US-12620256-B2 - System to provide multiconfiguration biometric hardware compatibility

US12620256B2US 12620256 B2US12620256 B2US 12620256B2US-12620256-B2

Abstract

A biometric identification system processes input data acquired by input devices to determine embeddings used to identify a user. Different types of input devices or hardware configurations of input devices may produce different output. Each hardware configuration may be associated with respective representation data. A set of transformer networks are used to transform an embedding from one representation data associated with a first type of device or hardware configuration to another. This enables user participation via different configurations of hardware without requiring users to re-enroll for different input devices or hardware configurations. Opportunistic updates are made to the embeddings as embeddings native to a particular configuration of hardware are acquired from the user.

Inventors

Manoj Aggarwal
Gerard Guy Medioni

Assignees

AMAZON TECHNOLOGIES, INC.

Dates

Publication Date: 20260505
Application Date: 20221031

Claims (20)

1 . A system comprising: a memory, storing first computer-executable instructions; and a hardware processor to execute the first computer-executable instructions to: determine first input image data acquired using a first input device associated with a first hardware configuration, wherein the first input device comprises a dedicated biometric input device; determine first representation data based on processing the first input image data with a first embedding model, wherein the first representation data is associated with a first representation space; determine first transformed representation data based on processing the first representation data with a first transformer network, wherein: the first transformed representation data is associated with a second representation space, and the second representation space is associated with a second hardware configuration comprising one of a smartphone device, a tablet device, a laptop computer, a home security device, or a desktop computer; and determine first data indicative of an association between the first representation data and the first transformed representation data.
2 . The system of claim 1 , the hardware processor to further execute the first computer-executable instructions to: determine first identification data; and wherein the first data associates the first identification data with the first representation data and the first transformed representation data.
3 . The system of claim 1 , the hardware processor to further execute the first computer-executable instructions to: determine second data indicative of a correspondence between the first representation data and first enrolled user data associated with the first representation space being less than a threshold value; determine third data indicative of a correspondence between the first transformed representation data and the first enrolled user data associated with the second representation space being greater than or equal to the threshold value; and determine, based on the third data, that the first enrolled user data is associated with the first input image data.
4 . The system of claim 3 , the hardware processor to further execute the first computer-executable instructions to: store the first representation data as associated with the first enrolled user data.
5 . The system of claim 1 , the hardware processor to further execute the first computer-executable instructions to; determine second input image data acquired using a second input device associated with the second hardware configuration; determine second representation data based on processing the second input image data with a second embedding model, wherein the second representation data is associated with the second representation space; determine second data indicative of a correspondence between the second representation data and the first transformed representation data being greater than or equal to a threshold value; and determine third data indicative of an association between the first representation data and the second representation data.
6 . The system of claim 1 , wherein: the first input device associated with the first hardware configuration acquires image data using a first illumination mode; and the second representation space is associated with the first input device using a second illumination mode.
7 . The system of claim 1 , wherein: the first input image data comprises first biometric image data.
8 . A method comprising: acquiring first biometric input image data using a first input device that is associated with a first hardware configuration; determining first representation data based on processing the first biometric input image data with a first embedding model, wherein the first representation data is associated with a first representation space; determining first transformed representation data based on processing the first representation data with a first transformer network, wherein the first transformed representation data is associated with a second representation space; determining first data indicative of an association between the first representation data and the first transformed representation data; acquiring second biometric input image data; and determining second representation data based on processing the second biometric input image data with a second embedding model, wherein the second representation data is associated with the second representation space.
9 . The method of claim 8 , further comprising: determining first identification data; and wherein the first data associates the first identification data with the first representation data and the first transformed representation data.
10 . The method of claim 8 , further comprising: determining second data indicative of a correspondence between the first representation data and first enrolled user data associated with the first representation space being less than a threshold value; determining third data indicative of a correspondence between the first transformed representation data and the first enrolled user data associated with the second representation space being greater than or equal to the threshold value; and determining, based on the third data, that the first enrolled user data is associated with the first biometric input image data.
11 . The method of claim 10 , further comprising: storing the first representation data as associated with the first enrolled user data.
12 . The method of claim 8 , further comprising: determining second data indicative of a correspondence between the second representation data and the first transformed representation data being greater than or equal to a threshold value; and determining third data indicative of an association between the first representation data and the second representation data.
13 . The method of claim 8 , wherein: the first representation space is associated with input image data representative of images acquired using one or more of a first set of wavelengths of light or a first illumination mode; and the second representation space is associated with input image data representative of images acquired using one or more of a second set of wavelengths of light or a second illumination mode.
14 . A system comprising: a memory, storing first computer-executable instructions; and a hardware processor to execute the first computer-executable instructions to: determine first representation data based on processing first input image data with a first embedding model, wherein the first representation data is associated with a first representation space, wherein the first representation space is associated with input image data representative of images acquired using one or more of a first set of wavelengths of light or a first illumination mode; determine first transformed representation data based on processing the first representation data with a first transformer network, wherein the first transformed representation data is associated with a second representation space, wherein the second representation space is associated with input image data representative of images acquired using one or more of a second set of wavelengths of light or a second illumination mode; and determine first data indicative of an association between the first representation data and the first transformed representation data.
15 . The system of claim 14 , the hardware processor to further execute the first computer-executable instructions to: determine, based on one or more of the first representation data or the first transformed representation data, first enrolled user data; determine, based on the first enrolled user data, a first set of representation spaces; and determine a first set of transformed representation data based on processing the first representation data with respective transformer networks, wherein each respective transformer network is associated with a respective one of the first set of representation spaces.
16 . The system of claim 14 , the hardware processor to further execute the first computer-executable instructions to: determine a first hardware configuration associated with the first representation data; determine, based on the first hardware configuration, a first set of representation spaces; and determine a first set of transformed representation data based on processing the first representation data with respective transformer networks, wherein each respective transformer network is associated with a respective one of the first set of representation spaces.
17 . The system of claim 14 , the hardware processor to further execute the first computer-executable instructions to: determine first identification data; and wherein the first data associates the first identification data with the first representation data and the first transformed representation data.
18 . The system of claim 14 , the hardware processor to further execute the first computer-executable instructions to; determine second representation data based on processing second input image data with a second embedding model, wherein the second representation data is associated with the second representation space; determine second data indicative of a correspondence between the second representation data and the first transformed representation data being greater than or equal to a threshold value; and determine third data indicative of an association between the first representation data and the second representation data.
19 . The system of claim 14 , further comprising: a first input device associated with a first hardware configuration, wherein the first input device acquires the first input image data using one or more image sensors that detect a first set of wavelengths; and a second input device associated with a second hardware configuration, wherein the second input device acquires second input image data using one or more image sensors that detect a second set of wavelengths; and the hardware processor to further execute the first computer-executable instructions to: determine second representation data based on processing the second input image data with a second embedding model, wherein the second representation data is associated with the second representation space.
20 . The system of claim 14 , further comprising: a first input device comprising a smartphone device, tablet device, laptop computer, desktop computer, or a home security device, wherein the first input device acquires the first input image data; a second input device comprising a smartphone device, tablet device, laptop computer, desktop computer, network connected camera, or a home security device, wherein the second Input device acquires second input image data; and the hardware processor to further execute the first computer-executable instructions to: determine second representation data based on processing the second input image data with a second embedding model, wherein the second representation data is associated with the second representation space.

Description

BACKGROUND Biometric input data may be used to assert an identity of a user. BRIEF DESCRIPTION OF FIGURES The detailed description is set forth with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The use of the same reference numbers in different figures indicates similar or identical items or features. The figures are not necessarily drawn to scale, and in some figures, the proportions or other aspects may be exaggerated to facilitate comprehension of particular aspects. FIGS. 1A and 1B illustrate a system to provide multiconfiguration biometric hardware compatibility, according to some implementations. FIG. 2 illustrates processing training input data to determine transformer training data, according to some implementations. FIG. 3 illustrates a transformer module during training, according to some implementations. FIG. 4 illustrates transforming representation data to provide compatibility with another hardware configuration, according to some implementations. FIG. 5 illustrates a query using native and transformed representation data, according to some implementations. FIG. 6 illustrates compatibility matrix data indicative of hardware configurations and respective representation data to be transformed in, according to some implementation. FIG. 7 is a flow diagram of enrolling with a first hardware configuration and backfilling representation data to a second hardware configuration, according to some implementation. FIG. 8 is a block diagram of a computing device to implement the system, according to some implementations. While implementations are described herein by way of example, those skilled in the art will recognize that the implementations are not limited to the examples or figures described. It should be understood that the figures and detailed description thereto are not intended to limit implementations to the particular form disclosed but, on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope as defined by the appended claims. The headings used herein are for organizational purposes only and are not meant to be used to limit the scope of the description or the claims. As used throughout this application, the word “may” is used in a permissive sense (i.e., meaning having the potential to), rather than the mandatory sense (i.e., meaning must). Similarly, the words “include,” “including,” and “includes” mean including, but not limited to. DETAILED DESCRIPTION Input data, such as used for biometric identification, may be acquired using different hardware configurations of input devices. The input devices may acquire input data using one or more modalities. For example, one modality may comprise images of surface skin of a user's palm while a second modality may comprise images of subcutaneous features such as veins of the user's palm. Different hardware configurations may have different physical configurations, operational characteristics, and so forth. Physical configurations may differ by physical placement of components such as camera(s), illuminator(s), type of camera(s) used, wavelengths of light used, resolution of input data acquired, and so forth. This may result in different hardware configurations acquiring different kinds of input data. For example, a first hardware configuration may acquire input data using two modalities, a second hardware configuration may acquire input data using a single modality and an image resolution of 1 megapixel, a third hardware configuration may acquire input data using the single modality at an image resolution of 5 megapixels, a fourth hardware configuration may acquire input data using three modalities, and so forth. Overall performance of a biometric identification system may be maximized by tuning specific combinations of hardware configuration with subsequent data processing. During operation, the input data may be processed using an embedding network that provides as output representation data. For example, the embedding network may provide as output a fixed length embedding vector that is representative of features in the input data. The input data may be processed in other ways as well. For example, the input data may be preprocessed using one or more filters, image transforms, and so forth to generate a canonical version of the input data for subsequent processing. The embedding networks may be trained using the input data associated with a particular hardware configuration. Continuing the earlier example, the first hardware configuration using two modalities may utilize a first embedding network trained to process first modality images and a second embedding network trained to process second modality networks. In comparison, the third hardware configuration using the single modality at relatively high resolution may utilize a third embedding network train