Identity recognition method and device based on brain electrical signals

Abstract

The embodiment of the invention relates to an identity recognition method and device based on brain electrical signals. The method includes the steps of determining a target stimulus frequency sequence, displaying n segments of stimulus signals corresponding to the target stimulus frequency sequence for a to-be-tested user; obtaining n segments of steady sate visual evoked potential (SSVEP) signals generated by the n segments of the stimulus signals; when the similarity between n segments of the SSVEP signals and n segments of preset SSVEP signals is greater than or equal to a threshold value, determining that the identity of the to-be-tested user is correct; if not, determining that the identity of the to-be-tested user is wrong. According to the identity recognition method and device based on the brain electrical signals, identity recognition is conducted through the SSVEP signals; compared with existing brain electrical identity recognition methods, stimulus duration can be shortened, signal features are more stable, an identity recognition system constructed on the basis of the identity recognition method and device is higher in confidentiality and uneasy to duplicate and counterfeit.

Description

technical field [0001] The invention relates to the field of information technology, and relates to a method and device for identification based on electroencephalogram signals. Background technique [0002] In the era of interconnection of all things, due to the exponential growth of the number of connected smart devices, the issue of information security has become particularly important. In the field of information security, identification is a widely used technology. As information security issues become more and more important, the research on various identification methods is also becoming a research hotspot. [0003] Traditional identification methods are generally realized by means of items or information passwords such as keys, identity documents, user names, and passwords. However, this traditional identification method is very easy to be stolen, lost or forgotten, and cannot fully meet people's expectations and requirements. So people began to resort to the use...

AI Technical Summary

Problems solved by technology

[0006] However, the signal-to-noise ratio of the EEG signals used above is generally relatively low, and the signal characteristics are not stable enough. Usually, it is necessary to collect EEG signals from multiple leads and a large number of training samples, which is not convenient to use.

For example, in the identification method based on resting EEG, the spontaneous EEG in the resting state is highly non-stationary, and is also easily affected by the state of the individual, and the variability within the individual is large; and during the test, the user generally needs Multiple electrodes covering the whole brain collect EEG signals, which is inconvenient for users

Another example is the EEG identification method based on P300 event-related potentials. The signal-to-noise ratio of P300 event-related potentials is very low, and a large number of repeated stimulations are required to be superimposed and averaged to obtain a stable waveform. The authentication takes a long time and is inconvenient to use; Moreover, P300 event-related potentials are involved in the advanced cognitive functions of people, and are mostly induced by novel stimuli, which are easily affected by the mental state of the user. Long-term stimulation will cause users to have adaptive responses, resulting in the attenuation of the induced P300 event-related potentials. , which is not conducive to the extraction of signal features, and the reliability is poor

Images