METHOD AND APPARATUS FOR RECOGNIZING USER BASED ON ON-DEVICE TRAINING

    公开(公告)号:EP3798925A1

    公开(公告)日:2021-03-31

    申请号:EP20192864.5

    申请日:2020-08-26

    IPC分类号: G06N3/04 G06N3/08 G06N3/063

    摘要: 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.

    INPUT DEVICE AND ELECTRONIC DEVICE INCLUDING THE SAME

    公开(公告)号:EP3582086A1

    公开(公告)日:2019-12-18

    申请号:EP19177432.2

    申请日:2019-05-29

    摘要: According to an embodiment, an input device of an electronic device, comprising a guide tube extending in a direction, a shaft mounted to be able to linearly move back and forth in the direction inside the guide tube, a first cam member rotatably mounted on the shaft inside the guide tube, being guided by the guide tube to linearly move along with the shaft in a first interval, and configured to rotate or linearly move about the shaft in a first position off the first interval to at least partially reenter into the first interval, a second cam member rotatably mounted on the shaft inside the guide tube, configured to linearly move in each of the first interval and a second interval adjacent to the first interval and differing from the first interval, and configured rotate and move about the shaft in the first position, a third cam member mounted on the shaft while facing the first cam member with the second cam member disposed the first cam member and the second cam member, the third cam member inside the guide tube and configured to linearly move back and forth along with the shaft, and a sensor module proximate to the first cam member, wherein as the third cam member linearly moves back and forth, the first cam member linearly moves and the second cam member linearly moves, and wherein the sensor module is configured to detect, at least, the first cam member reaching the first position to produce a first input signal.

    METHOD AND APPARATUS WITH BIOMETRIC INFORMATION SPOOF DETECTION

    公开(公告)号:EP4068226A1

    公开(公告)日:2022-10-05

    申请号:EP21215118.7

    申请日:2021-12-16

    IPC分类号: G06V40/40 G06V10/82

    摘要: 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.

    USER INTERFACE PROVIDING METHOD USING PRESSURE INPUT AND ELECTRONIC DEVICE IMPLEMENTING SAME

    公开(公告)号:EP3477455A2

    公开(公告)日:2019-05-01

    申请号:EP17831196.5

    申请日:2017-04-28

    摘要: Various embodiments provide an electronic device and a method therefor, the electronic device comprising a memory for storing instructions which, when executed, cause a processor to: display a user interface on a display; receive, from a touch sensor, first data indicating that an external object touches a part of the display; receive, from a pressure sensor, second data indicating the pressure applied against the display by the external object while the external object touches a part of the display; determine at least one application on the basis of at least a part of the first data; determine a change in the direction of the pressure applied against the display by the external object, on the basis of at least a part of the first data or the second data, wherein the direction is perpendicular to a first direction; and select a function associated with the at least one application on the basis of at least a part of the change, and perform the selected function. Other embodiments are also possible.

    ANTI-SPOOFING METHOD AND APPARATUS
    7.
    发明公开

    公开(公告)号:EP4068222A1

    公开(公告)日:2022-10-05

    申请号:EP22162557.7

    申请日:2022-03-16

    IPC分类号: G06V10/82 G06V40/12 G06K9/62

    摘要: An anti-spoofing method includes detecting first information related to whether the biometric information is forged, based on a first output vector of a first neural network configured to detect whether the biometric information is forged from the input data, extracting an input embedding vector including a feature of biometric information of a user from input data including the biometric information, calculating a similarity value of the input embedding vector based on a fake embedding vector and either one or both of a real embedding vector and an enrollment embedding vector that are provided in advance, calculating a total forgery score based on the similarity value and a second output vector of the first neural network according to whether the first information is detected, and detecting second information related to whether the biometric information is forged, based on the total forgery score.

    METHOD AND APPARATUS THAT DETECTS SPOOFING OF BIOMETRIC INFORMATION

    公开(公告)号:EP4012671A1

    公开(公告)日:2022-06-15

    申请号:EP21194586.0

    申请日:2021-09-02

    IPC分类号: G06V40/12 G06V40/40 G06V10/82

    摘要: A method and apparatus that detects whether biometric information is spoofed is provided. The method receives, from a sensor, first feature information including a static feature associated with biometric information of a user, and a dynamic feature obtained based on images related to the biometric information, detects whether the biometric information is spoofed based on a first score calculated based on the first feature information, fuses the first score with a second score calculated based on second feature information extracted from the images, based on a result of the detecting that the biometric information is spoofed based on the first score, and detects that the biometric information is spoofed based on a fused score.

    METHOD AND APPARATUS WITH BIOMETRIC SPOOFING CONSIDERATION

    公开(公告)号:EP4068227A1

    公开(公告)日:2022-10-05

    申请号:EP22162552.8

    申请日:2022-03-16

    摘要: A method and apparatus with spoofing consideration is provided. The method includes implementing convolution block(s) of a machine learning model that determines whether biometric information in an input image is spoofed, including generating a feature map including channels for an input feature map for the input image using convolution layers of a convolution block of the convolution block(s), in response to a total number of input channels of the convolution block and a total number of output channels of the convolution block being different, matching the total number of input channels of the convolution block and the total number of output channels of the convolution block by adding a zero-padding channel to the input feature map using a skip connection structure, and generating output data for determining whether the biometric information is spoofed, dependent on the generated feature map and a result of the skip connection structure.