A method for biometrics spoofing detection according to an embodiment of the present disclosure includes receiving a biometric authentication request from an application, acquiring biometrics at a sensor, and applying a machine learning-based anti-spoofing scheme to the biometrics based on an authentication purpose of the biometrics. The anti-spoofing scheme for biometrics of the present disclosure may include a deep neural network generated by machine learning, and may be used in an Internet of Things environment using a 5G network.

A method for identifying a user using an image of an object of the user, the method comprising: obtaining, by an optical sensor of a mobile device, the image of the object, wherein the object comprises a biometric characteristic of the user; providing the image to a neural network; processing the image by the neural network to identify-a position of the object and the object in the image; extracting, from the identified object, the biometric characteristic; storing the biometric characteristic in a storage devices and providing at least the biometric characteristic as input to an identification means to determine whether the biometric characteristic identifies the user.

An authentication method implemented by a computer, the authentication method including: extracting a feature amount of each of a plurality of feature points of a living body from imaged data of the living body; calculating a similarity between the feature amount of each of the plurality of feature points and a feature amount stored in a storage unit in association with a feature point that corresponds to each of the plurality of feature points; referring to the storage unit that stores weight information that indicates a weight to be applied to a similarity in association with the similarity to acquire the weight information associated with the calculated similarity; and executing authentication processing on the living body based on a similarity that is newly generated by applying the acquired weight information to the calculated similarity.

A method may involve obtaining a latent fingerprint on a surface, storing the latent fingerprint, obtaining a live fingerprint on the surface, and authenticating the live fingerprint based in part on the stored latent fingerprint and in part on previously-authenticated fingerprint data. The method may involve rejecting authentication of the live fingerprint as a potential spoof, if the live fingerprint matches the latent fingerprint under a relatively strict correlation test. The method may also involve, when the live fingerprint doesn’t closely match the latent fingerprint, granting authentication of the live fingerprint if the live fingerprint matches the previously-authenticated fingerprint data under a relatively loose correlation test.

A method for detecting spoof fingerprints with an under-display fingerprint sensor includes illuminating, with incident light emitted from a display, a target region of a fingerprint sample disposed on a top surface of the display; detecting a first scattered signal from the fingerprint sample with a first image sensor region of an image sensor located beneath the display, the first image sensor region not directly beneath the target region, the first scattered signal including a first portion of the incident light scattered by the target region; determining a scattered light distribution based at least in part on the first scattered signal; and identifying spoof fingerprints based at least in part on the scattered light distribution.

A circuit, system, and method for measuring or detecting pressure or force of a fingerprint on an array of electrodes is described. Pressure or force may be measured or detected using a processed image of the fingerprint, or by measurement of capacitance of deformed variable capacitors.

An under-screen fingerprint sensing device and a fingerprint sensing method are provided. The under-screen fingerprint sensing device includes a fingerprint sensor and a processor. When the fingerprint sensor senses a target object, a first color pixel, a second color pixel, and a third color pixel of the fingerprint sensor respectively output a first color original value, a second color original value, and a third color original value. The processor performs FFC on the first color original value, the second color original value, and the third color original value respectively to generate a first color correction value, a second color correction value, and a third color correction value. The processor determines whether the target object is a real finger according to the first color correction value, the second color correction value, and the third color correction value.

A computer-implemented method for identifying a user, the method using a computing device comprising an illumination source that, when activated, emits visible light, the method comprising taking two images of a scene potentially comprising a living body part carrying a biometric characteristic, wherein a first image is taken without the illumination source being activated and the second image is taken with the illumination source being activated, transferring the first image and the second image to a neural network and processing, by the neural network the first image and the second image, wherein the processing comprises comparing the first image and the second image, thereby determining whether the first image and the second image are images of a living body part, the method further comprising, if it is determined that the first image and the second image are images of a living body part, performing an identification algorithm to find a biometric characteristic for identifying the user and, if it is determined that the first image and the second image are not images of a living body part, not performing the identification algorithm.

Certain aspects of the present disclosure provide techniques and apparatus for biometric authentication using neural-network-based anti-spoofing protection mechanisms. An example method generally includes receiving an image of a biometric data source for a user; extracting, through a first artificial neural network, features for at least the received image; combining the extracted features for the at least the received image and a combined feature representation of a plurality of enrollment biometric data source images; determining, using the combined extracted features for the at least the received image and the combined feature representation as input into a second artificial neural network, whether the received image of the biometric data source for the user is from a real biometric data source or a copy of the real biometric data source; and taking one or more actions to allow or deny the user access to a protected resource based on the determination.

In some embodiments, there is provided a system for generating synthetic human fingerprints. The system includes at least one processor and at least one memory storing instructions which when executed by the at least one processor causes operations, such as receiving, from a database and/or a sensor, at least one real fingerprint; training, based on the at least one real fingerprint, a generative adversarial network to learn a distribution of real fingerprints; training a super-resolution engine to learn to transform low resolution synthetic fingerprints to high-resolution fingerprints; providing to the trained super resolution engine at least one low resolution synthetic fingerprint that is generated as an output by the trained generative adversarial network; and in response to the providing, outputting, by trained super resolution engine, at least one high resolution synthetic fingerprint.