The present disclosure generally pertains to image processing circuitry configured to: obtain biometric feature data being indicative of at least one biometric feature of a user of an imaging device; obtain image data from the imaging device used by the user; and associate the biometric feature data with the image data for verifying the user.

Biometric data are obtained from biometric sensors on a stand-alone computing device, which may contain an ASIC, connected to or incorporated within it. The computing device and ASIC, in combination or individually, capture biometric samples, extract biometric features and match them to one or more locally stored, encrypted templates. The biometric matching may be enhanced by the use of an entered PIN. The biometric templates and other sensitive data at rest are encrypted using hardware elements of the computing device and ASIC, and/or a PIN hash. A stored obfuscated Password is de-obfuscated and may be released to the authentication mechanism in response to successfully decrypted templates and matching biometric samples. A different de-obfuscated password may be released to authenticate the user to a remote or local computer and to encrypt data in transit. This eliminates the need for the user to remember and enter complex passwords on the device.

A device for biometric recognition, a method for biometric recognition and a method for registering a biometric template are disclosed herein. The device for biometric recognition, comprises: a sensor configured to sense biometric information of a biometric feature; a microprocessor configured to obtain the biometric information from the sensor and perform image preprocessing and feature extraction on the obtained biometric information, in order to obtain biometric data; and a security chip configured to store a biometric template, compare the obtained biometric data with the stored biometric template, in order to determine a biometric recognition result. Compared to conventional and logical isolating solutions, the embodiments of the present disclosure improves the security of biometric recognition.

An encoding method and system for a fingerprint of thing according to the present application is disclosed. Based on images of human fingerprints, at least one characteristic of fingerprint is provided on at least friction ridge lines so as to enable the encodement in the form of numbers and/or alphabets, and thereby a fingerprint image including the specific information are formed and can be used for labelling products with codes. The fingerprint image includes the specific information of a thing, and when attached onto said thing, is also unique similar to a fingerprint of an individual. Such fingerprint image for representing the specific identification information of a thing using minutia of finger can be referred to as fingerprint of thing (FOT). The fingerprint of thing, as a wholly new two-dimensional code which is generated based on images of human fingerprints, includes the more information than that of a one-dimensional barcode, and can be used for represent the information which cannot be represented by a one-dimensional barcode and will be too complicated for a two-dimensional barcode to represent. With an encoding method and system according to the present application, a fingerprint of thing including the unique identification information can be printed or carved onto every product, and can keep unchanged similar to a human fingerprint and can be readily used for query.

A network node is configured to enable authentication of a user of a client device based on biometric data captured by the client device. The network node receives, from the client device, a request to authenticate a user that includes a first set of transformed biometric data transformed with a first secret feature transform key shared with the client device; fetches, from a secure end-user repository, a second set of enrolled transformed biometric data associated with the first set of transformed biometric data and a second secret feature transform key with which the second set of biometric data was transformed at enrolment of the transformed biometric data; and submits the second set of transformed biometric data and the second secret feature transform key over a secure communication channel to the client device.

An electronic device for de-identifying dynamic biometric data of a user and an operation method thereof are disclosed. The method includes the operations of obtaining dynamic biometric data regarding a movement of a user; de-identifying the dynamic biometric data by distorting the dynamic biometric data; and transmitting the de-identified dynamic biometric data to a server.

The present disclosure generally relates to a method for authenticating a user by means of an electronic device, where the electronic device comprises a first and a second control unit adapted to process a biometric representation from a biometric sensor. Preferably, the second control unit comprises a secure element and/or a secure block adapted to provide a secure processing environment. The present disclosure also relates to a corresponding electronic device and to a computer program product.

A method is provided for operating a storage device having biometric security protection, including: simultaneously starting both a device initialization operation and a biometric recognition operation; and if the device initialization operation has completed and the biometric recognition operation has successfully completed, setting the storage device to a normal access mode permitting external access to the storage device in accordance with the biometric security protection, wherein the device initialization operation and the biometric recognition operation are performed concurrently.

Systems, methods, and non-transitory computer-readable media can be configured to train a featurizer based at least in part on a set of training data. The featurizer can be applied to at least one input to generate at least one tensor. The at least one tensor obfuscates or excludes at least one feature in the at least one input.

Image data is run through a neural network, and the neural network produces a vector representation of the image data. Random sparse sampling masks are created. The vector representation of the image data is masked with each of the random sparse sampling masks, the masking generating corresponding sparsely sampled vectors. The sparsely sampled vectors are transmitted to nodes of a consensus network, wherein a sparsely sampled vector of the sparsely sampled vectors is transmitted to a node of the consensus network. Votes from the nodes of the consensus network are received. Whether a consensus is achieved in the votes is determined. Responsive to determining that the consensus is achieved, at least one of identification and verification of the image data may be provided.