an action to be performed based on the classification.

14. The system of claim 13 , wherein the machine learning model is a binary classification model used to classify the testing object as a common object or an uncommon object.

15. The system of claim 13 , wherein the data further includes a thumbnail of the testing object and a timestamp corresponding to when the testing object was detected.

16. The system of claim 13 , wherein the system includes a facial recognition system.

17. The system of claim 16 , wherein the action is selected from the group consisting of: granting access to a service, denying access to a service, registering a user profile, prompting a user to submit a new image to complete registration, and combinations thereof.