Abstract:
A method of preprocessing an image including biological information is disclosed, in which an image preprocessor may set an edge line in an input image including biological information, calculate an energy value corresponding to the edge line, and adaptively crop the input image based on the energy value.
Abstract:
A fingerprint recognition method includes receiving an input partial image corresponding to a partial image of a fingerprint of a first user; partitioning the input partial image into a plurality of blocks; performing a comparison operation based on the plurality of blocks and the enrolled partial images corresponding to partial images of an enrolled fingerprint; and recognizing the fingerprint of the first user based on a result of the comparison operation.
Abstract:
An ultrasound imaging apparatus includes an ultrasonic probe configured to transmit an ultrasound to an object, receive an echo signal reflected from the object, and output the echo signal; a quality determiner configured to receive the echo signals and determine quality of voxels of a three-dimensional (3D) volume of the object to be rendered based on observation information of the 3D volume; and a beamformer configured to perform beamforming on the echo signal based on the quality of the voxels to generate an output signal.
Abstract:
A processor-implemented method with image preprocessing includes: transforming a fingerprint image into a frequency domain; suppressing a low-frequency region corresponding to a first noise component of the fingerprint image in the frequency domain; and restoring the frequency domain, in which the low-frequency region is suppressed, as an image.
Abstract:
A method with biometric information spoof detection includes extracting an embedding vector from an intermediate layer of a neural network configured to detect whether biometric information of a user is spoofed from an image including the biometric information; detecting first information regarding whether the biometric information is spoofed, based on the embedding vector; and detecting second information regarding whether the biometric information is spoofed based on whether the first information is detected, using an output vector output from an output layer of the neural network.
Abstract:
A processor-implemented method includes: obtaining an input embedding vector corresponding to an input fingerprint image for authentication; determining a confidence value of the input embedding vector based on fingerprint data of an initial model including either one or both of a trained real fingerprint determination model and a trained fake fingerprint determination model that are provided in advance; and updating the initial model based on the input embedding vector, in response to the confidence value being greater than or equal to a first threshold.
Abstract:
A processor-implemented anti-spoofing method includes: extracting an input embedding vector from input biometric information; obtaining a fake embedding vector of a predetermined fake model based on fake biometric information; obtaining either one or both of a real embedding vector of a predetermined real model and an enrolled embedding vector of an enrollment model the enrollment model being generated based on biometric information of an enrolled user; determining a confidence value of the input embedding vector based on the fake embedding vector and either one or both of the real embedding vector and the enrolled embedding vector; and determining whether the input biometric information is forged, based on the confidence value.
Abstract:
An electronic device is disclosed. The disclosed electronic device comprises: a touch screen display structure; a first wireless communication circuit; a second wireless communication circuit; a stylus pen including at least one button which can be pressed or touched; a processor operationally connected to the touch screen display structure and the first wireless communication circuit; and a memory operationally connected to the processor. A first application program including a first user interface, and a second application program including a second user interface are stored in the memory. The memory has instructions stored therein which are configured to cause, when executed, the processor to: execute the first application program and second application program when a user input is received; display at least one of the first user interface and second user interface by means of the touch screen display structure; receive a first signal, which is generated by the press or touch of the button for a first time period, from the stylus pen through the first wireless communication circuit; select one from the first application program and second application program on the basis of the first signal; change at least part of information displayed on the screen, at least partly on the basis of the selection; receive a second signal, which is generated by the press or touch of the button for a second time period different from the first time period, from the stylus pen through the first wireless communication circuit; and at least partly on the basis of the selection, perform a function of the first application program or a function of the second application program in response to the second signal. Various other embodiments are possible.
Abstract:
An on-device training-based user recognition method includes performing on-device training on a feature extractor based on reference data corresponding to generalized users and user data, determining a registration feature vector based on an output from the feature extractor in response to the input of the user data, determining a test feature vector based on an output from the feature extractor in response to an input of test data, and performing user recognition on a test user based on a result of comparing the registration feature vector to the test feature vector.
Abstract:
A processor fingerprint enrollment method and apparatus is disclosed. A processor implemented fingerprint enrollment method includes performing a matching between a received input fingerprint image of a user and one or more enrolled fingerprint images, and selectively, based on a result of the matching identifying a matched enrolled fingerprint image from the one or more enrolled fingerprint image and based on a calculated degree of diversity in the fingerprint corresponding to an overlapping region between the input fingerprint image and the matched enrolled fingerprint image, storing the input fingerprint as another enrolled fingerprint image.