Electrocardiogram (ECG) signal based identity authentication method and system

Abstract

The invention discloses an electrocardiogram (ECG) signal based identity authentication method, including a registration link and an authentication link, wherein the registration link includes the following steps: pre-storing a negative sample, pre-processing an ECG signal that is used as the negative sample, collecting a user template ECG signal, detecting the location of R waves, intercepting QTwaves, generating sparse feature templates from the intercepted QT waves by using a differential dictionary learning algorithm for sparse representation, and then evaluating an optimal sparse featuretemplate, and searching an optimal threshold; the authentication link includes the following steps: generating sparse features by using the pre-processed ECG signal, and then performing preliminary authentication based on the optimal threshold, and completing the authentication based on maximum entropy voting; and if remote identity authentication is performed, the method also includes the step of compressing data and transmitting the data to a remote authentication unit before the preliminary authentication. The ECG signal based identity authentication method disclosed by the invention is particularly suitable for the application of real-time authentication of ECG identities in remote dynamic medical treatment, and solves the problem of efficient and real-time identity authentication.

Description

technical field [0001] The invention relates to the field of identity authentication, in particular to an identity authentication method and system based on electrocardiographic signals. Background technique [0002] With the continuous development of remote mobile medical technology, the real-time unique authentication of user identity and diagnosis doctor identity is becoming more and more important. Biometric identification is based on the habit of biological behavior or individual biological characteristics, and automatically realizes the identification and authentication of individual identities. Traditionally more mature fingerprint, iris, voice, face and other technologies with better biological characteristics include: fingerprints, palm prints, ears, etc. However, factors such as large amount of data, complex calculations, easy acquisition and imitation, and high requirements for collection methods or collection environments limit the application of traditional bio...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problem that the identity authentication method based on the electrocardiogram signal is difficult to meet the high-efficiency requirements, and the technical problem that the identity authentication is difficult to realize real-time identity authentication, the present invention proposes an identity authentication method and system based on the electrocardiogram signal

Images