Identity recognition method and system based on electroencephalogram continuous action imagination normal form

Abstract

The invention discloses an identity recognition method and system based on an electroencephalogram continuous action imagination normal form. The method comprises the steps that electroencephalogram signals generated when a user performs motor imagination are collected; preprocessing the electroencephalogram signals to realize denoising of the electroencephalogram signals; performing feature extraction on the de-noised electroencephalogram signals; matching the features of the user with a preset electroencephalogram signal feature data set, and judging whether user identity recognition succeeds or not according to a matching result; the electroencephalogram signal feature data set comprises features corresponding to electroencephalogram signals when the registered user performs motor imagery. Compared with a traditional password / recruitment identity recognition method, the method can effectively overcome the inherent defects of easy forgetting and easy stealing, and meanwhile, compared with biological identity recognition, the method has the advantages of replaceability, canceling and resetting; the method is suitable for identity recognition of people with visual and auditory impairment, has the advantage of good universality, and enables the application of identity recognition to be more complete.

Description

technical field [0001] The invention belongs to the identification technology, and in particular relates to an identification method and system based on an electroencephalogram continuous action imagination paradigm. Background technique [0002] With the development of society and the improvement of people's living standards, people pay more and more attention to the protection of their privacy, and the protection of information is related to everyone's vital interests. However, with the rapid development of the Internet, our personally identifiable information is easily obtained by big data, which brings a certain degree of loss. At present, passwords, PINs, etc. are mostly used to identify identity information, but these methods have shortcomings such as being easy to forget and easy to steal, and cannot be applied to systems with a high security factor. And its own inherent characteristics are difficult to be forgotten and stolen, such as face, fingerprint, iris, voice,...

AI Technical Summary

Problems solved by technology

The environmental stimuli in the existing EEG identification are mostly induced by visual and auditory paradigms, such as the technical solutions disclosed in Chinese patent documents with application numbers 201811436522.0, 201810571367.7, and 201810269849.7, which are not friendly to people with visual and hearing impairments. Poor replaceability and diversity; while active cognition and motor imagery are mostly in the form of discrete sequences, the tasks are simple but the accuracy is low and the time required is long, which cannot meet the needs of practical applications

Moreover, the feature extraction and matching of EEG signals are not strict at present. If the identity verification failure is judged as successful, it will lead to extremely serious consequences.

Images