Mobile phone identity verification method based on DTW algorithm and walking gait data

Abstract

The invention discloses a mobile phone identity verification method based on a DTW algorithm and walking gait data, and the method comprises the steps: pre-collecting the walking gait data of a user for a period of time, carrying out preprocessing, signal segmentation, and cyclic elimination of similar periods, obtaining a plurality of matching templates with weaker similarity, generating a matching template library, acquiring a user walking gait period through a signal segmentation method according to mobile phone acceleration sensor data collected in real time, and finally calculating the similarity between real-time data and samples in a matching template library by the DTW algorithm, so that whether the user identity is legal or not is verified. Matching template samples are large in difference, user gait features can be reflected as comprehensively as possible, meanwhile, a matching template integration method is used for replacing a matching template average value synthesis method, the problems of one-sidedness, complexity and feature data loss of manual sample selection are solved, the recognition accuracy is improved, and the invention has the advantages of being small in calculation amount, high in accuracy and the like. And training samples are few.

Description

technical field [0001] The invention relates to the technical field of mobile phone identity verification, in particular to a mobile phone identity verification method based on DTW algorithm and walking gait data. Background technique [0002] With the continuous upgrading and updating of various hardware carried by smartphones, the built-in sensors of smartphones are also constantly improving. Currently, there are more than ten kinds of sensors such as accelerometers, gyroscopes, magnetometers, and barometers. By analyzing the sensor data, the usage status of the user can be obtained, and the specific behavior or status of the user can be identified, thereby realizing identity verification, which can be applied to various scenarios such as fast unlocking of mobile phones, fast payment, and information protection. [0003] Gait recognition is the recognition of human body identity through the analysis of human or animal gait. It has become an emerging biometric recognition t...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the defects and deficiencies of the above-mentioned manual selection matching template and matching template average value synthesis method, to provide a kind of automatic extraction of walking gait cycle based on DTW algorithm, to optimize the selection of matching template and to improve the accuracy of identity verification based on DTW algorithm In order to solve the one-sidedness and cumbersomeness of manual selection, at the same time, the method of matching template integration is used instead of the method of matching template average value synthesis to solve the problem of feature data loss and improve the recognition accuracy

Images