Method for biometric authentication through vascular studies and non-transitory computer-readable recording medium

TWI945162BActive Publication Date: 2026-11-11JVC KENWOOD CORP
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
TW110146031
Authority / Receiving Office
TW · TW
Patent Type
Patents
Current Assignee / Owner
Priority Date
2021-08-27
Filing Date
2021-12-09
Publication Date
2026-11-11
Estimated Expiration
2041-12-08

AI Technical Summary

Technical Problem

Vein pattern authentication systems are vulnerable to spoofing and require specialized, expensive equipment, making them difficult to deploy and less appealing for widespread adoption.

Method used

A method for biometric authentication using temporal changes in blood vessel dynamics, monitored through remote photoplethysmography, which utilizes standard electronic devices to analyze digital images of anatomical regions for deformation-induced blood flow patterns.

Benefits of technology

Provides high-security authentication without specialized equipment, is robust against spoofing, and allows for minimally disruptive user interaction, leveraging existing devices like smartphones for image capture.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure TWG2TB001919907_001
    Figure TWG2TB001919907_001
  • Figure TWG2TB001919907_002
    Figure TWG2TB001919907_002
  • Figure TWG2TB001919907_003
    Figure TWG2TB001919907_003
Patent Text Reader

Abstract

This article introduces methods for identifying unknown individuals based on changes in the spatial properties and directionality of blood flow through blood vessels over time. In general, these methods rely on monitoring vascular dynamics to identify unknown individuals. For example, an authentication platform can examine digital images of an anatomical region to determine how the properties of the vascular distribution within that region change as a result of deformation. Examples of these properties include the location, size, volume, and pressure of the blood vessels included in the vascular distribution, as well as the velocity and acceleration of the blood flowing through that vascular distribution.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] This disclosure relates to biometric authentication in computer security, and more specifically, to techniques for examining physiological characteristics to achieve minimally invasive authentication. [Cross-reference to related applications]

[0002] This application claims priority to U.S. Provisional Patent Application No. 63 / 127,054, filed on December 17, 2020, entitled “Vein Map Authentication with Image Sensor,” the entire contents of which are incorporated herein by reference. [Previous Technology]

[0003] Biometric authentication procedures verify an individual's identity through biometrics. The term "biometric" refers to physical or behavioral characteristics that can be used as a means of verifying identity. Biometrics are difficult to fake and convenient because the corresponding individual does not need to remember passwords or management tokens. Instead, the authentication mechanism is an integral part of the individual.

[0004] Fingerprints have historically been the most common biometric modality. However, with technological advancements, other biometric modalities have emerged. As an example, vascular pattern recognition (also known as "vein pattern identification") uses near-infrared light to create images of subcutaneous blood vessels (or simply "veins"). These subcutaneous blood vessels collectively define the "vascular pattern" or "vein map" that can be used for authentication. Vein pattern authentication has shown promise because vascular patterns are not only unique to the corresponding individual, but also undergo minimal changes as the individual ages.

[0005] Vein pattern authentication typically involves identifying and then analyzing the pattern of blood vessels along the back of the hand. For example, near-infrared light generated by a light-emitting diode (LED) can be emitted toward the back of the hand, thus penetrating the skin. Due to the different absorbance of blood vessels and other tissues, the near-infrared light will reflect toward the skin at different depths. The vascular pattern can be inferred based on the analysis of the reflected near-infrared light, and features such as branch locations and angles can be determined from the vascular pattern (and then used for authentication).

[0006] Vein pattern authentication has been touted as a contactless option for biometric authentication because vein patterns are relatively difficult to forge due to their complexity in reconstruction. Furthermore, vein pattern authentication offers significant improvements over other biometric authentication methods in terms of false acceptance (also known as "false positive rate") and false rejection (also known as "false negative rate"). However, vein pattern authentication has several drawbacks. For example, individuals are often reluctant to expose their bodies to unfamiliar light sources, which typically accompany the scanning equipment required for vein pattern authentication. Additionally, such scanning equipment can be difficult (if not impossible) to deploy in certain environments and is prohibitively expensive for many businesses. [Summary of the Invention]

[0007] and

Implementation Method

[0021] To register for an authentication program that relies on vein pattern matching, an individual (also referred to as a “user”) may initially be prompted to present their hand to a vascular scanner. The term “vascular scanner” can be used to refer to an imaging instrument that includes (i) a transmitter operable to emit electromagnetic radiation (e.g., in the near-infrared range) into the body, and (ii) a sensor operable to sense electromagnetic radiation reflected by physiological structures within the body. Typically, digital images are created based on reflected electromagnetic radiation used as a reference sample. In general, the reference sample represents a “live” vascular pattern that can be used for authentication.

[0022] Figure 1 provides a high-level illustration of a conventional authentication procedure, in which an unknown person is prompted to present their hand to a vascular scanner. As shown in Figure 1, the vascular scanner emits electromagnetic radiation onto the hand and then creates a digital image (also known as a “scan”) based on the electromagnetic radiation reflected by the blood vessels in the hand. This image indicates the vascular pattern of the hand and can therefore be verified against a reference sample created for a given individual during the enrollment phase (also known as the “registration phase”). If the digital image matches the reference sample, the unknown person will be authenticated as that given individual. However, if the digital image does not match the reference sample, the unknown person will not be authenticated as that given individual.

[0023] Because vein scanners do not require direct contact with the body during scanning, vein pattern matching has become an attractive option for biometric authentication. However, vein pattern matching has proven to be susceptible to spoofing. For example, Jan Krissler and Julian Albrecht demonstrated at the 2018 Chaos Communication Congress how to bypass a vein scanner using a wax prosthetic hand. While spoofing is unlikely to succeed under most real-world conditions, any concerns associated with vulnerabilities could hinder the adoption of reliable biometric authentication technologies.

[0024] Therefore, this paper introduces methods for authenticating unknown persons based on the temporal changes in the spatial characteristics and directionality of blood flow through blood vessels. In general, these methods rely on monitoring vascular dynamics to identify unknown persons. The term "vascular dynamics" refers to changes in the distribution and properties of blood vessels caused by deformation of the surrounding subcutaneous tissue, for example, due to gestures. Examples of vascular properties include the location, size, volume, and pressure of blood vessels, as well as the velocity and acceleration of blood flowing through them.

[0025] As discussed further below, these certified methods can be considered a form of remote photoplethysmography (PPG) monitoring. The term "photoplethysmography" refers to an optically acquired volumetric graph that can be used to detect changes in blood volume in subcutaneous tissue. During each cardiac cycle, the heart pumps blood to the periphery of the body. Although this pressure pulse weakens as the blood reaches the skin, it is still sufficient to dilate blood vessels in the subcutaneous tissue to a detectable degree. The volumetric change caused by the pressure pulse can be detected by illuminating the skin and then measuring the amount of light transmitted or reflected to an image sensor. In PPG, each cardiac cycle is shown as a peak, as shown in Figure 2.

[0026] Historically, pulse oximeters have been commonly used for PPG monitoring. PPG meters typically include at least one light-emitting diode (LED) that emits light through a part of the body, such as a fingertip or earlobe, to a photodiode. However, PPG can also be obtained through the analysis of digital images of an anatomical region of interest. In this case, pressure pulses can be identified through subtle changes in the color of the skin and subcutaneous tissue. However, the subtle characteristics of pressure pulses can be difficult to determine. For example, the timing and phase of pressure pulses are difficult to detect through the analysis of digital facial images due to the complex structure of the underlying vascular distribution and the complex effects of body posture and facial expressions. Deformation of subcutaneous tissue caused by body posture and facial expressions affects the resistance to blood flow through the facial venous network, thus affecting the signal generated by an image sensor that observes the subcutaneous tissue innervated by the venous network. Although the relationship between subcutaneous tissue deformation and the signal generated by the image sensor is difficult to quantify, deformation has a predictable effect on the signal (and can therefore be used as a means of authentication).

[0027] To determine whether to authenticate an unknown person as a given individual, the authentication platform (also called the "authentication system") can determine the degree to which the vascular dynamics of the unknown person are compared to those of a given individual. For example, suppose the unknown person wishes to authenticate herself as a given individual. In this scenario, the unknown person might be prompted to perform a gesture that causes deformation of the subcutaneous tissue (and therefore the vascular distribution) in the anatomical region. This gesture can be related to the anatomical region. For example, if the authentication platform wants to check the vascular dynamics of the face, it can prompt the unknown person to smile or frown, and if the authentication platform wants to check the vascular dynamics of the hand, it can prompt the unknown person to clench her hand.

[0028] When an unknown person performs a gesture, the camera of the electronic device can generate digital images of the anatomical area. For example, the camera can generate digital images rapidly and continuously at a predetermined rhythm. As another example, the camera can generate video of the anatomical area, in which case the digital images can represent frames of the video. Based on the analysis of the digital images, the authentication platform can generate a "biometric signature" or "vascular signature" for the unknown performance. For example, the authentication platform can generate a vein model that programmatically indicates how the blood vessel distribution deforms during the gesture. In general, the vein model specifies how the spatial characteristics of the blood vessel distribution change due to the gesture. Alternatively, the authentication platform can estimate measures of blood vessel properties based on the analysis of the digital images. For example, the authentication platform can attempt to quantify how the directionality of blood flow through the blood vessel distribution changes due to the gesture.

[0029] The authentication platform can then compare the biometric signature with a registered biometric signature (also known as a “reference biometric signature”) associated with a given individual to determine whether the unknown person should be authenticated as that given individual. For example, if the authentication platform generates a vein model that is programmed to indicate how the blood vessel distribution of an unknown person deforms during gesture performance, the authentication platform can (i) obtain a vein map associated with the given individual and (ii) estimate the deformation that the given individual can expect during gesture performance based on the vein map. As another example, if the authentication platform estimates a metric that indicates how blood vessel properties change during gesture performance, the authentication platform can (i) obtain a vein map associated with the given individual and (ii) estimate the metric that the given individual can expect during gesture performance based on the vein map. As discussed further below, the vein map can be stored in a digital profile containing information about the blood vessel distribution of a given individual. For example, the digital profile may include vein maps of different anatomical regions, metrics of different blood vessel properties, etc.

[0030] In summary, the authentication platform can present a notification instructing the person to be authenticated to perform a gesture that causes deformation of the anatomical region, acquire a digital image of the anatomical region generated by an electronic device when the person performs the gesture, estimate the blood flow characteristics of subcutaneous vessels within the anatomical region based on the digital image, and then determine whether to authenticate the person as the given individual based on the estimated characteristics and a comparison with a digital profile associated with the given individual. The estimated characteristics may be, for example, the directionality, velocity, volume, phase, or pressure of the blood flowing through the subcutaneous vessels.

[0031] Biometric signature-based authentication offers many of the same benefits as vein pattern matching, namely, high accuracy, reliability, and consistency, because the information to be "read" is inside the body. However, these methods are easier to implement because they do not require specialized equipment (e.g., a vascular scanner). Instead, authentication can be performed based on the analysis of digital images generated by an electronic device. While electronic devices may include specialized software, firmware, or hardware, commodity-standardized hardware (e.g., digital image sensors for mobile phones, tablets, etc.) may be sufficient to capture high-quality digital images.

[0032] In general, the authentication platform aims to facilitate a method by which individuals can link venography, as an authentication factor, with blood flow as a measurement of PPG signals. Therefore, authentication can be achieved using electronic devices that cannot detect an individual's blood vessels but can detect spatially decomposed PPG signals (e.g., through analysis of digital images). Specifically, the method described herein (i) enables highly secure authentication without the need for specialized equipment, (ii) allows authentication based on (e.g., modified) knowledge factors and biometric information of unknown persons and given individuals, and (iii) allows for robust authentication against deception and theft, as new modifications can be easily identified and requested.

[0033] For illustrative purposes, embodiments may be described in the context of monitoring the distribution of blood vessels in a given anatomical region. For example, embodiments may be described in the case of examining digital images of the face, palm, or fingers. However, the methods described herein can be similarly applied to the distribution of blood vessels in other parts of the human body.

[0034] Although not strictly necessary, implementation is described below in the case of instructions that can be executed by an electronic device. The term "electronic device" is generally used interchangeably with the term "computing device" and can therefore be used to refer to computer servers, point-of-sale (POS) systems, tablet computers, wearable devices (e.g., fitness trackers and watches), mobile phones, etc.

[0035] Although some modules may be described as being exclusively or primarily executed by a single electronic device, some implementations are executed in a distributed environment where modules are shared among multiple electronic devices linked together via a network. For example, an unknown person may be required to initiate an authentication process via a mobile phone that generates a digital image of an anatomical region, although the decision to authenticate the unknown person can be made by an authentication platform residing on a computer server that transmits the digital image to the mobile phone. Terminology

[0036] References to "an embodiment" or "one embodiment" in this specification mean that the described features, functions, structures, or characteristics are included in at least one embodiment of the present technology. The appearance of such phrases does not necessarily refer to the same embodiment, nor does it necessarily refer to mutually exclusive alternative embodiments.

[0037] Unless the context explicitly requires otherwise, the terms “comprise,” “comprising,” and “comprised of” shall be interpreted in an inclusive sense rather than an exclusive or exhaustive sense (i.e., “including but not limited to”). The term “based on” shall also be interpreted in an inclusive sense rather than an exclusive or exhaustive sense. Thus, unless otherwise stated, the term “based on” is intended to mean “at least partially based on.”

[0038] The terms “connected,” “coupled,” and variations thereof are intended to include any connection or coupling between two or more elements, whether direct or indirect. The connection / coupling can be physical, logical, or a combination thereof. For example, objects may be electrically or communicatively coupled to each other even without sharing a physical connection.

[0039] The term "module" can refer to a software component, a firmware component, or a hardware component. A module is typically a functional element that produces one or more outputs based on one or more inputs. For example, a computer program may include multiple modules responsible for performing different tasks or a single module responsible for performing all tasks.

[0040] When used to refer to a list of multiple items, the term "or" is intended to cover all of the following interpretations: any item in the list, all items in the list, and any combination of items in the list.

[0041] The order of steps performed in any process described herein is exemplary. However, unless contrary to physical possibility, these steps can be performed in various orders and combinations. For example, steps can be added to or removed from the steps described herein. Similarly, steps can be substituted or reordered. Therefore, any description of a process is intended to be open-ended. Authentication through analysis of vascular information.

[0042] This section describes an authentication platform that uses vascular dynamics as a biometric to verify that an unknown person is a given individual. As discussed further below, the spatial characteristics and directionality of blood flow through vessels in an anatomical region can be estimated based on the analysis of one or more digital images of that region. The spatial characteristics and directionality of blood flow will vary with deformation of the surrounding subcutaneous tissue (e.g., due to gestures), and these variations can be used to determine whether an unknown person is authenticated as a given individual.

[0043] Authentication platforms can be used to secure biometric-driven transactions, such as payments authenticated via a hands-free interface. For example, suppose an unknown person wishes to authenticate themselves to complete a transaction. Instead of prompting the unknown person to place a body part (e.g., her hand) near a vascular scanner, biometric authentication can be performed using the electronic device the unknown person uses to initiate the transaction. For example, if the unknown person initiates the transaction using her mobile phone, the mobile phone can generate a digital image of an anatomical region (e.g., the face) that can be analyzed by the authentication platform. As discussed further below, the authentication platform can reside on the mobile phone or another electronic device (e.g., a computer server) connected to the mobile phone. While this authentication method relies on the analysis of blood vessels under the skin, the mobile phone does not need to touch the skin. Instead, the unknown person can simply be prompted to use the mobile phone to generate a digital image of the anatomical region for authentication purposes. Therefore, authentication platforms can allow people to authenticate themselves in a minimally invasive manner by relying on information about vascular dynamics.

[0044] In some embodiments, the authentication platform operates independently to authenticate the identity of an unknown person, while in other embodiments, the authentication platform operates in conjunction with another system. For example, a payment system may interface with the authentication platform to ensure that transactions are completed securely and smoothly. As an example, the authentication platform may facilitate contactless payment procedures, where an unknown person is allowed to initiate or complete a transaction by making a body part available for imaging. As mentioned above, an unknown person can make a body part available for imaging by simply positioning it within the field of view of an electronic device's camera. While electronic devices are typically used to initiate or complete transactions, this is not always the case.

[0045] It should be noted that while the embodiments may discuss authentication in the context of initiating or completing a transaction, authentication can be useful in a variety of situations. For example, suppose individuals are invited one after another to a network-accessible meeting where sensitive information will be shared. Each person attempting to enter the network-accessible meeting may need to be authenticated by an authentication platform to be allowed access. Overview of the Authentication Platform

[0046] Figure 3 includes a high-order representation of system 300, which can be used to authenticate the identity of an unknown person whose vascular distribution is available for imaging. As shown in Figure 3, system 300 includes an authentication platform 302 that can access a user interface (UI) 304, an image sensor 306, a light source 308, a processor 310, or any combination thereof. As discussed further below, these components of system 300 can be embedded in the same electronic device or distributed among multiple electronic devices. For example, authentication platform 302 can reside partially or entirely on a network-accessible server system, while UI 304, image sensor 306, light source 308, and processor 310 can reside on another electronic device responsible for generating digital images of the unknown person.

[0047] UI 304 represents the interface through which an unknown person can interact with system 300. UI 304 may be a voice-driven graphical user interface (GUI) displayed on the display of an electronic device. Alternatively, UI 304 may be a non-voice-driven GUI displayed on the display of an electronic device. In such an embodiment, UI 304 may visually indicate body parts to be presented for authentication purposes. For example, UI 304 may visually prompt the unknown person to locate her body so that anatomical areas can be observed by image sensor 306. As an example, UI 304 may include a “live view” of digital images generated by image sensor 306, allowing the unknown person to easily align her face with image sensor 306. As another example, UI 304 may present an illustration indicating where the unknown person should place her hands so that image sensor 306 can image the palm or back of the hand. Furthermore, UI 304 may present the final authentication decision made by authentication platform 302.

[0048] The image sensor 306 can be any electronic sensor capable of detecting and transmitting information to generate a digital image. Examples of image sensors include charge-coupled device (CCD) sensors and complementary metal-oxide-semiconductor (CMOS) sensors. The image sensor 306 can be implemented in a camera module (or simply "camera"). In some embodiments, the image sensor 306 is one of a plurality of image sensors implemented in an electronic device. For example, the image sensor 306 can be included in a front or rear camera built into a mobile phone.

[0049] Typically, digital images are generated by an image sensor 306 in conjunction with ordinary visible light. However, the image data representing a digital image can be in various formats, color spaces, etc. For example, the image sensor 306 can be implemented in a camera designed to output image data according to a red-green-blue (RGB) color model, so as to assign separate chromaticity values ​​of red, green, and blue to each pixel. As another example, the image sensor 306 can be implemented within a camera designed to output image data according to one of the YCbCr color spaces, so as to assign a single value for the luminance component (Y) and a pair of values ​​for the chromaticity components (Cb, Cr) to each pixel.

[0050] The light source 308 includes one or more illuminators capable of emitting light in the visible or invisible range. For example, the light source 308 may include an illuminator capable of emitting white light when the image sensor 306 generates a digital image. Additionally or alternatively, the light source 308 may include an illuminator capable of emitting ultraviolet or infrared light. Examples of illuminators include light-emitting diodes (LEDs), organic LEDs (OLEDs), resonant cavity LEDs (RCLEDs), quantum dots (QDs), lasers such as vertical-cavity surface-emitting lasers (VCSELs), superluminescent diodes (SLEDs), and various phosphors.

[0051] Those skilled in the art will recognize that if image sensor 306 is instructed (e.g., via processor 310) to combine light emitted by light source 308 (whether visible or invisible) to generate a digital image, then image sensor 306 must be designed to detect electromagnetic radiation within an appropriate range. Besides CCD and CMOS, other examples of image sensors include monolithically integrated germanium (Ge) photodiodes, indium gallium arsenide (InGaAs) photodiodes, mercury cadmium telluride (HgCdTe) photodiodes, and other photodetectors (e.g., photodiodes) designed for the infrared and ultraviolet regions of the electromagnetic spectrum.

[0052] Therefore, the image sensor 306 and the light source 308 can operate together to generate digital images of the anatomical region under specific lighting conditions. For example, the image sensor 306 can generate a series of digital images when the light source 308 emits light within the visible range. As another example, the image sensor 306 can generate at least one digital image when the light source 308 emits light within the visible range, and at least one digital image when the light source 308 emits light within the invisible range.

[0053] As described above, the image sensor 306 and the light source 308 can be embedded in a single electronic device. In some embodiments, the electronic device is associated with an unknown person. For example, the image sensor 306 and the light source 308 can be embedded in a mobile phone associated with an unknown person. In other embodiments, the electronic device is not associated with an unknown person. For example, the image sensor 306 and the light source 308 can be embedded in a POS system through which an unknown person is attempting to complete a transaction.

[0054] This electronic device may be referred to as a "vascular monitoring device" because it is responsible for monitoring changes in the distribution of blood vessels within an anatomical region of interest. During the imaging portion of the authentication dialogue, the vascular monitoring device can collect image data related to the anatomical region. As discussed further below, the authentication platform 302 may be able to identify pulse waves by examining the image data. The term "pulse wave" can refer to a color change along the surface of the anatomical region caused by blood flow through the underlying subcutaneous tissue. While color changes may be difficult (if not impossible) to detect with the human eye, the authentication platform 302 may be able to identify these changes by analyzing the image data. Since pulse waves are related to the heartbeat cycle, information about the distribution of blood vessels in the anatomical region (and the entire cardiovascular system) can be collected from the pulse waves.

[0055] As shown in Figure 3, the authentication platform 302 may include a flow prediction algorithm 312, a flow measurement algorithm 314, a pattern matching algorithm 316, an authentication algorithm 318, and a biometric database 320. The biometric database 320 may store biometric data, representing collected information related to the vascular properties of unknown individuals. The biometric data in the biometric database 320 may vary depending on the authentication method employed by the system 300. The biometric data in the biometric database 320 may be encrypted, hashed, or otherwise obfuscated to prevent unauthorized access.

[0056] For example, the biometric database 320 may include digital profiles of various individuals, and each digital profile may include a vein map of the corresponding individual that can be used for authentication. Each vein map may consist of, or be composed of, two-dimensional or three-dimensional image data of a corresponding anatomical region. For example, suppose the authentication platform 302 is programmed to determine whether to authenticate an unknown person as a given individual based on the deformation of the blood vessel distribution within the anatomical region. In this case, the authentication platform 302 may prompt the unknown person to perform a gesture, and then determine the deformation of the blood vessel distribution in the anatomical region by analyzing image data generated by the image sensor 306. The authentication platform 302 may then compare the deformation with a vein model associated with the given individual. In general, the vein model may be programmed to indicate how the blood vessel distribution of the given individual deforms when performing a gesture. In other words, the vein model may represent a series of discrete locations that indicate how the shape of a single blood vessel or a group of blood vessels changes over time when a gesture is performed, thereby causing deformation of the surrounding subcutaneous tissue.

[0057] This vein model can be created in several different ways. In some embodiments, a given individual is prompted to perform a gesture while being imaged during the registration phase, and a vein model is created based on the analysis of the resulting digital image. In other embodiments, an anatomical region of the given individual is imaged so that a vein map can be generated by the authentication platform 302. In this embodiment, the authentication platform 302 can simulate the deformation of the blood vessel distribution when performing a gesture based on the vein map.

[0058] A digital profile may include a single vein model associated with a single gesture, multiple vein models associated with a single gesture, or multiple models associated with different gestures. Similarly, a digital profile may include a single vein model associated with a single anatomical region, multiple vein models associated with a single anatomical region, or multiple models associated with different anatomical regions. During the registration phase, individuals may be allowed to specify which anatomical regions and gestures can be used for authentication. While the authentication platform 302 may require the creation of at least one vein model for each anatomical region and gesture pair, individuals may also be allowed to create multiple vein models (e.g., for improved robustness).

[0059] Additionally or alternatively, the digital profile may include reference values ​​for different vascular properties that can be used for authentication (e.g., determining the blood velocity flowing through a vessel within a given anatomical region). Therefore, the biometric database 320 may include data indicating temporal changes in the vascular properties of a single tube of blood or a collection of vessels during the performance of a gesture. Authentication may be based on the similarity between values ​​of vascular properties such as pressure or flow rate, rather than the similarity between spatial deformations of vascular distribution, or, in addition to the similarity between spatial deformations of vascular distribution, authentication may also be based on the similarity between values ​​of vascular properties such as pressure or flow rate.

[0060] As described above, the biometric database 320 may include one or more biometric signatures. The nature of each biometric signature may depend on how authentication is performed. For example, each biometric signature may represent a vein model created for an individual during the registration phase. Alternatively, each biometric signature may represent one or more values ​​indicating the temporal changes in vascular properties when subcutaneous tissue in the anatomical region deforms. As an example, a biometric signature may contain a vector of length N, where each element is a value specifying the velocity of blood flow through the vascular distribution of the anatomical region when a gesture is performed. N may represent the number of samples taken over when a gesture is performed. In other words, N may represent the number of digital images of the anatomical region generated when a gesture is performed, since the flow velocity can be estimated independently for each digital image.

[0061] Biometric signatures in biometric database 320 can be associated with a single individual, in which case authentication platform 302 can be limited to authenticating an unknown person as that individual. Alternatively, these biometric signatures can be associated with multiple individuals, in which case authentication platform 302 may be able to authenticate an unknown person as any of those individuals. Furthermore, a single individual may have multiple biometric signatures in biometric database 320, as described above. These biometric signatures may correspond to different types (e.g., vein model and vascular characteristic values), different anatomical regions, or different gestures. For example, an individual may choose to create multiple biometric signatures for different anatomical regions during the registration phase, and each anatomical region may have a different biometric signature. As another example, an individual may choose to create multiple biometric signatures for different gestures during the registration phase, and each gesture may have a different biometric signature.

[0062] When executed by processor 310, the algorithm implemented in authentication platform 302 allows individuals to generate biometric signatures during the registration phase. Subsequently, the algorithm implemented in authentication platform 302 allows verification during the usage phase. The registration and usage phases are further described below.

[0063] The flow prediction algorithm 312 can be responsible for determining the relative timing of pulses within an anatomical region by analyzing one or more digital images of the anatomical region. For example, the flow prediction algorithm 312 can determine the timing or phase of pulses at specific spatial coordinates (e.g., a specified anatomical region) with or without physical deformation based on digital images. When no physical deformation is determined, this measurement may be referred to as a “measured venous flow pattern” or “measured flow pattern”, while when physical deformation is determined, this measurement may be referred to as a “measured deformed venous flow pattern” or “measured deformed flow pattern”. As an example, the relative arrival time of pulses can be estimated based on the identification of characteristics of pulses (such as dicrotic waves). Based on this information, the flow prediction algorithm 312 can estimate the velocity of blood flowing through the vascular distribution within the anatomical region. Alternatively, the flow prediction algorithm 312 can estimate other vascular properties, such as the phase of pressure pulses in the anatomical region, blood flow direction, blood flow volume, or pressure of the vascular distribution.

[0064] The flow measurement algorithm 314 can be responsible for predicting the propagation pattern of pulse waves that will occur when the anatomical region is deformed. This propagation pattern may be referred to as the "predicted deformed venous flow pattern" or "predicted deformed flow pattern". To achieve this, the flow measurement algorithm 314 can create a PPG by modeling, estimating, or otherwise predicting how the pulse waves will propagate through the deformed anatomical region. The flow measurement algorithm 314 can take the measured flow pattern, venogram, and deformed venogram as input. As mentioned above, the deformed venogram can be determined based on at least one digital image of the deformed anatomical region, or the deformed venogram can be determined by simulating deformation by altering the venogram.

[0065] In some embodiments, the flow measurement algorithm 314 is a machine learning algorithm. For example, the flow measurement algorithm 314 may be based on a neural network and have parameters that are based on best practice paradigms or adjusted experimentally.

[0066] The predicted deformable flow pattern can be expressed using two-dimensional or three-dimensional coordinates associated with the surface of the anatomical region. Furthermore, the predicted deformable flow pattern can be associated with (i) temporal information and (ii) phase information. The temporal information can relate to the relative time it takes for a pressure pulse to arrive at a coordinate after reaching the anatomical region. The temporal information can, for example, correspond to identifiable features of the pressure pulse, such as a dicrotic wave or another portion of a pulse wave representing the pressure pulse. The phase information can relate to the relative phase of the pressure pulse appearing at each coordinate at a single point in time. Each coordinate in the anatomical region can have a different pulse waveform due to the varying effects on pressure pulses across the anatomical region.

[0067] The pattern matching algorithm 316 can be responsible for calculating the matching strength between the predicted deformable flow pattern and the measured deformable flow pattern. In other words, the pattern matching algorithm 316 can be responsible for establishing the similarity between the measured deformable flow pattern and the measured deformable flow pattern. The similarity can be represented using a metric called a "matching score". The matching score can be represented using any suitable numerical scale. For example, the matching score can indicate the similarity using any integer value between 0 and 100 or any decimal value between 0 and 1.

[0068] The authentication algorithm 318 can be responsible for determining whether to authenticate the unknown person as a given individual based on the matching score. For example, the authentication algorithm 318 can be programmed to authenticate the unknown person as a given individual if the matching score exceeds a predetermined threshold. If the matching score does not exceed the predetermined threshold, the authentication algorithm 318 will not authenticate the unknown person as a given individual. Typically, the authentication algorithm 318 is designed to output a binary signal indicating whether the authentication is appropriate (e.g., pass or fail). However, the authentication algorithm 318 can also be designed to output a non-binary signal. As an example, the output generated by the authentication algorithm 318 can indicate (i) that the unknown person should be authenticated as a given individual, (ii) that the unknown person should not be authenticated as a given individual, or (iii) that further authentication attempts are needed. If the authentication algorithm 318 cannot definitively determine whether the authentication is appropriate, the authentication platform 302 can take further action (e.g., by prompting the unknown person to perform another gesture or presenting another anatomical region for imaging).

[0069] Figure 4 illustrates an example of an electronic device 400 capable of implementing an authentication platform 414, which is designed to authenticate the identity of an unknown person based on image data generated by an image sensor 408. As discussed above, the image data may represent one or more digital images of anatomical regions of the body. In some embodiments, those digital images are generated based on ambient light reflected from the anatomical regions to the image sensor 408. In other embodiments, a light source 410 emits light toward the anatomical regions to illuminate them, while those digital images are generated by the image sensor 408. Note that the light source 410 may also be configured to emit a series of discrete "pulses" or "flashes" of light at time intervals.

[0070] In some embodiments, the authentication platform 414 is embodied as a computer program executed by the electronic device 400. For example, the authentication platform 414 may reside on a mobile phone capable of acquiring image data that can determine whether the authentication is appropriate. As another example, the authentication platform 414 may reside on a POS system capable of acquiring image data that can make a determination. In other embodiments, the authentication platform 414 is embodied as a computer program executed by another electronic device communicatively connected to the electronic device 400. In this embodiment, the electronic device 414 may transmit the image data to another electronic device for processing. For example, although the authentication of an unknown person may be requested by the POS system used to initiate the transaction, the image data may be generated by a mobile phone located near the unknown person. The image data may be provided to the POS system or another electronic device (e.g., a computer server) for processing, or it may be processed by the mobile phone before being transmitted to the POS system or other electronic device. Those skilled in the art will recognize that the form of the authentication platform 414 may also be distributed across multiple electronic devices.

[0071] Electronic device 414 may include processor 402, memory 404, UI output mechanism 406, image sensor 408, light source 410, and communication module 412. Communication module 412 may be, for example, a wireless communication circuit designed to establish a communication channel with other electronic devices. Examples of wireless communication circuits include integrated circuits (also referred to as "chips") configured for Bluetooth, Wi-Fi, NFC, etc. Processor 402 may have general-purpose characteristics similar to a general-purpose processor, or processor 402 may be an application-specific integrated circuit (ASIC) that provides control functions for electronic device 400. As shown in FIG. 4, processor 402 may be directly or indirectly coupled to all components of electronic device 400 for communication purposes.

[0072] Memory 404 can be composed of any suitable type of storage medium, such as static random access memory (SRAM), dynamic random access memory (DRAM), electrically erasable programmable read-only memory (EEPROM), flash memory, or temporary registers. In addition to storing instructions that can be executed by processor 402, memory 404 can also store image data generated by image sensor 408 and data generated by processor 402 (e.g., when executing the module of authentication platform 414). Note that memory 404 is merely an abstract representation of the storage environment. Memory 404 can be composed of actual memory chips or modules.

[0073] As discussed above, the light source 410 can be configured to emit light (more specifically, electromagnetic radiation) in the visible or invisible range toward an anatomical region of the unknown human body to be authenticated. Typically, the light source 410 emits light only when instructed to do so. For example, if the authentication platform 414 determines that authentication is necessary, the authentication platform 414 can generate an output that prompts the processor 402 to (i) instruct the light source 410 to emit light and (ii) instruct the image sensor 408 to generate image data.

[0074] Communication module 412 can manage communication between components of electronic device 400. Communication module 412 can also manage communication with other electronic devices. Examples of electronic devices include mobile phones, tablets, personal computers, wearable devices, POS systems, and network-accessible server systems consisting of one or more computer servers. For example, in an embodiment where electronic device 400 is a mobile phone, communication module 412 can facilitate communication with a network-accessible server system responsible for examining image data generated by image sensor 408.

[0075] For convenience, the authentication platform 414 may be referred to as a computer program residing in memory 404. However, the authentication platform 414 may consist of software, firmware, or hardware components implemented in or accessible to the electronic device 400. According to the embodiments described herein, the authentication platform 414 may include various algorithms as discussed above with reference to FIG3. Typically, these algorithms are executed by separate modules of the authentication platform 414, which are individually addressable (and thus can be executed independently without interfering with other modules). These modules may be integral parts of the authentication platform 414. Alternatively, these modules may be logically separate from the authentication platform 414, but operate "together" with it. Together, these algorithms may enable the authentication platform 414 to authenticate the identity of an unknown person based on the analysis of vascular dynamics determined from image data generated from image sensor 408.

[0076] For example, suppose an unknown person wishes to authenticate themselves as a given individual. In this case, the unknown person may be prompted to perform a gesture that causes deformation of the blood vessel distribution in an anatomical region. When the unknown person performs the gesture, the image sensor 408 can generate image data, which is a digital image representing the anatomical region. Based on the analysis of this digital image, the authentication platform 414 can generate a "biometric signature" of the unknown performance. For example, the authentication platform 414 can generate a vein model that programmatically indicates how the blood vessel distribution deforms during the gesture, or the authentication platform 414 can estimate a measure of blood vessel properties based on the analysis of the image data.

[0077] The authentication platform 414 can then compare the biometric signature with a registered biometric signature associated with a given individual to determine whether the unknown person should be authenticated as the given individual. Typically, registered biometric signatures are stored in a biometric database 416. In Figure 4, the biometric database 416 is located in memory 404 of the electronic device 400. However, the biometric database 416 may alternatively or additionally be located in remote memory accessible via a network by the electronic device 400. If the biometric signature is sufficiently similar to a registered biometric signature, the authentication platform 414 can authenticate the unknown person as the given individual.

[0078] Other elements may also be included as part of the authentication platform 414. For example, the UI module may be responsible for generating content to be output by the UI output mechanism 406 for presentation to an unknown person. The form of the content may depend on the nature of the UI output mechanism 406. For example, if the UI output mechanism 406 is a speaker, the content may include audio instructions to position the electronic device 400 so that the image sensor 408 can observe the anatomical area. As another example, if the UI output mechanism 406 is a display, the content may include visual instructions to position the electronic device 400 so that the image sensor 408 can observe the anatomical area. The UI output mechanism 406 may also be responsible for outputting (e.g., issuing or displaying) the authentication decision made by the authentication platform 414. Vascular deformation caused by gesture expression.

[0079] Within a given anatomical region, the blood vessels beneath the skin define the vascular distribution. As an example, the face contains several anatomical regions (e.g., the forehead, cheeks, and chin) where the vascular distribution can be visually monitored. Figure 5 illustrates how the underlying vascular distribution in an anatomical region (here, the face) changes due to the expression of a gesture that causes physical deformation of the surrounding tissue. Figure 5 also illustrates how blood flowing through the vascular distribution can be monitored based on pulse waves. In other words, blood flow within the vascular distribution can be visually monitored as blood flows toward the arterioles at the tips of the capillaries in the anatomical region. In Figure 5, arbitrary cells numbered 1-4 are used to show an example sequence of pulse arrival.

[0080] As discussed above, the measured flow pattern may change because (i) the physical movement of blood vessels alters their position and (ii) deformation of surrounding tissues alters the hemodynamic flow properties of the blood vessel distribution of interest. For example, tissue compression may cause an increase in microvascular pressure, thereby altering the relative pulse phase and pulse velocity. Typically, the blood vessel distribution will deform in a predictable manner whenever a gesture is repeatedly performed. If (i) the gesture, (ii) the undeformed blood vessel pattern (e.g., the upper left image in Figure 5), and (iii) the measured flow pattern (e.g., the lower left image in Figure 5) are known, then the measured deformed flow pattern (e.g., the lower right image in Figure 5) and / or the deformed blood vessel pattern (e.g., the upper right image in Figure 5) can be determined. This process is further discussed below with reference to step 904 of Figure 9. Determining the flow pattern through pulse analysis

[0081] An important aspect of the methods described herein is determining the blood flow pattern through the distribution of blood vessels in a given anatomical region via the analysis of image data. Figures 6A-C illustrate several different methods for determining, calculating, or otherwise obtaining pulse waves. Figure 6A illustrates a method for defining a region of interest (ROI) to generate a digital image using object recognition. As shown in Figure 6B, red and green pixel values ​​can be captured for the ROI over a period of time of at least one cycle. This can be done for multiple patches within the ROI, where the pixel values ​​are averaged across each patch. The patches can have a fixed size and be distributed within the ROI according to a segmentation function. Alternatively, the patches can have an adjustable size (e.g., based on the size of the ROI or based on the amount of available computational resources). The average pixel values ​​from each patch can then be used to estimate pulse wave values ​​that can be used to determine the phase of the pulse wave. As shown in Figure 6C, these pulse wave values ​​can represent the relative phase period in arbitrary units.

[0082] Note that since the red and green pixel values ​​are related to variations occurring at different depths (e.g., different vascular structures), the components may be affected differently by physical deformations. This difference can be a useful component that can be used to train the algorithm described herein to detect and then to create predictions. Therefore, it may be beneficial to ensure that the red and green pixel values ​​are not only available for the authentication platform but also independently used to calculate phase predictions and estimates. Authentication Method

[0083] Figure 7 includes a flowchart of a procedure 700 for authenticating a user of an authentication platform based on the analysis of visual evidence of vascular dynamics in an anatomical region. As discussed further below, the authentication procedure has three phases: a training phase, a registration phase, and a usage phase. These phases can be designed to allow minimally destructive authentication without requiring the user to interact with the electronic device in unusual ways. Instead, the user can simply make gestures, while the electronic device generates digital images of the anatomical region distorted by the expression of these gestures.

[0084] For illustrative purposes, the authentication procedure can be described in the case of monitoring the distribution of blood vessels when the surrounding subcutaneous tissue deforms due to the gesture. However, the surrounding subcutaneous tissue can deform in other ways. For example, if the blood vessel distribution to be monitored is located in the finger, the user can be prompted to position the finger adjacent to the electronic device so that tactile feedback generated by a tactile actuator (or simply "actuator") located inside the electronic device can deform the surrounding subcutaneous tissue.

[0085] To begin the training phase, the flow prediction algorithm may undergo supervised, semi-supervised, or unsupervised learning, wherein training data is extracted, created, or otherwise obtained and then provided to the flow prediction algorithm for training purposes. Training data may include measured flow patterns and / or measured deformed flow patterns, associated with corresponding venograms and / or deformed venograms. Typically, training data is associated with a single anatomical region, because an understanding of deformities in one anatomical region (e.g., the face) may not be applicable to another anatomical region (e.g., the hand). However, training data may be associated with multiple individuals. Therefore, for a variety of individuals, training data may include measured flow patterns, measured deformed flow patterns, venograms, deformed venograms, or any combination thereof.

[0086] In some embodiments, gesture learning is accomplished through transfer learning based on a model learned during normal time (e.g., a state without gestures, also referred to as the "normal state"). For example, each layer of the neural network can be divided into (i) a first layer associated with gesture-independent features of the corresponding individual and (ii) a second layer associated with gesture-dependent features of the corresponding individual. A simplification of the image data used for learning (and a simplification of the learning process) can be anticipated by fixing the first layer and learning only the second layer for each gesture of interest.

[0087] As described above, a portion of the training data (e.g., vein patterns and deformed vein patterns) may be image data. In some embodiments, the image data is generated from various capture angles or positions, or from various image sensors (e.g., corresponding to different electronic devices), to provide greater robustness to these variations during the usage phase.

[0088] Furthermore, the training data can be divided into a training set and a test set; for example, 80% of the training data may be allocated to the training set and 20% to the test set. Those skilled in the art will recognize that these values ​​are provided for illustrative purposes. More or less than 80% of the training data may be allocated to the training set. Similarly, more or less than 20% of the training data may be allocated to the test set. The share of training data allocated to the training set is typically greater than (e.g., 2, 3, 5 times, etc.) the share of training data allocated to the test set. The training set can be used to train the flow prediction algorithm as discussed below, while the test set can be used to confirm that the flow prediction algorithm has correctly learned how to predict flows.

[0089] In general, a flow prediction algorithm comprises a set of algorithms designed to produce an output (also referred to as a “prediction”) related to the flow of blood through the vascular distribution of an anatomical region given inputs. These inputs may include venograms, deformed venograms, or image data of the anatomical region. In some embodiments, this set of algorithms represents one or more neural networks. The neural network learns by processing paradigms, each paradigm being associated with known inputs and outputs to form a weighted probabilistic correlation between the inputs and outputs. These weighted probabilistic correlations may be referred to as “weights.” During the training phase, the neural network of the flow prediction algorithm can initially use randomly selected weights. As the flow prediction algorithm learns from measured flow patterns, venograms, and deformed venograms, these weights can be adjusted. Thus, the flow prediction algorithm can adjust these weights as it learns how to output predicted deformed flow patterns.

[0090] Each predicted deformed flow pattern output by the flow prediction algorithm can be scored based on its deviation from the corresponding measured deformed flow pattern, which is the actual situation. Typically, this is done for each example included in the training set. More specifically, the pattern matching algorithm can calculate a score using a threshold for the time or phase of each time coordinate (e.g., + / - 3, 5, or 10 milliseconds). If the time difference between the measured deformed flow pattern and the predicted deformed flow pattern exceeds the threshold, the time coordinate can be marked as a failure. The score can be calculated by the pattern matching algorithm based on the percentage of time coordinates that have been classified as failures. Furthermore, the pattern matching algorithm can compare the score to a predetermined threshold, classifying each example in the training set as "pass" or "fail" depending on whether the corresponding score exceeds the predetermined threshold. The pattern matching algorithm can calculate the overall success rate of the flow prediction algorithm based on the percentage of pass examples in the training set.

[0091] Note that the weights of the neural network in the flow prediction algorithm can be adjusted according to any scheme to optimize success. An example of a known scheme is the Monte Carlo method. Therefore, this part of the training phase can be repeated for a predetermined number of periods, or this part of the training phase can be repeated until the overall success rate reaches an acceptable value (e.g., 90, 95, or 98%).

[0092] To ensure the proper functioning of the flow prediction algorithm, a test set can be used. Therefore, the flow prediction algorithm can be applied to the test set, including geovenous maps and deformed geovenous maps, to generate predicted flow patterns or predicted deformed flow patterns. As discussed above, the pattern matching algorithm can calculate a score indicating the performance of the flow prediction algorithm based on a comparison between the predicted flow pattern or predicted deformed flow pattern and the measured flow pattern or measured deformed flow pattern, respectively.

[0093] During the registration phase (also known as the “setting phase”), vein maps and deformed vein maps can be generated for the user during normal use of the electronic device. For example, upon receiving input instructing the initiation of the registration phase, the electronic device can generate digital images of anatomical regions when they are deformed (e.g., due to the user’s gestures). When the electronic device generates a digital image of a face, the deformation can be indicated by the UI through a request (e.g., via text) for the user to smile, frown, or purse their lips. For example, the UI can display a graphical representation of the deformation using a general model of the anatomical region or the human body to visually guide the user. As another example, the UI can display a graphical representation of a gesture that would cause deformation of the anatomical region. For example, the graphical representation can serve as a visual instruction to interact with the electronic device responsible for generating digital images in a specific manner (e.g., swiping a finger across the screen, gripping the casing in a specific manner, etc.).

[0094] From these digital images, venograms and deformed venograms of the anatomical region can be generated. As shown in Figure 7, the venograms and deformed venograms are typically stored in a biometric database and then subsequently retrieved when an unknown person attempts to authenticate themselves as a user.

[0095] Figure 8 includes a flowchart of process 800 performed by the authentication platform during the usage phase (also known as the “implementation phase”). Initially, the authentication platform receives input from a source instructing the unknown person to authenticate as a given individual (step 801). In some embodiments, the source is a computer program running on the same electronic device as the authentication platform. For example, if the authentication platform resides on a mobile phone, the authentication request may originate from a mobile application through which the unknown person is attempting to perform an activity requiring authentication. In other embodiments, the source is from another electronic device. For example, suppose the unknown person attempts to complete a transaction using a POS system associated with a merchant. In this case, the POS system may need to perform authentication. While the POS system can be responsible for generating the image data required for authentication, the authentication platform may reside on a computer server connected to the POS system via a network communication.

[0096] The authentication platform may then receive (i) a vein pattern and (ii) a deformed vein pattern associated with a given individual (step 802). As discussed above, the deformed vein pattern may be associated with a gesture performed by the given individual during the registration phase. Furthermore, the authentication platform may display a notification prompting an unknown person to perform a gesture (step 803). This notification is intended to prompt an unknown person to perform the same gesture as the given individual performed during the registration phase.

[0097] As discussed above, gestures may cause deformation of the anatomical region of interest. When an unknown person makes a gesture, an electronic device can monitor the deformation of the anatomical region. For example, an image sensor of the electronic device can generate image data through observation of the anatomical region, and an authentication platform can acquire this image data for analysis (step 804). In some embodiments, the image data includes digital images generated before, during, or after the deformation of the anatomical region. For example, the electronic device can generate a first series of digital images in a first time interval before deformation occurs, and a second series of digital images in a second time interval while the deformation is "held". Thus, the electronic device can generate digital images when the anatomical region is in its natural state (also known as a "relaxed" state) and deformed state. Typically, the first and second time intervals are long enough that at least one complete heartbeat pulse cycle can be observed. Although the duration of a heartbeat pulse cycle varies depending on various physiological factors, it typically falls within the range of 0.5-2.0 seconds. Therefore, the first and second intervals can be at least 1, 2, or 3 seconds. Optionally, a longer duration can be used to capture more than one heartbeat pulse cycle.

[0098] The authentication platform can then analyze the image data to determine (i) the measured flow pattern and (ii) the measured deformed flow pattern (step 805). To achieve this, the authentication platform can apply a flow measurement algorithm to the image data. When applied to the image data, the flow measurement algorithm can initially perform a registration operation (also known as a “mapping operation”) to determine the pixel locations in the image data corresponding to certain anatomical coordinates in the venogram and deformed venogram. This mapping operation ensures that the values ​​in these datasets are correlated with the same locations in the anatomical region. The flow measurement algorithm can then average the red or green frequency components of the image data across various pixel regions (e.g., 3x3, 6x6, or 9x9 pixel regions). The selected frequency band can roughly correspond to the frequency of the pressure pulses that deliver blood to the anatomical region. However, other frequencies can be used alternatively if appropriate. The averaged red or green frequency components can be calculated for the image data corresponding to different time points, thereby creating a time series specifying the intensity of the frequency band of interest. For example, the flow measurement algorithm can average the red or green frequency components of different digital images (e.g., representing video frames generated by an electronic device). Furthermore, flow measurement algorithms can perform pattern recognition to determine the relative time of a single identifiable phase of a pressure pulse (such as a dicrotic wave) based on the analysis of the average value of a time-varying series of red or green frequency components. After this phase of the pressure pulse has been identified, the flow measurement algorithm can assign time values ​​to some or all pixel regions relative to the earliest detected occurrence of the identified phase of the pressure pulse. In general, these time values ​​can represent flow patterns indicating how blood flows through the vascular distribution of an anatomical region, as determined from the analysis of image data. If the image data is associated with an anatomical region in its natural state, this flow pattern can be referred to as a "measured flow pattern." If the image data is associated with an anatomical region in its deformed state, this flow pattern can be referred to as a "measured deformed flow pattern."

[0099] The authentication platform can then apply the flow prediction algorithm to (i) the measured flow pattern generated for an unknown person, (ii) the venogram of a given individual, and (iii) the deformed venogram of a given individual, in order to generate a predicted deformed flow pattern (step 806). In general, the predicted deformed flow pattern can be a data structure containing time values ​​representing a prediction of how blood might flow through the vascular distribution of a given individual when performing a gesture.

[0100] The authentication platform can then apply the pattern matching algorithm to (i) the measured deformable flow pattern and (ii) the predicted deformable flow pattern to generate a metric indicating similarity (step 807). As discussed above, this metric may be referred to as the “matching score”. In general, this metric can indicate how comparable the measured deformable flow pattern and the predicted deformable flow pattern are based on each value.

[0101] The authentication platform can then determine whether to authenticate the unknown person as a given individual based on the metric (step 808). For example, the authentication platform can apply an authentication algorithm that compares the metric with a predetermined threshold. If the metric exceeds the predetermined threshold, the authentication platform can generate an output indicating that the unknown person should be authenticated as a given individual. However, if the metric does not exceed the predetermined threshold, the authentication platform can generate an output indicating that the unknown person should not be authenticated as a given individual.

[0102] Figure 9 includes a flowchart of another process 900 for determining whether an unknown person is identified as a given individual through vascular studies. Meanwhile, Figure 10 includes a visual illustration of the process by which the authentication platform determines whether to identify an unknown person as a given individual. Initially, the authentication platform may receive input indicating a request to identify an unknown person as a given individual (step 901). Step 901 of Figure 9 may be substantially similar to step 801 of Figure 8. For illustrative purposes, process 900 is described in the case of examining a digital image generated by an electronic device possessed by an unknown person. However, those skilled in the art will recognize that process 900 can be similarly applied to scenarios where an unknown person is near but does not possess an electronic device (e.g., the electronic device is a POS system).

[0103] Subsequently, the authentication platform can obtain digital profiles associated with a given individual claimed by an unknown person (step 902). For example, the authentication platform can access a biometric database that stores digital profiles associated with different individuals, and then the authentication platform can select a digital profile from multiple digital profiles based on input. Typically, the input identifies the given individual claimed by an unknown person (e.g., using a name or identifier such as an email address or phone number), so the authentication platform can simply identify the appropriate digital profile from those digital profiles stored in the biometric database.

[0104] A digital profile may include one or more vascular patterns (also referred to as “vein patterns”) associated with a given individual. In addition to being associated with a given individual, each vascular pattern may also be associated with a given anatomical region. For example, a digital profile may include individual vascular patterns for the face, palm, fingers, etc. Furthermore, a digital profile may include vascular patterns for the same anatomical region in different states. For example, a digital profile may include (i) a first vascular pattern that provides spatial information about the blood vessels in the anatomical region when the anatomical region is in a natural state, and (ii) a second vascular pattern that provides spatial information about the blood vessels in the anatomical region when the anatomical region is in a deformed state (e.g., due to the expression of a gesture).

[0105] Then, the authentication platform can present instructions to the unknown person to perform a gesture that causes deformation of the anatomical area, while the camera of the electronic device is pointed towards the anatomical area (step 903). When the unknown person performs the gesture, the camera can generate a series of digital images. These digital images can be generated rapidly and continuously at a predetermined rhythm (e.g., every 0.1, 0.2, or 0.5 seconds). Alternatively, the camera can generate video of the anatomical area, in which case the digital images can represent frames of the video. In this scenario, the digital images can be generated at a predetermined rate (e.g., 20, 30, or 60 frames per second).

[0106] The authentication platform can then estimate the flow pattern of the unknown person based on the digital images generated by the camera. More specifically, the authentication platform can estimate (i) a first flow pattern of blood when the anatomical region of the unknown person is in a natural state and (ii) a second flow pattern of blood when the anatomical region of the person is in a deformed state (step 904) based on the analysis of the digital images. As discussed above, these flow patterns will be estimated based on different digital images generated by the camera of the electronic device. The first flow pattern can be generated based on the analysis of digital images of the anatomical region in its natural state (e.g., those digital images generated before or after a gesture has been performed), and the second flow pattern can be generated based on the analysis of digital images of the anatomical region in its deformed state (e.g., those digital images generated when a gesture is performed or sustained). As discussed above with respect to FIG8, the first and second flow patterns can be estimated based on a programming analysis of the pixels of the corresponding digital images in order to identify color changes (e.g., on the red or green component) that indicate the flow of blood through the blood vessels in the anatomical region.

[0107] Furthermore, the authentication platform can predict a third flow pattern of blood passing through her anatomical region if a given individual were to perform a gesture, based on a digital profile and a first flow pattern (step 905). As described above, the digital profile may include (i) a first vascular pattern that provides spatial information about the blood vessels in the anatomical region when the given individual's anatomical region is in a natural state, and (ii) a second vascular pattern that provides spatial information about the blood vessels in the anatomical region when the given individual's anatomical region is in a deformed state. By applying an algorithm to the first vascular pattern, the second vascular pattern, and the first flow pattern, the authentication platform can generate a third flow pattern as output. In general, the algorithm can simulate blood flow through blood vessels during anatomical region deformation that may be caused by a gesture.

[0108] The authentication platform can then determine whether to authenticate the unknown person as a given individual based on a comparison of the second and third flow patterns (step 906). For example, suppose the first, second, and third flow patterns are represented as matrices. The first flow pattern can be represented as a first vector or matrix, where each element includes a value indicating the estimated blood flow through the corresponding segment of the unknown person's anatomical region in its natural state. The second flow pattern can be represented as a second vector or matrix, where each element includes a value indicating the estimated blood flow through the corresponding segment of the unknown person's anatomical region in its deformed state. Simultaneously, the third flow pattern can be represented as a third vector or matrix, where each element includes a value indicating the estimated blood flow through the corresponding segment of the given individual's anatomical region in its deformed state. In this case, the authentication platform can apply an algorithm to the second and third vectors or matrices to generate scores indicating the similarity between the second and third flow patterns. The authentication platform can then determine the probability that the unknown person is a given individual based on the scores. Note that the term "matrix," as used herein, can refer to a series of column vectors or row vectors.

[0109] Other steps may also be included. As an example, the authentication platform may generate a signal (e.g., in the form of a message or notification) indicating whether an unknown person has been authenticated as a given individual. The authentication platform may transmit this signal to the source from which it received the authentication request. For example, if a request to authenticate an unknown person is received from a computer program running on a mobile phone, the authentication platform may signal the mobile phone so that the computer program can determine whether to allow the unknown person to perform any task requiring authentication. Similarly, if a request to authenticate an unknown person is received from a POS system during a transaction, the authentication platform may signal the POS system so that the transaction can be completed.

[0110] As discussed above with reference to Figure 8, performing authentication may require the authentication platform to apply a flow prediction algorithm to (i) a flow pattern of measurements associated with an unknown person, (ii) a venogram associated with a given individual, and (iii) a deformed venogram associated with a given individual, to produce a predicted deformed flow pattern. This predicted deformed flow pattern represents the authentication platform's prediction of how blood will flow through the vascular distribution if a given individual were to perform a specific gesture. In some embodiments, the flow prediction algorithm is part of a set of algorithms that collectively define the flow prediction model. Typically, the flow prediction model is a machine learning (ML) or artificial intelligence (AI) model that is "trained" using paradigms to make predictions, i.e., how blood will flow through the vascular distribution when deformed.

[0111] Figure 11 includes a flowchart of a process 1100 for creating a model that is trained to predict blood flow through the vascular distribution of an anatomical region when deformed. As mentioned above, an anatomical region may deform through the expression of a gesture, or it may deform through the application of an external force (e.g., tactile feedback generated by a haptic actuator). The nature of the deformation may depend on the anatomical region. For example, the vascular distribution in the face may be more easily deformed by instructing a person to make an expression (e.g., smiling or frowning), while the vascular distribution in the fingers may be more easily deformed by instructing a person to place their finger on an electronic device and then applying an external force (e.g., via tactile feedback).

[0112] Initially, the authentication platform can identify models to be trained to predict blood flow through the venous network in the anatomical region when deformed (step 1101). Note that the terms "venous network" and "vasculature" are used interchangeably. Therefore, the term "venous network" can refer to the portion of the vasculature system located in the anatomical region. While the anatomical region can be any part of the body where vascular dynamics can be monitored through imaging, common anatomical regions include the fingers, the palmar and dorsal sides of the hand, and the face.

[0113] Next, the authentication platform can acquire (i) a first series of vascular patterns corresponding to an anatomical region in its natural state, (ii) a second series of vascular patterns corresponding to an anatomical region in its deformed state, (iii) a series of flow patterns expressing how blood flows through each vascular pattern in the first series when the anatomical region is in its natural state, and (iv) a series of deformed flow patterns expressing how blood flows through each vascular pattern in the second series when the anatomical region is in its deformed state (step 1102). Each vascular pattern in the first series can indicate the spatial relationship between subcutaneous blood vessels when the anatomical region is in its natural state. Simultaneously, each vascular pattern in the second series can indicate the spatial relationship between subcutaneous blood vessels when the anatomical region is in its deformed state.

[0114] Furthermore, each vascular pattern in the first series can be associated with a corresponding vascular pattern in the second series, and corresponding vascular patterns in the first and second series can be associated with the same individual. Therefore, a single individual can be associated with a vascular pattern in the first series, a vascular pattern in the second series, one flow pattern, and one deformable flow pattern. Typically, each vascular pattern in the first series is associated with a different individual, although the same individual can be associated with multiple vascular patterns in the first series. For example, a single individual can be associated with vascular patterns corresponding to the same anatomical region but generated using image data produced by different electronic devices. Similarly, each vascular pattern in the second series is typically associated with a different individual. However, as described above, each vascular pattern in the first series can be associated with the same individual as the corresponding vascular pattern in the second series.

[0115] Then, the authentication platform can provide (i) the first series of vascular patterns, (ii) the second series of vascular patterns, (iii) the series of flow patterns, and (iv) the series of deformed flow patterns to the model as training data (step 1103). This method, when applied to vascular patterns associated with a person, trains the model to predict blood flow through the venous network in the person's anatomical region. In other words, the authentication platform can provide this information as training data to the model, thereby generating a trained model capable of predicting blood flow. For example, if the authentication platform's task is to predict blood flow through the anatomical region of a given individual, the authentication platform can apply the trained model to a pair of vascular patterns associated with the given individual. The pair of vascular patterns may include one vascular pattern corresponding to the anatomical region in its natural state and another vascular pattern corresponding to the anatomical region in its deformed state. After training is complete, the authentication platform can store the trained model in a biometric database (step 1104). Other considerations and implementation A. Personalized gestures

[0116] As discussed above, vein mapping can play a crucial role in determining whether an unknown person should be authenticated as a given individual. To tailor the authentication process, authentication platforms can design or select variations based on those vein maps.

[0117] For example, suppose an unknown person wishes to authenticate herself as a given individual. As part of the authentication process, the authentication platform can acquire venograms associated with the given individual (e.g., a first venogram of the anatomical region in its natural state and a second venogram of the anatomical region in a deformed state). In this case, the authentication platform can design or select deformations that will better represent or emphasize the unique morphology of these venograms. For example, the authentication platform can analyze some or all of the venograms contained in a biometric database to identify sufficiently unique features. These features may relate to the spatial relationships between different blood vessels (e.g., unusual branching locations or unusual sizes), or they may relate to the vascular properties of the vessels (e.g., if the velocity, volume, or pressure of blood flowing through the venous network changes more or less than the average after deformation).

[0118] Additionally or alternatively, the authentication platform may utilize the system to convey a request to the unknown person to perform a gesture in a manner that presents unique characteristics (or otherwise prompt, stimulate, or induce deformation). For example, the authentication platform may request the unknown person to apply pressure along a location on the palm to inhibit or block blood flow to a specific blood vessel, thereby having a unique effect on the venous resistance of other blood vessels flowing into that specific vessel. The effect of the deformation on the pressure pulse emitted through the anatomical area (and therefore also the visual image data capturing the pressure pulse) may be located at the same location as the deformation, or the effect may be located at a distance from the location of the deformation.

[0119] As discussed above, as part of the certification process, the certification platform can generate measured flow patterns and measured deformed flow patterns. In some embodiments, the certification platform determines the differences between the measured flow patterns and the measured deformed flow patterns, and then compares these differences with other paradigms to ensure that the variations in the pattern data generated by the deformation are also sufficiently unique. B. Measured Flow Pattern Matching

[0120] After the measured flow pattern and the measured deformed flow pattern of an unknown person are known, the authentication platform can authenticate the unknown person solely based on the matching of the measured flow patterns, since the correlation with the authentication factors of the original venogram is previously established. This "lightweight" authentication process may only be applicable to certain situations, such as those involving minimally sensitive information or operations. However, if, for example, time or computational resources are limited, this "lightweight" authentication process can be useful for quickly authenticating unknown persons. C. Multiple Deformations

[0121] As discussed above, a given individual can be prompted to perform multiple gestures during the registration phase. This approach offers a significant security advantage because it provides multiple authentication options. If an unknown person seeks to be authenticated as a given individual, the authentication platform can request the unknown person to perform any combination of the gestures performed by the given individual during the registration phase. Therefore, the authentication platform can request the unknown person to perform multiple different gestures during the authentication process, and the authentication platform can authenticate the unknown person as the given individual only if a predetermined percentage of those gestures (e.g., more than 50%, exactly 100%) results in a match with the given individual.

[0122] The authentication platform can also request an unknown person to perform the same gesture multiple times. For example, the authentication platform can request an unknown person to perform a single gesture multiple times during the authentication process, and the authentication platform can authenticate the unknown person as a given individual only if a predetermined percentage of those gestures (e.g., more than 50%, exactly 100%) results in a match with the given individual.

[0123] In embodiments where the authentication platform allows individuals to perform multiple gestures during the registration phase, the authentication platform can manage separate biometric databases for different gestures. For example, the authentication platform can manage a first biometric database including information for a first gesture (e.g., vein patterns and deformed vein patterns), a second biometric database including information for a second gesture, and so on. Alternatively, the authentication platform can store information associated with different gestures in different parts of a single biometric database.

[0124] Furthermore, entries in a biometric database can be associated not only with the name or identifier of the corresponding individual (e.g., email address or phone number), but also with tags that identify corresponding gestures. Thus, different postures (e.g., smiling or frowning) can be associated with different tags that can be attached to entries in a biometric database.

[0125] In some embodiments, appropriate tags are identified based on the analysis of image data used for authentication. For example, if the image data includes digital images of faces, the authentication platform can examine those digital images to determine which gesture is being performed. Automated analysis of image data can be useful in several ways. First, the authentication platform may be able to infer which gesture an unknown person is performing, rather than explicitly instructing the unknown person to perform a gesture. Second, the authentication platform may be able to generate appropriate vein maps to retrieve from a biometric database. For example, if the authentication platform determines that an unknown person is performing a given gesture in a digital image, the authentication platform can retrieve a vein map associated with the given gesture from a biometric database. Benefits of Authentication of Unknown Persons via Ranged Vascular Studies A. Due to aging and environmental changes

[0126] While it is understood that the shape of blood vessels generally does not change, vascular properties, such as flow rate, can be affected by factors such as age and disease. Environmental factors, such as temperature and humidity, can also affect vascular properties. For example, blood vessels may constrict or shrink due to low temperatures. Blood flow can also be affected by physiological factors (e.g., stress or tension) and physiological activities (e.g., exercise).

[0127] Authentication platforms can be designed to be robust to these variations in vascular properties. An important aspect of authentication platforms is their focus on the local spatial properties and directionality of blood flow resulting from deformation. Therefore, the effects of these factors—which often affect the entire body—are usually negligible or manageable (e.g., through modeling). For example, the directional patterns of blood flow through the venous network in anatomical regions due to gestures will be observable in states of tension and relaxation, although the absolute intensity of the signal (e.g., determined through analysis of image data) may differ.

[0128] Variations in global blood flow can introduce some noise into individual measurements. However, this effect has been adequately addressed in recent studies, which have shown that blood flow can still be easily observed after physical activity (e.g., exercise). B. Robustness in challenging scenarios

[0129] Continued research has improved the accuracy and robustness of identifying or monitoring vascular dynamics through the analysis of digital images. There is also increased interest in remote monitoring, particularly in methods utilizing readily available electronic devices such as mobile phones and tablets.

[0130] When changes in the health status of an unknown user affect spatial properties locally (e.g., due to injury, stroke, etc.), the authentication platform can employ modeling techniques to explain these changes. For example, if the authentication platform detects deformation based on analysis of image data related to an unknown person, it can apply an ML-based model designed to adjust the venogram accordingly. Therefore, the authentication platform may be able to intelligently manipulate the venogram to account for changes in an individual's health status after the registration phase has been completed. As another example, if the authentication platform detects a high heart rate based on analysis of image data related to an unknown person, it can apply an ML-based model to determine appropriate adjustments to vascular properties such as flow rate or pressure. However, these types of adjustments are not expected to be widely needed, as spatial information and vascular properties tend to remain fairly consistent over time. Processing System

[0131] FIG12 is a block diagram illustrating an example of a processing system 1200 in which at least some of the operations described herein can be implemented. For example, the components of the processing system 1200 may be mounted on an electronic device including an image sensor. As another example, the components of the processing system 1200 may be mounted on an electronic device including an authentication platform responsible for inspecting image data generated by the image sensor.

[0132] The processing system 1200 may include a processor 1202, main memory 1206, non-volatile memory 1210, a network adapter 1212 (e.g., a network interface), a video display 1218, an input / output device 1220, a control device 1222 (e.g., a keyboard, pointing device, or mechanical input, such as buttons), a drive unit 1224 including storage medium 1226, or a signal generating device 1230 communicatively connected to bus 1216. Bus 1216 is described as an abstraction representing one or more physical buses and / or point-to-point connections connected via appropriate bridges, adapters, or controllers. Therefore, bus 1216 may include system bus, peripheral component interconnect (PCI) bus, PCI-Express bus, HyperTransport bus, industry standard architecture (ISA) bus, small computer system interface (SCSI) bus, universal serial bus (USB), inter-integrated circuit (I2C) bus, or bus conforming to IEEE standard 1394.

[0133] The processing system 1200 may share a computer processor architecture similar to that of a computer server, router, desktop computer, tablet computer, mobile phone, video game console, wearable electronic device (e.g., watch or fitness tracker), network-connected (“smart”) device (e.g., TV home assistant device), augmented or virtual reality system (e.g., head-mounted display), or another electronic device capable of executing a set of instructions (sequential or otherwise) specifying actions to be taken by the processing system 1200.

[0134] Although the main memory 1206, non-volatile memory 1210, and storage medium 1224 are shown as a single medium, the terms "storage medium" and "machine-readable medium" should be understood to include a single medium or multiple media storing one or more sets of instructions 1226. The terms "storage medium" and "machine-readable medium" should also be understood to include any medium capable of storing, encoding, or carrying a set of instructions for execution by the processing system 1200.

[0135] Generally, routines executed to implement embodiments of the present disclosure can be implemented as part of an operating system or a particular application, component, program, object, module, or sequence of instructions (collectively, "computer program"). A computer program typically contains one or more instructions (e.g., instructions 1204, 1208, 1228) set at different times in various memories and storage devices in a computing device. When read and executed by processor 1202, the instructions cause processing system 1200 to perform operations to execute various forms of the present disclosure.

[0136] Although embodiments have been described in the context of full-featured computing devices, those skilled in the art will understand that various embodiments can be distributed as computer products in various forms. This disclosure applies regardless of the specific type of machine or computer-readable media used to actually cause the distribution. Further examples of machine and computer-readable media include recordable media, such as volatile memory devices, non-volatile memory devices 1210, removable disks, hard disk drives, optical discs (e.g., read-only optical disc memory (CD-ROMs) and digital optical discs (DVDs)), cloud-based storage, and transmission media, such as digital and analog communication links.

[0137] The network adapter 1212 enables the processing system 1200 to coordinate data in the network 1214 with entities outside the processing system 1200 through any communication protocol supported by the processing system 1200 and external entities. The network adapter 1212 may include a network adapter card, a wireless network interface card, a switch, a protocol converter, a gateway, a bridge, a hub, a receiver, a repeater, or a transceiver including integrated circuitry (e.g., enabling communication via Bluetooth or Wi-Fi). Note

[0138] For purposes of illustration and description, the foregoing description of various embodiments of the claimed subject matter has been provided. It is not intended to be exhaustive or to limit the claimed subject matter to the precise form disclosed. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to best describe the principles of the invention and its practical application, thereby enabling those skilled in the art to understand the claimed subject matter, the various embodiments, and the various modifications suitable for the particular purpose considered.

[0139] While the embodiments describe certain examples and considered best modes, the technology can be practiced in many ways, however detailed the embodiments may be. Examples may differ considerably in their implementation details, but are still covered by the specification. Specific terms used in describing certain features or manner of the various embodiments should not be construed as implying that the term is redefined herein as limited to any particular characteristic, feature, or manner of the technology associated with that term. In general, the terms used in the following claims should not be construed as limiting the technology to the specific embodiments disclosed in the specification, unless those terms are explicitly defined herein. Therefore, the actual scope of the technology includes not only the disclosed embodiments but also all equivalent ways of implementing or carrying out the embodiments.

[0140] The language used in this specification has been chosen primarily for readability and pedagogical purposes. It may not have been chosen to describe or limit the subject matter of the application. Therefore, the scope of the technology is intended not to be limited by the implementation methods, but rather by the scope of any patent application published based on this invention. Thus, the disclosure of various embodiments is intended to illustrate, and not limit, the scope of the technology as set forth in the following patent application claims. [Simplified Explanation of the Diagram]

[0008] [Figure 1] includes advanced instructions for traditional authentication procedures, in which an unknown person is prompted to show their hand to the blood vessel scanner.

[0009] [Figure 2] illustrates how each heartbeat cycle is displayed as a peak in a photoplethysmogram.

[0010] [Figure 3] includes a high-order representation of the system, which can be used to authenticate the identity of an unknown person whose vasculature is available for imaging.

[0011] [Figure 4] shows an example of an electronic device capable of implementing an authentication platform designed to authenticate the identity of an unknown person based on image data generated by an image sensor.

[0012] [Figure 5] illustrates how the distribution of underlying blood vessels in an anatomical region (here, the face) is altered by the expression of gestures that cause physical deformation of the surrounding tissues.

[0013] [Figures 6A-C] describe several different methods for determining, calculating or otherwise obtaining pulse waves.

[0014] [Figure 7] includes a flowchart of a procedure for authenticating users of an authentication platform based on the analysis of visual evidence of vascular dynamics in an anatomical region.

[0015] [Figure 8] is a flowchart of the process performed by the certification platform during the use phase (also known as the “implementation phase”).

[0016] [Figure 9] includes a flowchart of another process for determining whether an unknown person is identified as a given individual through vascular studies.

[0017] [Figure 10] includes a visual illustration of the process through which the authentication platform determines whether to authenticate an unknown person as a given individual.

[0018] [Figure 11] includes a flowchart of the process for creating a model that is trained to predict blood flow through the distribution of blood vessels in the anatomical region when deformed.

[0019] [Figure 12] is a block diagram illustrating an example of a processing system in which at least some of the operations described herein can be implemented.

[0020] Through a study of the embodiments in conjunction with the drawings, the various features of the technology described herein will become more apparent to those skilled in the art. Embodiments are shown in the drawings by way of example and not limitation. Although various embodiments are illustrated for illustrative purposes, those skilled in the art will recognize that alternative embodiments may be employed without departing from the principles of the technology. Therefore, while specific embodiments are shown in the drawings, various modifications can be made to the technology.

Claims

1. A method for biometric authentication through vascular studies, comprising: The system receives input requesting authentication of a person possessing an electronic device, including a camera; acquires a digital profile associated with a given individual claimed by the person; while the camera of the electronic device is directed toward the person's anatomical region, instructs the person to perform a gesture that deforms the person's anatomical region; based on analysis of the digital image generated by the camera, estimates (i) a first blood flow pattern when the person's anatomical region is in a natural state and (ii) a second blood flow pattern when the person's anatomical region is deformed; based on the digital profile and the first flow pattern, predicts a third blood flow pattern that would be expected through the given individual's anatomical region if the given individual were to perform the gesture; and determines whether to authenticate the person as the given individual based on a comparison of the second and third flow patterns.

2. The method of claim 1, wherein the digital profile includes (i) a first vascular pattern providing spatial information about blood vessels in the anatomical region when the anatomical region is in the natural state and (ii) a second vascular pattern providing spatial information about blood vessels in the anatomical region when the anatomical region is in the deformed state.

3. The method of claim 2, wherein the prediction includes: The algorithm is applied to the first vascular pattern, the second vascular pattern, and the first flow pattern. The algorithm generates the third flow pattern as output by simulating the blood flow through the blood vessels during the deformation of the anatomical region caused by the gesture.

4. The method of claim 1, wherein the estimation includes: These digital images are examined to identify color changes that indicate blood flow through blood vessels in the anatomical region.

5. The method of claim 1, wherein the first flow pattern is represented as a first vector, each element of the first vector including a value indicating estimated blood flow through the corresponding segment of the anatomical region of the person in the natural state; and wherein the second flow pattern is represented as a second vector, each element of the second vector including a value indicating estimated blood flow through the corresponding segment of the anatomical region of the person in the deformed state; and wherein the third flow pattern is represented as a third vector, each element of the third vector including a value indicating estimated blood flow through the corresponding segment of the anatomical region of the given individual in the deformed state.

6. The method of claim 5, wherein the determination includes: The algorithm is applied to the second and third matrices to generate scores that indicate the similarity between the second and third flow patterns; And the probability of determining that person is the given individual based on that score.

7. The method of request item 1, wherein the acquisition includes: Access a biometric database that stores digital profiles associated with different individuals, and select a digital profile from those digital profiles based on the input.

8. The method of request item 7, wherein the input identifies the given individual as claimed by the person.

9. A non-transitory computer-readable recording medium having instructions stored thereon that, when executed by a processor of an electronic device, cause the electronic device to perform operations, including: Identify models to be trained to predict blood flow through the venous network in the anatomical region when deformed; Obtain (i) a first series of vascular patterns corresponding to the anatomical region in its natural state, (ii) a second series of vascular patterns corresponding to the anatomical region in its deformed state, (iii) a series of flow patterns expressing how blood flows through each vascular pattern in the first series when the anatomical region is in its natural state, and (iv) a series of deformed flow patterns expressing how blood flows through each vascular pattern in the second series when the anatomical region is in its deformed state; and provide (i) the first series of vascular patterns, (ii) the second series of vascular patterns, (iii) the series of flow patterns, and (iv) the series of deformed flow patterns to the model as training data to generate a trained model that, when applied to vascular patterns associated with a person, can predict blood flow through the venous network in that person's anatomical region.

10. The non-transitory medium of claim 9, wherein each vascular pattern in the first series is associated with a corresponding vascular pattern in the second series, and wherein the corresponding vascular patterns in the first series and the second series are associated with the same individual.

11. The non-temporary medium of claim 9, wherein each vascular pattern in the first series indicates the spatial relationship between subcutaneous vessels when the anatomical region is in the natural state, and wherein each vascular pattern in the second series indicates the spatial relationship between subcutaneous vessels when the anatomical region is in the deformed state.

12. The non-temporary media as requested in claim 9, wherein each vascular pattern in the first series is associated with a different individual.

13. The non-temporary medium as requested in item 9, wherein the anatomical region is a finger.

14. The non-temporary medium as requested in item 9, wherein the anatomical region is the palmar or dorsal side of the hand.

15. The non-temporary media as requested in item 9, wherein the anatomical region is the face.

16. The non-transitory media as in claim 9, wherein the model includes a neural network with parameters adjusted based on the provided results.

17. A method for biometric authentication via vascular studies, comprising: The notification is displayed, instructing the person to be authenticated to perform a gesture that causes deformation of the person's anatomical area; Acquire digital images of the anatomical region generated by an electronic device when the person performs the gesture; based on the digital images, estimate the characteristics of blood flow through subcutaneous vessels in the anatomical region, wherein the characteristics are deformations of the venous network formed by the subcutaneous vessels caused by the gesture; and determine whether to authenticate the person as the given individual based on a comparison of the estimated characteristics with a profile associated with the given individual.

18. The method of claim 17, wherein the digital images are generated by combining visible light, infrared light or ultraviolet light emitted by the electronic device.

19. The method of claim 17, wherein the characteristic is related to the directionality, velocity, volume, phase, or pressure of blood flowing through the subcutaneous vessels.

Citation Information

Patent Citations

  • Information processing device, information processing method, and program

    CN108885695A

  • Electronic device including contactless palm biometric sensor and related methods

    CN110245548A

  • Biometric authentication device

    US20190370527A1

  • Access control using multi-authentication factors

    US20200272717A1