System for biometric identification enrollment

1 . A system comprising:

one or more memories, storing first computer-executable instructions; and

one or more hardware processors to execute the first computer-executable instructions to:

begin a pre-enrollment process by performing steps to:

acquire, at a first time, first input image data of a hand of a user using a first device, wherein:

the first input image data is associated with a first modality, and

the first device is of a first type configured to acquire image data with the first modality;

determine, at a second time, first representation data using a first portion of a machine learning network to process the first input image data;

determine, at a third time, first identification data associated with the first input image data; and

store, at a fourth time, the first identification data and the first representation data as pre-enrollment data; and

after the pre-enrollment process has been completed, complete an enrollment process by performing steps to:

acquire, at a fifth time, second input image data of the hand of the user using a second device, wherein:

the second input image data is associated with a second modality,

the second device is of a second type that is different from the first type, and

the second device is configured to acquire image data with the second modality that is different from the first modality;

determine, at a sixth time, second representation data using a second portion of the machine learning network to process the second input image data;

determine, at a seventh time, that the first representation data is associated with the second representation data; and

store, at an eighth time, the first identification data and the second representation data as enrolled user data, wherein the first identification data is associated with the second representation data.

2 . The system of claim 1 , the one or more hardware processors to further execute the first computer-executable instructions to:

determine, after the fourth time, transaction data that is associated with the second device;

determine, after the eighth time, that the first identification data is associated with the transaction data; and

process the transaction data using the first identification data.

3 . The system of claim 1 , the one or more hardware processors to further execute the first computer-executable instructions to:

determine, before the first time, that one or more of the first device or an application executing on the first device are approved for use.

4 . The system of claim 1 , the one or more hardware processors to further execute the first computer-executable instructions to:

determine, before the seventh time, that the second representation data is not associated with previously enrolled representation data.

5 . The system of claim 1 , the one or more hardware processors to further execute the first computer-executable instructions to:

delete the first representation data after one of:

the first representation data is associated with the second representation data, or the first representation data has been stored for longer than a specified time.

6 . The system of claim 1 , the one or more hardware processors to further execute the first computer-executable instructions to:

determine first supplemental data that is associated with the first device and the first time;

determine second supplemental data that is associated with the second device and the second time; and

determine, before the seventh time, that at least a portion of the first supplemental data corresponds to the second supplemental data.

7 . The system of claim 1 , the one or more hardware processors to further execute the first computer-executable instructions to:

determine supplemental data that is associated with the second device and the second time; and

determine, before the seventh time, that at least a portion of the supplemental data corresponds to the first identification data.

8 . The system of claim 1 , the one or more hardware processors to further execute the first computer-executable instructions to:

determine, using a third portion of the machine learning network to process the first input image data, first intermediate representation data;

determine first intersection representation data using a fourth portion of the machine learning network to process the first intermediate representation data;

determine, using a fifth portion of the machine learning network to process the second input image data, second intermediate representation data;

determine second intersection representation data using a sixth portion of the machine learning network to process the second intermediate representation data; and

determine, based on the first intersection representation data and the second intersection representation data, that the first representation data is associated with the second representation data.

9 . The system of claim 8 , the one or more hardware processors to further execute the first computer-executable instructions to:

determine a first distance in an intersection embedding space between the first intersection representation data and the second intersection representation data; and

determine that the first representation data is associated with the second representation data based on the first distance being less than a threshold distance.

10 . The system of claim 1 , the one or more hardware processors to further execute the first computer-executable instructions to:

determine transformed representation data using a second machine learning network to process the first representation data, wherein the transformed representation data and the second representation data are associated with an embedding space; and

determine, based on the transformed representation data and the second representation data, that the first representation data is associated with the second representation data.

11 . A computer-implemented method comprising:

acquiring first input image data of a hand of a user using a first device of a first type, wherein the first device is configured to acquire image data of a first modality;

determining first representation data based on the first input image data;

determining first identification data associated with the first input image data;

storing the first identification data and the first representation data;

after the storing the first identification data and the first representation data, acquiring second input image data of the hand of the user using a second device of a second type that is different from the first type, wherein the second device is configured to acquire image data of a second modality that is different from the first modality;

determining second representation data based on the second input image data;

determining that the first representation data is associated with the second representation data; and

storing the first identification data and the second representation data as enrolled user data, wherein the first identification data is associated with the second representation data.

12 . The method of claim 11 , further comprising:

acquiring third input image data using a third device;

determining third representation data based on the third input image data;

determining that the third representation data is associated with one or more of the first representation data or the second representation data; and

storing the third representation data, wherein the first identification data is associated with the third representation data.

13 . The method of claim 11 , further comprising:

determining first supplemental data that is associated with the first input image data;

determining second supplemental data that is associated with the second input image data; and

determining that at least a portion of the first supplemental data corresponds to the second supplemental data.

14 . The method of claim 11 , further comprising:

determining, using a first portion of a machine learning network to process the first input image data, first intermediate representation data;

determining first intersection representation data using a second portion of the machine learning network to process the first intermediate representation data;

determining, using a third portion of the machine learning network to process the second input image data, second intermediate representation data;

determining second intersection representation data using a fourth portion of the machine learning network to process the second intermediate representation data; and

determining, based on the first intersection representation data and the second intersection representation data, that the first representation data is associated with the second representation data.

15 . The method of claim 11 , further comprising:

determining transformed representation data using a machine learning network to process the first representation data, wherein the transformed representation data and the second representation data are associated with an embedding space; and

determining, based on the transformed representation data and the second representation data, that the first representation data is associated with the second representation data.

16 . A system comprising:

one or more memories, storing first computer-executable instructions; and

one or more hardware processors to execute the first computer-executable instructions to:

acquire first input image data of a hand of a user using a first device of a first type, wherein the first input image data is associated with a first modality;

determine first representation data based on the first input image data;

determine first identification data associated with the first input image data;

store the first identification data and the first representation data;

acquire second input image data of the hand of the user using a second device of a second type that is different from the first type, wherein the second input image data is associated with a second modality that is different from the first modality;

determine second representation data based on the second input image data;

determine that the first representation data is associated with the second representation data; and

store the first identification data and the second representation data as enrolled user data, wherein the first identification data is associated with the second representation data.

17 . The system of claim 16 , the one or more hardware processors to execute the first computer-executable instructions to:

acquire third input image data using a third device, wherein the third device utilizes at least a third modality to acquire the third input image data;

determine third representation data based on the third input image data;

determine the third representation data is associated with one or more of the first representation data or the second representation data; and

store the third representation data, wherein the first identification data is associated with the third representation data.

18 . The system of claim 16 , the one or more hardware processors to further execute the first computer-executable instructions to:

determine transaction data that is associated with the second device;

determine that the first identification data is associated with the transaction data; and

process the transaction data using the first identification data.

19 . The system of claim 16 , the one or more hardware processors to further execute the first computer-executable instructions to:

determine first supplemental data that is associated with the first input image data;

determine second supplemental data that is associated with the second input image data; and

determine that at least a portion of the first supplemental data corresponds to the second supplemental data.