Method and device for identity authentication, terminal and storage medium

Abstract

The invention discloses a method and device for identity authentication, a terminal and a storage medium. The method comprises: collecting time domain gait data of a target user based on a sensor in amobile terminal, and extracting the time domain gait data by using the periodic algorithm to obtain time domain gait data of each period as first gait data; performing coordinate transformation on the first gait data to obtain second gait data, converting the second gait data into frequency domain gait information and obtaining a feature sequence corresponding to the target user based on a pre-trained feature generation model; and entering the feature sequence of the target user into a single classification model corresponding to the target user, and passing the authentication when the data output by the single classification model is first preset data. The technical scheme of the embodiment of the invention realizes the technical effect of improvement of the accuracy and security of identity authentication by using the user gait information because of the individualization nature of the user gait information.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of security authentication, and in particular, to an identity authentication method, device, terminal, and storage medium. Background technique [0002] The identity authentication method based on gait recognition was first proposed by Gafurov in 2006. Through a large number of repeated experiments, he found the gait similarities between the same users and the differences between different users, and concluded that each user's Gait is unique and can be authenticated by the user's gait. [0003] There are four main types of gait recognition-based methods in the prior art: identity authentication based on machine vision, based on ground sensors, based on wearable sensors or based on sensors set in mobile terminals. Among them, the authentication method based on machine vision is: use a camera to capture a series of gait images of the user during walking, and then use the image matchi...

AI Technical Summary

Problems solved by technology

Among them, the authentication method based on machine vision is: use a camera to capture a series of gait images of the user during walking, and then use the image matching algorithm to realize the user's identity authentication, but this identity authentication method is easily affected by the external environment. Exemplary ones are easily affected by external ambient light, whether there are obstacles, or the shooting distance, so the effect is poor; the authentication method based on the ground sensor is: capture the user's gait through the force sensor set on the floor or in the carpet Features, this authentication method is easily affected by the weight of the items worn by the user, and its application range is small, so it is not universal

The above two methods are to analyze the user's gait data picture from the computer point of view, the cost is high, the identity authentication cannot be performed in real time, and the applicability is not strong

The third method is based on wearable sensors for identity authentication, that is, using acceleration signals to analyze the uniqueness of gait. However, although this method can perform identity authentication in real time, it does not take into account the user's pace in the application process. Changes, the need to wear the sensor during use is cumbersome and complicated, and ignores the individual differences of users, resulting in inaccurate detection of technical problems

Although the fourth embodiment solves the technical problem that identity authentication cannot be performed in real time, it still does not solve the technical problem of poor applicability and low accuracy of identity authentication by detecting the user's gait data through the built-in sensor in the mobile phone

Images