CN101828921A - Identity identification method based on visual evoked potential (VEP) - Google Patents
Identity identification method based on visual evoked potential (VEP) Download PDFInfo
- Publication number
- CN101828921A CN101828921A CN201010199826A CN201010199826A CN101828921A CN 101828921 A CN101828921 A CN 101828921A CN 201010199826 A CN201010199826 A CN 201010199826A CN 201010199826 A CN201010199826 A CN 201010199826A CN 101828921 A CN101828921 A CN 101828921A
- Authority
- CN
- China
- Prior art keywords
- error
- wave band
- vep
- evoked potential
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention belongs to the field of brain electricity and identity identification, providing an identity identification method which can effectively describe the components of the characteristic of the brain electricity and can achieve the requirement for improving the identification rate. The technical scheme is that the identity identification method based on visual evoked potential (VEP) comprises the following steps of: applying some image stimulation to a subject; selecting a proper scalp leading electrode to capture the visual evoked potential of the subject; preprocessing an original brain electricity signal in a de-noising way; extracting a gamma wave band power spectrum to be taken as the characteristic of the brain electricity to be researched; processing the characteristic of the brain electricity with Fisher linear discrimination; and studying and testing the optimized characteristic parameter in a classifying way through a BP neural network to realize the identity identification. The method is mainly applied to the identity identification.
Description
Technical field
The present invention relates to brain electricity and identification field, specifically relate to personal identification method based on visual evoked potential (VEP).
Background technology
Living things feature recognition is by various high-tech information detection meanss, utilizes human body inherent physiology of institute or behavior characteristics to carry out the personal identification evaluation.Biological characteristic mainly comprises two kinds of physiological feature and behavior characteristicss: physiological feature is meant inherent, and geneogenous human body physical features is as fingerprint, iris, palm shape, people's face etc.; Behavior characteristics is meant the feature that extracts from the performed motion of people, mostly be posteriority, as person's handwriting, keystroke, gait etc.In the MIT of calendar year 2001 Technology Review magazine, biometrics identification technology is listed in one of 10 most possible technology that change the world.And estimate that in the near future, the biological identification technology will be deep into the every aspect of our life, its combined influence power will be not second to the Internet.
From the information science angle, living things feature recognition belongs to traditional pattern recognition problem, and it does not rely on various synthetical and additional article, identification be people itself.Everyone biological characteristic has uniqueness different with other people and constant over a period to come stability, is difficult for forging and personation, so utilize biological identification technology to carry out the identity identification, has advantages such as safe, reliable, accurate.
Yet not having a kind of biological characteristic is that perfectly the recognition method of various biological characteristics all has its certain scope of application and requirement, and single living creature characteristic recognition system shows limitation separately in actual applications.Use first generation biological identification technologies such as wider fingerprint, people's face, iris and the identification of palm shape, need the cooperation of monitored target mostly, sometimes even need monitored target to finish necessary operation could to realize.These ways are more loaded down with trivial details, and recognition speed is slow and use inconvenience, and is not susceptible to user acceptance.But the reliability of fingerprint recognition contacts than the higher actual physical that needs; People's face does not need physics to contact with iris identification, yet but is subjected to more environmental limitations when practical application.Studies show that, the prosthetic finger made from the gelatin fingerprint recognition system of just can out-tricking easily, suffering from cataractous human iris can change, and a false eye iris feature that etches on contact lens also can allow iris authentication system hard to tell whether it is true or false or the like.Along with continuous intellectuality, the technicalization of means of crime, first generation identity recognizing technology will face false proof, antitheft challenge.Therefore the proposition of the biological authentication method that exigence is new.
Than traditional living things feature recognition method, (Electroencephalogram, identification EEG) is a kind of newer thinking based on the brain electricity.In fact, as far back as nineteen sixty, neurophysiologist and psychiatrist just propose and have verified the judgement of " having certain dependency between people's EEG signals and the gene information of carrying ".Yet pathological analysis and clinical diagnosis are devoted in early stage major part research more; Up in recent years, researcheres are just put into healthy human body with more energy, attempt to set up certain individual brain electrical feature and the one-to-one relationship between its genes carried information, thereby the brain electricity is used for identification as a kind of effective feature, open the new approaches in this field.
Should meet the following requirements at least as a kind of effective biological characteristic: 1) universality; 2) uniqueness; 3) stability; 4) can adopt polarity.In addition, brain electricity (EEG) also has other significantly and special advantages is embodied in:
(1) because the brain electricity derives from the thinking activities of brain, be difficult to reappear, thereby be not easy to be replicated or to copy at pressure or under coercing, system robustness is strong.
(2) the brain electricity has the individual dependency of height.In same thing of thinking, different individualities also can produce different EEG signals for same outside stimulus or main body.
(3) the brain electricity is present in each live body with physiological function, and impaired probability is very little, and is relatively stable.By comparison, some traditional biological characteristic (as fingerprint or sound) may be owing to accidental injury (as the skin burn of hand or cry out) and the recognition function that forfeiture itself has.
(4) the brain electricity has and only exists in live body, so can only be used for the detection at body, is difficult to more duplicate and forge with respect to external features such as fingerprints.
At present, the identity recognizing technology based on EEG signals all belongs to the starting stage at home and abroad.1999, people such as M.Poulos propose the imagination that the brain electricity is used for identification first, and set up AR (Auto-Regressive) model and extract brain electrical feature parameter, by the method for study vector quantization (LVQ) 4 samples are classified, reached the recognition result of 72%-84%.
Summary of the invention
For overcoming the deficiencies in the prior art, a kind of personal identification method based on visual evoked potential (VEP) is provided, brain electrical feature composition can be described more effectively, reach the requirement that improves discrimination, the technical scheme that the present invention takes is, personal identification method based on visual evoked potential (VEP), comprise the following steps: that the experimenter is applied certain image to be stimulated, select suitable scalp crosslinking electrode to gather experimenter's vision inducting brain, after original EEG signals carried out the denoising pretreatment, extract the power spectrum of γ wave band and study as the brain electrical feature; Utilize the Fisher linear discriminant that the brain electrical feature is handled subsequently; By the BP neutral net optimized characteristic parameter is carried out classification learning and test at last, to realize the identification of identity.
The extraction that the power spectrum of described extraction γ wave band is studied the midbrain electrical feature as the brain electrical feature is based on Pa Sewaer Parseval T/F theorem, calculates the γ wave band power spectrum of each passage respectively, and computing formula is as follows:
GBP is the abbreviation of Gamma Band Power, the energy of expression γ wave band, wherein,
Be the γ wave band EEG signals behind each channel filtering, N is the data sum after each channel filtering and the normalization;
And then each passage GBP carried out normalization, eliminate data difference:
NGBP is the abbreviation of Normalised Gamma Band Power, expression normalization γ wave band spectrum energy.
The core of described BP neutral net is by propagated error backward on one side, the mode of round-off error is constantly adjusted the network parameter that comprises weights, threshold value forward on one side, to realize or to approach desirable input and output vector correlation, calculating is all propagated in each training twice:
1) forward calculation---begin successively to calculate backward output from input layer, produce finally and export, and calculate the actual error of exporting with target of exporting;
2) backwards calculation---begin forward propagated error signal successively from output layer, revise weights, up to error less than given threshold value,
For n input learning sample a
1, a
2, a
n, the known output sample corresponding with it is A
1, A
2... A
qThe destination of study is the actual output C with network
1, C
2... C
qWith target vector A
1, A
2... A
qBetween error revise weights, make A
1(1=1,2 ..., q) with the C that expects
1Approaching as much as possible, even the error sum of squares of network output layer arrives minimum greatly, be by the continuously variation of computing network weights and deviation and approach target gradually on the direction that descends with respect to the error function slope, the variation of weights and deviation each time all is directly proportional with the influence of network error, and is delivered to each layer in the mode of back propagation.
Take the way of K folding cross validation to come the identification ability of test b P neutral net: data set is divided into the K equal portions, in turn will wherein (K-1) part as training data, 1 part as test data, test, each test all can draw corresponding accuracy, and K the meansigma methods conduct of accuracy as a result is to the estimation of arithmetic accuracy.
Its characteristics of the present invention are:
1, because the present invention adopts the feature extracting method based on γ wave band power spectrum, can describe brain electrical feature composition more effectively, have very high accuracy of identification;
2, because the present invention adopts signal post-processing, based on the identity recognizing technology of BP neutral net, thereby the present invention has the measurement accuracy height, is difficult to duplicate;
3, based on the personal identification method of vision inducting brain electricity, be to traditional brain electricity application, as the expansion of brain-computer interface technology, also open new thinking for living things feature recognition.
Description of drawings
Fig. 1 the technology of the present invention flow chart.
The picture example of Fig. 2 Snodgrass and Vanderwart picture library.
Fig. 3 tests the sequential setting.
Fig. 4 electrode modes of emplacement.
Fig. 5 Fisher linear discriminant sketch map.
Fig. 6 BP network topology structure
The specific embodiment
Adopt resting electroencephalogramidentification different with early stage research, the present invention is based on vision inducting brain electricity (VEP) more.(Visual Evoked Potential is to be subjected to the evoked brain potential signal that certain special visual stimulus was produced when (as observing picture) as the experimenter VEP) to visual evoked potential.Studies show that the VEP of γ wave band (30-50Hz) is and higher brain function activity, and is closely-related as memory, cognition etc.Because memory, cognitive level are embodying individual variation usually, thereby can carry out identification with the VEP signal of this wave band.
The present invention proposes the method that a kind of vision inducting brain electricity (VEP) of the γ of utilization wave band carries out identification, involved key technology comprises: the collection of EEG signals, signal processing, feature extraction and Classification and Identification etc.Its techniqueflow is: the experimenter is applied certain image to be stimulated, and selects suitable scalp crosslinking electrode to gather experimenter's vision inducting brain electricity, original EEG signals is carried out pretreatment such as denoising after, the power spectrum of extraction γ wave band is studied as the brain electrical feature; Utilize the Fisher linear discriminant that the brain electrical feature is handled subsequently, when effectively reducing the characteristic vector dimension, improved recognition efficiency; By the BP neutral net optimized characteristic parameter is carried out classification learning and test at last, to realize the identification of identity.Than other biometrics identification technology, based on the identification thinking novelty of brain electricity, have uniqueness and significant advantage, be breakthrough to traditional EEG research, also provide new approaches for exploring more polynary effectively personal identification method from now on.
Personal identification method based on the brain electricity comprises following basic step: eeg signal acquisition, Signal Pretreatment, feature extraction, signal post-processing and Classification and Identification etc., Figure 1 shows that techniqueflow chart of the present invention: the experimenter is applied suitable visual stimulus, gather the corresponding vision inducting brain that produces, after pretreatment such as denoising, extract effective brain electrical feature, and it is carried out the dimensionality reduction operation to optimize reorganization; At last the brain electrical feature is sent into grader and carry out classification learning and test, reach the purpose of identification.
The collection of 1 vision induced EEG signals (VEP)
The VEP signal is the evoked brain potential signal that produces when the experimenter is subjected to certain visual stimulus.The picture stimulation of setting of the present invention derives from Snodgrass and Vanderwart picture library.This picture group sheet designs for studying man memory and cognitive competence at first, all pictures wherein are has the common black and white string diagram that concordance characterizes, illustrated things all is that things clear and definite implication, easy identification is arranged, as kite, door, flag, envelope etc., Fig. 2 are some picture examples.
Experimental design is as follows:
1) experimenter wears electrode cap, selects comfortable posture to be sitting on the chair.
2) require the picture play on experimenter's viewing distance 1m computer screen at a distance, identification is also remembered things in the picture.
3) each picture stimulates and continues 300ms, twice adjacent stimulus intervals 5s, and the sequential setting is as shown in Figure 3.10 pictures are carried out in every group of experiment altogether stimulates (picture does not repeat).
4) on the basis of international standard 10/20 crosslinking electrode place system, increase the number that leads and lead to 64, A1 wherein, A2, NZ are reference electrode, as shown in Figure 4.Sample frequency is 256Hz.
5) only with the EEG signals in the 300ms stimulating course that collects as object of study.Every group of experiment has the individual sampled point of 768 (256*0.3*10) like this.
The pretreatment of 2 original EEG signals
At first original EEG signals being carried out pretreatment before extracting feature, mainly is to remove to wait the noise of introducing nictation.The signal of blinking that is mixed in the original brain electricity does not possess identification ability, belongs to noise, it should be removed.Because signal of blinking continues 250ms usually, signal amplitude is between 100-200 μ V, and the amplitude of useful EEG signals is much smaller than this, so can pass through the low pass filter of one 100 μ V with the signal of blinking filtering.
The selection of 3 wave bands
Studies show that the VEP of γ wave band (30-50Hz) is and higher brain function activity, and is closely-related as memory, cognition etc.And the vision induced EEG signals that the experiment of the visual stimulus of the present invention design is excited carrier experimenter's information such as memory, cognition just.Because memory, cognitive level are embodying individual variation usually, thereby can carry out identification with the VEP signal of this wave band.In addition, because EEG signals is gathered simultaneously by 64 electrodes, it is more obvious that this just makes that the diversity of cerebral activity between the individuality embodies ground.
Given this, the present invention has carried out filtering by Butterworth filter to original EEG signals, only keeps wherein maximally related γ wave band (30-50Hz) and studies, and the number of data points of each passage is normalized to 256.
The extraction of 4 brain electrical features
The extraction of brain electrical feature is calculated the γ wave band power spectrum of each passage respectively based on Pa Sewaer (Parseval) T/F theorem, and computing formula is as follows:
The energy of GBP (Gamma Band Power) expression γ wave band.Wherein,
Be the γ wave band EEG signals behind each channel filtering, N is the data sum (after filtering and the normalization) of each passage, as previously mentioned, and N=256.
And then each passage GBP carried out normalization, eliminate data difference:
NGBP (Normalised Gamma Band Power) expression normalization γ wave band spectrum energy.
5 signal post-processing
Target of the present invention be the γ wave band spectrum energy that will extract as feature, finally be used for Classification and Identification.And by comprising a lot of redundancies in the spectrum energy feature that obtains after above-mentioned Pa Sewaer (Parseval) T/F theorem and the normalization, they do not have separability, reduced recognition effect on the contrary, thereby be necessary these features are optimized and screen.The present invention is that the method by Fisher discriminant analysis realizes the feature screening.
The central idea of the discriminant analysis method under the Fisher meaning is to manage to find out a best projection direction, with the spot projection in the P dimension space in lower dimensional space, different points is separated as much as possible, thereby improve the separability of data point, be illustrated in figure 5 as the Fisher linear discriminant sketch map of two class samples.
Suppose a sample set { X}
i, when carrying out linear Fisher judgment analysis, target is to find the linear projection direction, so that the projection result of training sample on these shows: dispersion minimum in the class, dispersion maximum between class.Define the within class scatter matrix S of all kinds of samples
wAnd dispersion matrix S between class
bAs follows respectively:
Wherein: C is a sample class number;
The Fisher criterion function is defined as:
I(w)=(w
TS
bw)/(w
TS
ww)????????????????????(5)
So, the problem of searching best projection direction just is converted into the problem of seeking optimal mapping direction w* on mathematics.Obviously, best projection direction w* is and the corresponding characteristic vector of the eigenvalue of maximum of feature structure:
S
bw=λS
ww???????????????????????????????(6)
In fact a best projection direction can not be extracted competent discriminant information, need promptly obtain 1 best projection direction w with former data projection to some orthogonal directions usually
1, w
2, w
1, have the incoherent best projection vector set of statistics and exactly X obtained 1 dimension projection properties Y to this 1 best projection direction projection:
In the present invention, 40 people are done classification (classification is counted C=40), every class all extracts 10 samples, i.e. n
iDo not distinguish, be n=10; Through above-mentioned spectrum energy NGBP computational methods, the intrinsic dimensionality that obtains each sample is p=64.Then the primitive character matrix of i class sample can be expressed as:
Concrete implementation step is as follows:
[3] calculate dispersion matrix between interior dispersion of all kinds of classes and class by (3), (4) respectively;
[4] the Fisher criterion function I (w) of definition in the structure (5) obtains 1 best projection direction w by asking its extreme value
1, w
2, w
1(1<p);
[5] former sample characteristics collection { X}
iConversion by (7) obtains projection properties collection { Y}
i, wherein:
Through experimental verification, the effect that reaches when 1=36 is best, has realized the dimensionality reduction of feature and has optimized reorganization.
Be easy to proof, the Partial Feature of giving up does not have separability, and the feature that keeps makes in dimensionality reduction that then inhomogeneous point separates as far as possible, thereby improves the separability of data point, improves recognition accuracy.
6 identifications based on the BP neutral net
(Artificial Neural Network ANN) is the neutral net that can realize certain function of manual construction on the basis that the mankind understand its cerebral nerve network understanding to artificial neural network.It is based on imitation cerebral nerve network structure and function and a kind of information processing system of setting up, has the non-linear of height.
The present invention selects multilayer feedforward neural network and error Back-Propagation learning algorithm (Error Back Propagation) for use, abbreviates the BP network as.The BP artificial neural network is by the learning rules that the tutor the is arranged training study that exercises supervision, after a pair of learning model offers network, neuronic activation value is propagated to output layer through the intermediate layer from input layer, all obtains the input response of network at the various neurons of output layer.And, successively revise the connection weights of each layer through the intermediate layer from output layer according to the direction that reduces error between desired output and the real output value, get back to input layer at last, so be called " error Back-Propagation algorithm ".Along with constantly carrying out of this error Back-Propagation correction, network also constantly rises to the accuracy of input pattern response.Last in reaching the range of error of permission, network is restrained after reaching poised state automatically.Be illustrated in figure 6 as basic BP topology of networks.
The core of BP network algorithm is by propagated error backward on one side, Yi Bian the mode of round-off error is constantly adjusted network parameter (weights, threshold value) forward, with realization or approach desirable input and output vector correlation.It all propagates calculating twice to each training:
1) forward calculation---begin successively to calculate backward output from input layer, produce finally and export, and calculate the actual error of exporting with target of exporting;
2) backwards calculation---begin forward propagated error signal successively from output layer, revise weights, up to error less than given threshold value.
For n input learning sample a
1, a
2, a
n, the known output sample corresponding with it is A
1, A
2... A
qThe destination of study is the actual output C with network
1, C
2... C
qWith target vector A
1, A
2... A
qBetween error revise weights, make A
1(1=1,2 ..., q) with the C that expects
1Approaching as much as possible; Even the error sum of squares of network output layer arrives minimum greatly.It is by the continuously variation of computing network weights and deviation and approach target gradually on the direction that descends with respect to the error function slope.The variation of weights and deviation each time all is directly proportional with the influence of network error, and is delivered to each layer in the mode of back propagation.
With the characteristic vector { Y} after above-mentioned dimensionality reduction and the optimization
iAs input, the category label under the sample itself is realized Classification and Identification as target vector by nerve network system.For the identification ability of accurate test b P neutral net, prevent that because of the bad point of local data influences recognition effect, the present invention has taked the way of K folding cross validation.Data set is divided into the K equal portions, in turn will wherein (K 1) part as training data, 1 part as test data, tests.Each test all can draw corresponding accuracy, and K the meansigma methods conduct of accuracy as a result is to the estimation of arithmetic accuracy.
Beneficial effect: the present invention is tested on the data base of 40*10 sample composition altogether 40 classifications, at first after the calculation of filtered γ wave band power spectrum of EEG signals as the brain electrical feature; Through Fisher discriminant analysis primary 64 dimensional features are reduced to 36 dimensions after screening then; Realize Classification and Identification by the BP neutral net at last.Adopt the cross validation of different broken numbers, obtain following recognition result respectively, as table 1:
Table 140 experimenter's recognition result
K rolls over cross validation | Correct recognition rata |
??K=1 | ??76.8% |
??K=2 | ??79.6% |
??K=5 | ??84.5% |
??K=10 | ??86.9% |
Result shown in the table 1 shows, is carrying the information of individual separability in the vision induced EEG signals, can be used for identification as a kind of biological characteristic.The feature extracting method based on γ wave band power spectrum that this experiment proposes can more effectively must be described brain electrical feature composition, and the result satisfies the requirement of discrimination.
The brain electricity can not only be used for pathological analysis and medical diagnosis, and as a kind of effective biological characteristic, its generation and people's thinking activities is closely related, shows the individual dependency of height.A kind of as in the brain electricity, the vision inducting brain electricity is to be subjected to the EEG signals that produces when certain image stimulates at individuality, it is relevant with abilities such as man memory and cognitions, and these abilities are embodying tangible individual difference.
Based on this, the present invention proposes a kind of new personal identification method based on the vision inducting brain electricity, is the expansion to traditional brain electricity application (as the brain-computer interface technology), also opens new thinking for living things feature recognition.This invention can remedy the deficiency of traditional biological feature identification technique, because of its high accuracy with significant advantage such as be difficult to duplicate, as a kind of strong replenishing, can integratedly be applied to the mechanism and the place of military field or some high security requirement, create the social living environment of safer harmony, and be expected to obtain the lifting of considerable social benefit and public safety service.Optimum implementation intends adopting patent transfer, technological cooperation or product development.
Claims (4)
1. personal identification method based on visual evoked potential (VEP), it is characterized in that, comprise the following steps: that the experimenter is applied certain image to be stimulated, select suitable scalp crosslinking electrode to gather experimenter's vision inducting brain, after original EEG signals carried out the denoising pretreatment, extract the power spectrum of γ wave band and study as the brain electrical feature; Utilize the Fisher linear discriminant that the brain electrical feature is handled subsequently; By the BP neutral net optimized characteristic parameter is carried out classification learning and test at last, to realize the identification of identity.
2. a kind of personal identification method according to claim 1 based on visual evoked potential (VEP), it is characterized in that, the extraction that the power spectrum of described extraction γ wave band is studied the midbrain electrical feature as the brain electrical feature is based on Pa Sewaer Parseval T/F theorem, calculate the γ wave band power spectrum of each passage respectively, computing formula is as follows:
GBP is the abbreviation of Gamma Band Power, the energy of expression γ wave band, wherein,
Be the γ wave band EEG signals behind each channel filtering, N is the data sum after each channel filtering and the normalization;
And then each passage GBP carried out normalization, eliminate data difference:
NGBP is the abbreviation of Normalised Gamma Band Power, expression normalization γ wave band spectrum energy.
3. a kind of personal identification method according to claim 1 based on visual evoked potential (VEP), it is characterized in that, the core of described BP neutral net is by propagated error backward on one side, the mode of round-off error is constantly adjusted the network parameter that comprises weights, threshold value forward on one side, to realize or to approach desirable input and output vector correlation, calculating is all propagated in each training twice:
Forward calculation---begin successively to calculate backward output from input layer, produce finally and export, and calculate the actual error of exporting with target of exporting;
Backwards calculation---begin forward propagated error signal successively from output layer, revise weights, up to error less than given threshold value,
For n input learning sample a
1, a
2, a
n, the known output sample corresponding with it is A
1, A
2... A
qThe destination of study is the actual output C with network
1, C
2... C
qWith target vector A
1, A
2... A
qBetween error revise weights, make A
1(1=1,2 ..., q) with the C that expects
1Approaching as much as possible; Even the error sum of squares of network output layer arrives minimum greatly, be by the continuously variation of computing network weights and deviation and approach target gradually on the direction that descends with respect to the error function slope, the variation of weights and deviation each time all is directly proportional with the influence of network error, and is delivered to each layer in the mode of back propagation.
4. a kind of personal identification method according to claim 1 based on visual evoked potential (VEP), it is characterized in that, take the way of K folding cross validation to come the identification ability of test b P neutral net: data set is divided into the K equal portions, in turn will wherein (K-1) part as training data, 1 part as test data, test, each test all can draw corresponding accuracy, and K the meansigma methods conduct of accuracy as a result is to the estimation of arithmetic accuracy.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201010199826A CN101828921A (en) | 2010-06-13 | 2010-06-13 | Identity identification method based on visual evoked potential (VEP) |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201010199826A CN101828921A (en) | 2010-06-13 | 2010-06-13 | Identity identification method based on visual evoked potential (VEP) |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101828921A true CN101828921A (en) | 2010-09-15 |
Family
ID=42713248
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201010199826A Pending CN101828921A (en) | 2010-06-13 | 2010-06-13 | Identity identification method based on visual evoked potential (VEP) |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101828921A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102509103A (en) * | 2011-09-29 | 2012-06-20 | 天津大学 | Identifying method based on visual evoked P3 potential |
CN103405229A (en) * | 2013-07-12 | 2013-11-27 | 电子科技大学 | Induced brain wave extraction method based on bootlace sampling |
CN105303631A (en) * | 2015-09-22 | 2016-02-03 | 江西科技学院 | Method for carrying out card punching and attendance checking-in in small office by utilizing electroencephalogram signals |
CN105389494A (en) * | 2015-11-04 | 2016-03-09 | 上海大学 | Biometric identification password verification system and method based on brain wave |
CN106491143A (en) * | 2016-10-18 | 2017-03-15 | 哈尔滨工业大学深圳研究生院 | Judgment method of authenticity and device based on EEG signals |
CN106580320A (en) * | 2016-12-16 | 2017-04-26 | 长春大学 | EEG signal feature analysis method and system based on visual inducement |
WO2017088693A1 (en) * | 2015-11-23 | 2017-06-01 | 中国银联股份有限公司 | Feature recognition-based identity verification method |
CN107067519A (en) * | 2017-05-12 | 2017-08-18 | 广东工业大学 | A kind of safety box based on the electric identification of brain |
WO2017201972A1 (en) * | 2016-05-26 | 2017-11-30 | 华为技术有限公司 | Identity recognition method and device based on electroencephalogram signal |
CN108882888A (en) * | 2016-03-08 | 2018-11-23 | 克里斯托夫·古格 | Device and method for the electro photoluminescence to subject |
CN108985029A (en) * | 2018-06-05 | 2018-12-11 | 中国科学院半导体研究所 | The brain electricity personal identification method of view-based access control model stimulation |
CN109002798A (en) * | 2018-07-19 | 2018-12-14 | 大连理工大学 | It is a kind of singly to lead visual evoked potential extracting method based on convolutional neural networks |
CN109171753A (en) * | 2018-08-16 | 2019-01-11 | 广东工业大学 | A kind of EEG signals EEG personal identification method encoding neural network certainly based on depth |
CN109784023A (en) * | 2018-11-28 | 2019-05-21 | 西安电子科技大学 | Stable state vision inducting brain electricity personal identification method and system based on deep learning |
CN109982737A (en) * | 2016-11-30 | 2019-07-05 | 索尼公司 | Output-controlling device, output control method and program |
CN110121711A (en) * | 2016-12-21 | 2019-08-13 | 华为技术有限公司 | A kind of personal identification method and equipment of view-based access control model Evoked ptential |
CN110321691A (en) * | 2019-07-30 | 2019-10-11 | 东南大学 | A kind of subscription authentication device and its method for authenticating suitable for brain-computer interface |
CN111329474A (en) * | 2020-03-04 | 2020-06-26 | 西安电子科技大学 | Electroencephalogram identity recognition method and system based on deep learning and information updating method |
CN113080971A (en) * | 2021-04-12 | 2021-07-09 | 北京交通大学 | Method and system for judging fatigue state by detecting blink signals |
CN116738215A (en) * | 2023-08-11 | 2023-09-12 | 之江实验室 | Electroencephalogram identity recognition method and device based on steady-state visual evoked potential |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004248714A (en) * | 2003-02-18 | 2004-09-09 | Kazuo Tanaka | Authentication method using living body signal and authentication apparatus therefor |
CN1803086A (en) * | 2005-12-02 | 2006-07-19 | 清华大学 | Objectively detected identity recognition method based on human brain memory character |
US20080294907A1 (en) * | 2007-05-21 | 2008-11-27 | Hively Lee M | Methods for using a biometric parameter in the identification of persons |
CN101491441A (en) * | 2009-02-26 | 2009-07-29 | 江西蓝天学院 | Identification method based on electroencephalogram signal |
CN101703405A (en) * | 2009-11-09 | 2010-05-12 | 江西蓝天学院 | Wavelet analysis and Welch algorithm personal identification method |
CN101716079A (en) * | 2009-12-23 | 2010-06-02 | 江西蓝天学院 | Brainprint identity identification authentication method based on multi-characteristics algorithm |
-
2010
- 2010-06-13 CN CN201010199826A patent/CN101828921A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004248714A (en) * | 2003-02-18 | 2004-09-09 | Kazuo Tanaka | Authentication method using living body signal and authentication apparatus therefor |
CN1803086A (en) * | 2005-12-02 | 2006-07-19 | 清华大学 | Objectively detected identity recognition method based on human brain memory character |
US20080294907A1 (en) * | 2007-05-21 | 2008-11-27 | Hively Lee M | Methods for using a biometric parameter in the identification of persons |
CN101491441A (en) * | 2009-02-26 | 2009-07-29 | 江西蓝天学院 | Identification method based on electroencephalogram signal |
CN101703405A (en) * | 2009-11-09 | 2010-05-12 | 江西蓝天学院 | Wavelet analysis and Welch algorithm personal identification method |
CN101716079A (en) * | 2009-12-23 | 2010-06-02 | 江西蓝天学院 | Brainprint identity identification authentication method based on multi-characteristics algorithm |
Non-Patent Citations (1)
Title |
---|
20081029 A.Yazdani,et.al. Fisher Linear Discriminant Based Person Identification Using Visual Evoked Potentials 1677-1680 1-4 , 2 * |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102509103A (en) * | 2011-09-29 | 2012-06-20 | 天津大学 | Identifying method based on visual evoked P3 potential |
CN103405229A (en) * | 2013-07-12 | 2013-11-27 | 电子科技大学 | Induced brain wave extraction method based on bootlace sampling |
CN103405229B (en) * | 2013-07-12 | 2015-12-09 | 电子科技大学 | A kind of evoked brain potential extracting method based on bootlace sampling |
CN105303631A (en) * | 2015-09-22 | 2016-02-03 | 江西科技学院 | Method for carrying out card punching and attendance checking-in in small office by utilizing electroencephalogram signals |
CN105389494A (en) * | 2015-11-04 | 2016-03-09 | 上海大学 | Biometric identification password verification system and method based on brain wave |
WO2017088693A1 (en) * | 2015-11-23 | 2017-06-01 | 中国银联股份有限公司 | Feature recognition-based identity verification method |
CN108882888A (en) * | 2016-03-08 | 2018-11-23 | 克里斯托夫·古格 | Device and method for the electro photoluminescence to subject |
WO2017201972A1 (en) * | 2016-05-26 | 2017-11-30 | 华为技术有限公司 | Identity recognition method and device based on electroencephalogram signal |
CN106491143A (en) * | 2016-10-18 | 2017-03-15 | 哈尔滨工业大学深圳研究生院 | Judgment method of authenticity and device based on EEG signals |
CN109982737B (en) * | 2016-11-30 | 2022-06-28 | 索尼公司 | Output control device, output control method, and program |
CN109982737A (en) * | 2016-11-30 | 2019-07-05 | 索尼公司 | Output-controlling device, output control method and program |
CN106580320A (en) * | 2016-12-16 | 2017-04-26 | 长春大学 | EEG signal feature analysis method and system based on visual inducement |
CN110121711A (en) * | 2016-12-21 | 2019-08-13 | 华为技术有限公司 | A kind of personal identification method and equipment of view-based access control model Evoked ptential |
CN107067519A (en) * | 2017-05-12 | 2017-08-18 | 广东工业大学 | A kind of safety box based on the electric identification of brain |
CN107067519B (en) * | 2017-05-12 | 2023-02-03 | 广东工业大学 | Safe box based on brain electricity identification |
CN108985029A (en) * | 2018-06-05 | 2018-12-11 | 中国科学院半导体研究所 | The brain electricity personal identification method of view-based access control model stimulation |
CN109002798A (en) * | 2018-07-19 | 2018-12-14 | 大连理工大学 | It is a kind of singly to lead visual evoked potential extracting method based on convolutional neural networks |
CN109171753B (en) * | 2018-08-16 | 2021-05-11 | 广东工业大学 | Electroencephalogram EEG (electroencephalogram) identity recognition method based on deep self-coding neural network |
CN109171753A (en) * | 2018-08-16 | 2019-01-11 | 广东工业大学 | A kind of EEG signals EEG personal identification method encoding neural network certainly based on depth |
CN109784023B (en) * | 2018-11-28 | 2022-02-25 | 西安电子科技大学 | Steady-state vision-evoked electroencephalogram identity recognition method and system based on deep learning |
CN109784023A (en) * | 2018-11-28 | 2019-05-21 | 西安电子科技大学 | Stable state vision inducting brain electricity personal identification method and system based on deep learning |
CN110321691A (en) * | 2019-07-30 | 2019-10-11 | 东南大学 | A kind of subscription authentication device and its method for authenticating suitable for brain-computer interface |
CN110321691B (en) * | 2019-07-30 | 2022-03-11 | 东南大学 | User authentication device and method suitable for brain-computer interface |
CN111329474A (en) * | 2020-03-04 | 2020-06-26 | 西安电子科技大学 | Electroencephalogram identity recognition method and system based on deep learning and information updating method |
CN113080971A (en) * | 2021-04-12 | 2021-07-09 | 北京交通大学 | Method and system for judging fatigue state by detecting blink signals |
CN116738215A (en) * | 2023-08-11 | 2023-09-12 | 之江实验室 | Electroencephalogram identity recognition method and device based on steady-state visual evoked potential |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101828921A (en) | Identity identification method based on visual evoked potential (VEP) | |
CN101862194B (en) | Imagination action EEG identification method based on fusion feature | |
CN106886792B (en) | Electroencephalogram emotion recognition method for constructing multi-classifier fusion model based on layering mechanism | |
Abo-Zahhad et al. | A new multi-level approach to EEG based human authentication using eye blinking | |
CN108776788B (en) | Brain wave-based identification method | |
Lu et al. | A study of personal recognition method based on EMG signal | |
CN110772268A (en) | Multimode electroencephalogram signal and 1DCNN migration driving fatigue state identification method | |
Palaniappan | Method of identifying individuals using VEP signals and neural network | |
CN109784023B (en) | Steady-state vision-evoked electroencephalogram identity recognition method and system based on deep learning | |
Li et al. | Multi-modal bioelectrical signal fusion analysis based on different acquisition devices and scene settings: Overview, challenges, and novel orientation | |
El-Fiqi et al. | Convolution neural networks for person identification and verification using steady state visual evoked potential | |
CN105877766A (en) | Mental state detection system and method based on multiple physiological signal fusion | |
Sharma et al. | Individual identification based on neuro-signal using motor movement and imaginary cognitive process | |
CN101843491A (en) | Resting electroencephalogram identification method based on bilinear model | |
CN103472922A (en) | Destination selecting system based on P300 and SSVEP (Steady State Visual Evoked Potential) hybrid brain-computer interface | |
CN102509103A (en) | Identifying method based on visual evoked P3 potential | |
CN110786849B (en) | Electrocardiosignal identity recognition method and system based on multi-view discriminant analysis | |
Moctezuma et al. | Event-related potential from eeg for a two-step identity authentication system | |
CN104536572B (en) | It is a kind of based on event related potential across the universal brain-machine interface method of individual | |
CN113040772A (en) | Classification method of syphilis addicts and normal persons based on electroencephalogram signals | |
CN113569997A (en) | Emotion classification method and system based on graph convolution neural network | |
Kong et al. | Personal identification based on brain networks of EEG signals | |
Ma et al. | A classification algorithm of an SSVEP brain-Computer interface based on CCA fusion wavelet coefficients | |
CN114081505A (en) | Electroencephalogram signal identification method based on Pearson correlation coefficient and convolutional neural network | |
Wang et al. | Stable EEG Biometrics Using Convolutional Neural Networks and Functional Connectivity. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Open date: 20100915 |