Biometric facial recognition for accessing device and authorizing event processing

1. A biometric facial recognition computing platform, comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

at least one memory storing computer-readable instructions that, when executed by the at least one processor, cause the biometric facial recognition computing platform to:

receive a request to access a device, the request including user identifying information;

query a database to obtain a pre-stored image of a user associated with the user identifying information and data associated with the pre-stored image, the data including a mean pixel value of the pre-stored image and a variance of the pre-stored image, the variance being determined based on data from at least a first pixel of the pre-stored image and eight pixels adjacent the first pixel of the pre-stored image;

capture, via an image capturing device, an image of a user requesting access to the device;

determine a mean pixel value for the captured image of the user requesting access to the device;

determine, based on the mean pixel value for the captured image, a variance of the captured image, the variance further being based on data from at least a first pixel of the captured image and eight pixels adjacent the first pixel of the captured image;

use a probabilistic neural network to determine a similarity score between the pre-stored image and the captured image based, at least in part, on the data associated with the pre-stored image and the mean pixel value and variance for the captured image; and

determine whether the similarity score is at or above a pre-determined threshold; and

responsive to determining that the similarity score is at or above the pre-determined threshold, provide access to the device.

2. The biometric facial recognition computing platform of claim 1 , wherein providing access to the device includes enabling functionality of the device.

3. The biometric facial recognition computing platform of claim 1 , further including instructions that, when executed, cause the biometric facial recognition computing platform to:

responsive to determining that the similarity score is not above the pre-determined threshold, providing limited access to the device.

4. The biometric facial recognition computing platform of claim 3 , wherein providing limited access includes enabling some functionality of the device and disabling other functionality of the device.

5. The biometric facial recognition computing platform of claim 1 , further including instructions that, when executed, cause the biometric facial recognition computing platform to:

responsive to determining that the similarity score is not above the pre-determined threshold, prevent access to the device.

6. The biometric facial recognition computing platform of claim 1 , further including instructions that, when executed, cause the biometric facial recognition computing platform to:

responsive to determining that the similarity score is not above the pre-determined threshold, request additional authentication information from the user requesting access to the device.

7. The biometric facial recognition computing platform of claim 1 , wherein the device is a self-service device.

8. The biometric facial recognition computing platform of claim 1 , further including instructions that, when executed, cause the biometric facial recognition computing platform to:

prior to receiving the request to access the device:

receive one or more images of a user; and

pre-processing the received one or more images of the user to determine a mean pixel value and variance of each image of the received one or more images.

9. The biometric facial recognition computing platform of claim 1 , further including instructions that, when executed, cause the biometric facial recognition computing platform to:

prior to determining a mean pixel value for the captured image, determine whether the captured image is in grayscale.

10. The biometric facial recognition computing platform of claim 9 , further including instructions that, when executed, cause the biometric facial recognition computing platform to:

responsive to determining that the captured image is not in grayscale, converting the captured image to grayscale and determining the mean pixel value for the captured image; and

responsive to determining that the captured image is in grayscale, determining the mean pixel value for the captured image.

11. The biometric facial recognition computing platform of claim 1 , further including instructions that, when executed, cause the biometric facial recognition computing platform to:

prior to capturing the image of the user requesting access to the device, determine whether a position of the user is appropriate to capture an image; and

responsive to determining that the position of the user is not appropriate, displaying an instruction to the user to modify the position of the user.

12. A method, comprising:

receiving, by a device, a request to access the device, the request including user identifying information;

transmitting, by the device, the received request and identifying information to a biometric facial recognition computing platform;

querying, by the biometric facial recognition computing platform, a database to obtain a pre-stored image of a user associated with the user identifying information and data associated with the pre-stored image, the data including a mean pixel value of the pre-stored image and a variance of the pre-stored image, the variance being determined based on data from at least a first pixel of the pre-stored image and eight pixels adjacent the first pixel of the pre-stored image;

capturing, via an image capturing device, an image of a user requesting access to the device;

transmitting, from the image capturing device to the biometric facial recognition computing platform, the captured image;

determining, by the biometric facial recognition computing platform, a mean pixel value for the captured image of the user requesting access to the device;

determining, by the biometric facial recognition computing platform and based on the mean pixel value for the captured image, a variance of the captured image the variance further being based on data from at least a first pixel of the captured image and eight pixels adjacent the first pixel of the captured image;

using a probabilistic neural network to determine, by the biometric facial recognition computing platform, a similarity score between the pre-stored image and the captured image based, at least in part, on the data associated with the pre-stored image and the mean pixel value and variance for the captured image;

determining, by the biometric facial recognition computing platform, whether the similarity score is at or above a pre-determined threshold; and

responsive to determining that the similarity score is at or above the pre-determined threshold, providing access to the device.

13. The method of claim 12 , wherein providing access to the device includes enabling functionality of the device.

14. The method of claim 12 , further including instructions that, when executed, cause the biometric facial recognition computing platform to:

responsive to determining that the similarity score is not above the pre-determined threshold, providing limited access to the device.

15. The method of claim 14 , wherein providing limited access includes enabling some functionality of the device and disabling other functionality of the device.

16. The method of claim 12 , further including instructions that, when executed, cause the biometric facial recognition computing platform to:

responsive to determining that the similarity score is not above the pre-determined threshold, prevent access to the device.

17. The method of claim 12 , further including instructions that, when executed, cause the biometric facial recognition computing platform to:

responsive to determining that the similarity score is not above the pre-determined threshold, request additional authentication information from the user requesting access to the device.

18. The method of claim 12 , further including:

prior to receiving the request to access the device:

receive, by the biometric facial recognition computing platform, one or more images of a user; and

pre-processing, by the biometric facial recognition computing platform, the received one or more images of the user to determine a mean pixel value and variance of each image of the received one or more images.

19. One or more non-transitory computer-readable media storing instructions that, when executed by a biometric facial recognition computer system comprising at least one processor, memory, and a communication interface, cause the biometric facial recognition computer system to:

receive a request to access a device, the request including user identifying information;

query a database to obtain a pre-stored image of a user associated with the user identifying information and data associated with the pre-stored image, the data including a mean pixel value of the pre-stored image and a variance of the pre-stored image, the variance being determined based on data from at least a first pixel of the pre-stored image and eight pixels adjacent the first pixel of the pre-stored image;

capture, via an image capturing device, an image of a user requesting access to the device;

determine a mean pixel value for the captured image of the user requesting access to the device;

determine, based on the mean pixel value for the captured image, a variance of the captured image, the variance further being based on data from at least a first pixel of the captured image and eight pixels adjacent the first pixel of the captured image;

use a probabilistic neural network to determine a similarity score between the pre-stored image and the captured image based, at least in part, on the data associated with the pre-stored image and the mean pixel value and variance for the captured image;

determine whether the similarity score is at or above a pre-determined threshold; and

responsive to determining that the similarity score is at or above the pre-determined threshold, provide access to the device.

20. The one or more non-transitory computer-readable media of claim 19 , wherein providing access to the device includes enabling functionality of the device.

21. The one or more non-transitory computer-readable media of claim 19 , further including instructions that, when executed, cause the biometric facial recognition computing system to:

responsive to determining that the similarity score is not above the pre-determined threshold, providing limited access to the device.

22. The one or more non-transitory computer-readable media of claim 21 , wherein providing limited access includes enabling some functionality of the device and disabling other functionality of the device.

23. The one or more non-transitory computer-readable media of claim 19 , further including instructions that, when executed, cause the biometric facial recognition computing system to:

prior to receiving the request to access the device:

receive one or more images of a user; and

pre-processing the received one or more images of the user to determine a mean pixel value and variance of each image of the received one or more images.

24. The one or more non-transitory computer-readable media of claim 19 , further including instructions that, when executed, cause the biometric facial recognition computing system to:

prior to determining a mean pixel value for the captured image, determine whether the captured image is in grayscale.

25. The one or more non-transitory computer-readable media of claim 24 , further including instructions that, when executed, cause the biometric facial recognition computing system to:

responsive to determining that the captured image is not in grayscale, converting the captured image to grayscale and determining the mean pixel value for the captured image; and

responsive to determining that the captured image is in grayscale, determining the mean pixel value for the captured image.