US Patent Application 18355020. USER AUTHENTICATION APPARATUS, USER AUTHENTICATION METHOD AND TRAINING METHOD FOR USER AUTHENTICATION simplified abstract

From WikiPatents
Jump to navigation Jump to search

USER AUTHENTICATION APPARATUS, USER AUTHENTICATION METHOD AND TRAINING METHOD FOR USER AUTHENTICATION

Organization Name

Samsung Electronics Co., Ltd.


Inventor(s)

Heewon Kim of Seoul (KR)

Seon Min Rhee of Seoul (KR)

Jihye Kim of Anyang-si (KR)

Ju Hwan Song of Suwon-si (KR)

Jaejoon Han of Seoul (KR)

USER AUTHENTICATION APPARATUS, USER AUTHENTICATION METHOD AND TRAINING METHOD FOR USER AUTHENTICATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18355020 titled 'USER AUTHENTICATION APPARATUS, USER AUTHENTICATION METHOD AND TRAINING METHOD FOR USER AUTHENTICATION

Simplified Explanation

- The patent application describes a method and apparatus for user authentication using a frontalized face image. - The method involves acquiring an input image of the user's face and calculating a confidence map with confidence values for authenticating the user. - The confidence map is generated by comparing the input image with a depth image of the user's frontalized face. - A second feature vector is extracted from a second image generated using the input image and the confidence map. - A first feature vector is obtained from an enrolled image of the user. - The user authentication is performed by correlating the first feature vector with the second feature vector.


Original Abstract Submitted

A user authentication method and a user authentication apparatus acquire an input image including a frontalized face of a user, calculate a confidence map including confidence values, for authenticating the user, corresponding to pixels with values maintained in a depth image of the frontalized face of the user among pixels included in the input image, extract a second feature vector from a second image generated based on the input image and the confidence map, acquire a first feature vector corresponding to an enrolled image, and perform authentication of the user based on a correlation between the first feature vector and the second feature vector.