CN111653005A - Identity authentication method based on electroencephalogram signal, and safe unlocking method and system - Google Patents
Identity authentication method based on electroencephalogram signal, and safe unlocking method and system Download PDFInfo
- Publication number
- CN111653005A CN111653005A CN202010275632.4A CN202010275632A CN111653005A CN 111653005 A CN111653005 A CN 111653005A CN 202010275632 A CN202010275632 A CN 202010275632A CN 111653005 A CN111653005 A CN 111653005A
- Authority
- CN
- China
- Prior art keywords
- identity authentication
- electroencephalogram
- authentication
- paradigms
- face
- 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
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00896—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys specially adapted for particular uses
- G07C9/00912—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys specially adapted for particular uses for safes, strong-rooms, vaults or the like
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/259—Fusion by voting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention belongs to the technical field of identity authentication, and particularly relates to an identity authentication method based on an electroencephalogram signal, a safe unlocking method and a system, wherein the authentication method comprises the following steps: acquiring electroencephalogram signals under visual playing paradigms under at least two different security levels by using wearable equipment, wherein the visual playing paradigms comprise a resting state paradigms and a face stimulation paradigms, and sample data of the face stimulation paradigms comprise a face image of a detected person and a strange face image which are used for acquiring the electroencephalogram signals and have known identity information; respectively extracting features from a time domain, a frequency domain and a time-frequency domain aiming at the electroencephalogram signals, and classifying by utilizing an integrated classifier; and judging the identity authentication of the detected person according to the classification result. The invention meets the safety level requirements under different scenes, uses multi-space fusion feature extraction and combines an integrated classifier, realizes identity authentication based on biotechnology, improves authentication accuracy and safety, is applicable to safety equipment such as a safe box, an access control system and the like, and has better application value.
Description
Technical Field
The invention belongs to the technical field of identity authentication, and particularly relates to an identity authentication method based on an electroencephalogram signal, and a safe unlocking method and system.
Background
With the increasing demand of identity authentication in the fields of information security, financial security and the like, the traditional identity identification technology is difficult to meet the special requirements of various industries. Compared with the traditional identity recognition technology, the recognition technology based on the biological characteristic information has the advantages of uniqueness, stability, collection and the like. However, with the emergence of artificial intelligence algorithms such as generation countermeasure networks, the security of the traditional biological features such as fingerprints, faces and irises is continuously challenged due to the inherent characteristic that the biological features can be copied, and people urgently need an identity authentication mode with a higher safety factor. In recent years, the rapid development of brain science provides a new idea for the field of identity authentication, and a biological feature identification mode based on brain veins gradually becomes a research hotspot.
The brain print unlocking mainly utilizes the individual difference of human brain function signals as biological characteristics. The research of modern neuroimaging technology shows that the human brain not only has the structural difference determined by genes, but also has the functional differences of memory, character, thinking and the like, and provides theoretical support for brain striations as biological characteristics. Especially, the brain veins have the unique advantages of stress resistance and in vivo detection, namely, when people are held or threatened, the brain function signals are obviously different from the brain activities in the normal state. The electroencephalogram has higher time resolution as a common brain signal testing means, so the invention mainly researches the identity authentication technology based on the electroencephalogram. At present, the identity authentication technology based on the electroencephalogram mainly faces the following problems: firstly, the existing electroencephalogram acquisition equipment is expensive, complex to operate and poor in user experience; secondly, the authentication mode is single, and the safety level requirements under different scenes cannot be met; thirdly, the existing authentication has low accuracy and cannot meet the actual requirement; fourth, most of the existing researches are still in an experimental verification stage, and are lack of application in real life.
Disclosure of Invention
Therefore, the identity authentication method based on the electroencephalogram signal, the safe unlocking method based on the electroencephalogram signal and the safe unlocking system based on the electroencephalogram signal are provided, the user experience is improved, the accuracy and the safety of identity authentication are improved, and the method and the system can be applied to the safety fields of safes, access control systems and the like which need identity authentication.
According to the design scheme provided by the invention, the identity authentication method based on the electroencephalogram signal comprises the following contents:
acquiring electroencephalogram signals under visual playing paradigms under at least two different security levels by using wearable equipment, wherein the visual playing paradigms comprise a resting state paradigms and a face stimulation paradigms, and sample data of the face stimulation paradigms comprise a face image of a detected person and a strange face image which are used for acquiring the electroencephalogram signals and have known identity information;
respectively extracting features from a time domain, a frequency domain and a time-frequency domain aiming at the electroencephalogram signals, and classifying by utilizing an integrated classifier;
and judging the identity authentication of the detected person according to the classification result.
As the identity authentication method based on the electroencephalogram signals, the electroencephalogram electrodes for collecting the signals are further set, the electroencephalogram cap is used for collecting the multichannel electroencephalogram signals, and the lead signals distributed on the top leaves and the occipital leaves for feature extraction are selected through the maximum correlation minimum redundancy algorithm.
As the identity authentication method based on the electroencephalogram signals, an electroencephalogram cap consistent with a lead signal channel is further adopted according to the international 10-20 electrode arrangement standard.
As the identity authentication method based on the electroencephalogram signals, further, in a resting state paradigm, a detected person collects the connection relation and the activity degree among all brain areas under a calm state; in the face stimulation paradigm, the face image of the detected person is mixed with the face images of other people to form a face sequence group, and electroencephalogram signal acquisition is carried out on the detected person in the process of playing the face sequence group.
As the identity authentication method based on the electroencephalogram signals, the method further comprises the following steps of firstly preprocessing the extracted electroencephalogram signals, wherein the preprocessing comprises the following steps: signal data in the time period are removed according to the set transient time period, and artifact signal removal and low-pass filtering are sequentially carried out; and carrying out segmentation and baseline correction comparison on the signal data to obtain electroencephalogram signal data for feature extraction.
As the intelligent network attack and defense strategy optimization method oriented to the maximization of the countermeasures, the method further utilizes an integrated classifier for classification, and comprises the following contents: respectively utilizing a plurality of classifiers to classify the extracted electroencephalogram signal characteristics, wherein the plurality of classifiers at least comprise: a KNN classifier, an LDA classifier and an SVM classifier; and integrating the classification results of the plurality of classifiers, and using the classification result with the largest vote number as an identity authentication basis by using a voting strategy.
The invention further provides a safe unlocking method based on electroencephalogram authentication, the first-layer identity authentication is carried out based on the identity authentication method based on the electroencephalogram signals, the second-layer identity authentication is carried out by combining the safe password, and the safe unlocking action is carried out after the double identity authentication is passed.
Further, the invention also provides a safe unlocking system based on the electroencephalogram authentication, which comprises the following components: the safe electromagnetic lock comprises an operation panel and a circuit board, wherein the operation panel is arranged on the safe and used for inputting instructions, and the circuit board is connected with the operation panel and used for controlling the electromagnetic lock of the safe to act according to the instruction input; the circuit board is provided with a singlechip for performing data operation processing according to instruction input, and the singlechip is also connected with an electroencephalogram authentication module; the operation panel is provided with an unlocking key, a brain print reading key, a password input keyboard and an identity authentication key, wherein the unlocking key is sequentially connected with the single chip microcomputer and used for inputting a safe unlocking instruction, the brain print reading key is used for inputting a first layer of identity authentication, the password input keyboard is used for inputting a second layer of identity authentication, and the identity authentication key is used for inputting an authentication instruction; the brain electricity authentication module comprises: a wearable device and a brain print authentication unit; wherein the content of the first and second substances,
the wearable device is used for reading a key instruction according to brain lines fed back by the single chip microcomputer and acquiring electroencephalograms under visual playing paradigms under at least two different security levels, wherein the visual playing paradigms comprise a resting state paradigms and a face stimulation paradigms, and sample data of the face stimulation paradigms comprise face images of a tested person and strange face images which are used for acquiring the electroencephalograms and have known identity information;
the brain print authentication unit is used for respectively extracting the characteristics of the extracted electroencephalogram signals from a time domain, a frequency domain and a time-frequency domain according to the identity authentication instruction fed back by the single chip microcomputer and classifying the electroencephalogram signals by using an integrated classifier; and judging the identity of the detected person according to the classification result.
As the safe unlocking system based on the electroencephalogram authentication, the single chip microcomputer is further connected with an alarm for alarming and reminding the unlocking instruction under the condition that the identity authentication fails.
The invention has the beneficial effects that:
the wearable equipment can complete multi-channel self-defined wireless electroencephalogram signal acquisition equipment based on the ADS1299 chip, has the characteristics of low cost, simplicity and convenience in operation, wireless transmission and the like, and provides a hardware basis for accurate and reliable acquisition of electroencephalogram signals; aiming at different safety level requirements, two brain print authentication modes are designed, on one hand, the brain print authentication mode based on human face visual stimulation is realized by utilizing the specific reaction of an individual to a human face picture, and the electroencephalogram characteristics capable of reflecting the identity of the individual can be stably induced, so that the basic requirement of identity authentication safety is met; on the other hand, by utilizing a resting state mode closer to reality, only brain signals of a user in a calm state are acquired, and the identity is recognized through the connection relation and the activity degree among all brain areas; the safe unlocking identity authentication is realized based on the biotechnology, the safe unlocking identity authentication can be applied to hardware and can also be used in software, the compatibility among equipment can be ensured while the safety and the stability of the identity authentication are ensured, the application range is wide, and the social application value is good.
Description of the drawings:
FIG. 1 is a schematic flow chart of an embodiment of an identity authentication method;
FIG. 2 is a schematic diagram showing electrode selection in the example;
FIG. 3 is a schematic diagram of a peripheral connection circuit of a wearable device in an embodiment;
FIG. 4 is a schematic diagram of a human face visual stimulus paradigm in an embodiment;
FIG. 5 is a schematic diagram of an electroencephalogram signal data processing flow in the embodiment;
FIG. 6 is a schematic illustration of an exemplary embodiment of a safe operating interface;
FIG. 7 is a diagram showing the result of identity authentication of the safe in the embodiment;
FIG. 8 is a circuit schematic of a circuit board of an embodiment;
FIG. 9 is a schematic diagram of identity authentication of an unlocking system of the safe in the embodiment;
FIG. 10 is a diagram illustrating the result of the test of the accuracy of the authentication mode in the embodiment;
FIG. 11 is a schematic diagram comparing the prior art with the embodiment;
FIG. 12 is a diagram illustrating actual test results of multiple users in the embodiment.
The specific implementation mode is as follows:
in order to make the objects, technical solutions and advantages of the present invention clearer and more obvious, the present invention is further described in detail below with reference to the accompanying drawings and technical solutions.
The research of modern neuroimaging technology shows that the human brain not only has the structural difference determined by genes, but also has the functional differences of memory, character, thinking and the like, and provides theoretical support for brain striations as biological characteristics. Especially, the brain veins have the unique advantages of stress resistance and in vivo detection, namely, when people are held or threatened, the brain function signals are obviously different from the brain activities in the normal state. The method aims at the problems that the existing electroencephalogram acquisition equipment for electroencephalogram identity authentication is expensive, complex to operate, single in authentication mode, low in authentication accuracy, lack of practical application and the like. Therefore, in the embodiment of the present invention, based on the practical application requirement of the electroencephalogram identity authentication technology, referring to fig. 1, an identity authentication method based on an electroencephalogram signal is provided, which includes the following contents:
s101, acquiring electroencephalogram signals under visual playing paradigms under at least two different security levels by using wearable equipment, wherein the visual playing paradigms comprise a resting state paradigms and a face stimulation paradigms, and sample data of the face stimulation paradigms comprise self face images and strange face images of a tested person for acquiring the electroencephalogram signals and known identity information;
s102, extracting features from a time domain, a frequency domain and a time-frequency domain respectively aiming at the electroencephalogram signals, and classifying by utilizing an integrated classifier;
s103, judging the identity authentication of the detected person according to the classification result.
Aiming at different safety level requirements, two brain print authentication modes are designed, on one hand, the brain print authentication mode based on human face visual stimulation is realized by utilizing the specific reaction of an individual to a human face picture, and the electroencephalogram characteristics capable of reflecting the identity of the individual can be stably induced, so that the basic requirement of identity authentication safety is met; on the other hand, the resting state mode which is closer to reality is utilized, only brain signals of the user in the resting state need to be collected, the identity is recognized through the connection relation and the activity degree between all brain areas, and the practicability and the accuracy of the identity authentication mode are improved.
As the identity authentication method based on the electroencephalogram signals in the embodiment of the invention, further, electroencephalogram electrodes for collecting signals are set, an electroencephalogram cap is used for collecting multichannel electroencephalogram signals, and lead signals distributed in the top leaves and the occipital leaves for feature extraction are selected through a maximum correlation minimum redundancy algorithm. Furthermore, according to the international 10-20 electrode arrangement standard, an electroencephalogram cap consistent with a lead signal channel is adopted.
By collecting 64 channels of identity authentication electroencephalogram signals for multiple users, combining the maximum correlation minimum redundancy algorithm with classification accuracy, 8 leads distributed on the top leaves and the occipital leaves and having high authentication accuracy and good stability are selected, as shown in figure 2, according to the international 10-20 electrode arrangement standard, an 8-channel electroencephalogram cap can be adopted, so that the equipment has the characteristics of low impedance, low noise and strong anti-interference capability, is convenient to wear, and is more suitable for practical application. Referring to fig. 3, an ADS1299 chip can be used to complete an 8-channel self-defined wireless electroencephalogram signal acquisition device, so that the wireless transmission expands the range of activity of a user and increases the comfort of user experience; the pluggable electrode interface can be used, the electrode is convenient to replace, and the brain area signals of specific positions can be conveniently collected in a centralized mode. According to the 8 electrode positions with the highest accuracy determined by the previous experiments, guidance can be provided for the later data processing and the authentication detection. A double-battery power supply mode is adopted in a voltage stabilizing circuit of acquisition hardware, data acquisition and Bluetooth communication power supply are separated, and data interference of an acquisition module is avoided. In order to expand the activity range of a user, a wireless Bluetooth communication module is used, an HM-18 Bluetooth transparent transmission module is adopted, and the module only needs to provide a 3.3V power supply and a serial port.
As the identity authentication method based on the electroencephalogram signals in the embodiment of the invention, further, in a resting state paradigm, a detected person collects the connection relation and the activity degree among all brain areas under a resting state; in the face stimulation paradigm, the face image of the detected person is mixed with the face images of other people to form a face sequence group, and electroencephalogram signal acquisition is carried out on the detected person in the process of playing the face sequence group.
More than 80% of information in life is acquired by vision, so a face vision image can be selected as experimental stimulation, the face of a user is mixed with a strange face to form a face sequence group and is quickly played according to the difference of brain signals of the user and other faces when different individuals watch the face and the brain signals of the other people, and the identity of the user is determined by the response of individual brain waves. The paradigm is that the authentication is carried out according to electroencephalogram signals induced when a user watches different human faces, the strange human faces seen by the user are relatively calm, but the electroencephalogram signals are severely different when the user sees the face images of the user. This is because the brain distinguishes itself from others, and the search for own information has a higher priority in consciousness, where the difference in facial features is an important recognition basis in our daily societies.
In order to facilitate the use of users, visual playing paradigms with different safety levels are adopted to perform visual stimulation to induce electroencephalogram signals. For the resting state paradigm, only the user needs to keep calm, the actions of biting, swallowing and the like are avoided, the resting state paradigm is closer to the actual resting state paradigm, only brain signals of the user in the calm state need to be collected, and the identity is recognized through the connection relation and the activity degree among all brain areas; for the face stimulation paradigm, as shown in fig. 4, according to the difference of the brain signals of different individuals watching the face of the user and the face of other people, the specific reaction of the individuals to the face pictures of the users is utilized, the face of the user is mixed with the strange face to form a face sequence group and the face sequence group is played quickly, the electroencephalogram characteristics capable of reflecting the identity of the individual can be stably induced, the identity of the user is determined by the brain wave reaction of the individual, and therefore the basic requirements of identity authentication safety are met. The method comprises the steps that in an actual scene of a user in a resting state paradigm, an acquisition site is selected to be performed in a closed and quiet room, tested intelligent equipment is removed to reduce signal interference of an electromagnetic environment to an acquisition process, the tested user is reminded of relaxing the body and the mind but not entering a sleeping state, actions such as tooth biting, swallowing, eye movement, leg crossing and the like are avoided as much as possible in the data acquisition process, the total time of each tested user can be designed to be 6 minutes of data acquisition, the tested user can perform 2 block data flows in the whole acquisition process, block-1 is resting state eye opening for 3 minutes, block-2 is resting state eye closing for 3 minutes, and 1 minute relaxation time is arranged between the two block acquisition.
As an identity authentication method based on electroencephalogram signals in the embodiment of the present invention, further, for extracted electroencephalogram signals, preprocessing is performed first, where the preprocessing includes: signal data in the time period are removed according to the set transient time period, and artifact signal removal and low-pass filtering are sequentially carried out; and carrying out segmentation and baseline correction comparison on the signal data to obtain electroencephalogram signal data for feature extraction.
In the preprocessing, transient state of the first 10 seconds can be removed, artifacts such as electro-oculogram and myoelectricity are removed, 0-60hz low-pass filtering is carried out by using a Chebyshev filter, data are divided into 85 sections of samples of non-overlapped 2-second data, and comparison is carried out by using a traditional baseline correction method and a self-mean baseline correction method so as to obtain more standard electroencephalogram signal data for feature extraction.
As an intelligent network attack and defense strategy optimization method oriented to the maximization of the countermeasures in the embodiment of the present invention, further, an integrated classifier is used for classification, as shown in fig. 5, which includes the following contents: respectively utilizing a plurality of classifiers to classify the extracted electroencephalogram signal characteristics, wherein the plurality of classifiers at least comprise: a KNN classifier, an LDA classifier and an SVM classifier; and integrating the classification results of the plurality of classifiers, and using the classification result with the largest vote number as an identity authentication basis by using a voting strategy.
And 3 basic classifiers KNN, LDA and SVM are used for identity discrimination, and the classification results of the three classifiers are integrated, and the final identity authentication basis is obtained by using a voting strategy, so that the classification and identity authentication performance is greatly improved.
Furthermore, the embodiment of the invention also provides a safe unlocking method based on electroencephalogram authentication, which is characterized in that the first-layer identity authentication is carried out based on the identity authentication method based on the electroencephalogram signal, the second-layer identity authentication is carried out by combining the safe password, and the safe unlocking action is carried out after the double identity authentication is passed.
Further, an embodiment of the present invention further provides a safe unlocking system based on electroencephalogram authentication, as shown in fig. 6, including: the safe electromagnetic lock comprises an operation panel and a circuit board, wherein the operation panel is arranged on the safe and used for inputting instructions, and the circuit board is connected with the operation panel and used for controlling the electromagnetic lock of the safe to act according to the instruction input; the circuit board is provided with a singlechip for performing data operation processing according to instruction input, and the singlechip is also connected with an electroencephalogram authentication module; the operation panel is provided with an unlocking key, a brain print reading key, a password input keyboard and an identity authentication key, wherein the unlocking key is sequentially connected with the single chip microcomputer and used for inputting a safe unlocking instruction, the brain print reading key is used for inputting a first layer of identity authentication, the password input keyboard is used for inputting a second layer of identity authentication, and the identity authentication key is used for inputting an authentication instruction; the brain electricity authentication module comprises: a wearable device and a brain print authentication unit; wherein the content of the first and second substances,
the wearable device is used for reading a key instruction according to brain lines fed back by the single chip microcomputer and acquiring electroencephalograms under visual playing paradigms under at least two different security levels, wherein the visual playing paradigms comprise a resting state paradigms and a face stimulation paradigms, and sample data of the face stimulation paradigms comprise face images of a tested person and strange face images which are used for acquiring the electroencephalograms and have known identity information;
the brain print authentication unit is used for respectively extracting the characteristics of the extracted electroencephalogram signals from a time domain, a frequency domain and a time-frequency domain according to the identity authentication instruction fed back by the single chip microcomputer and classifying the electroencephalogram signals by using an integrated classifier; and judging the identity of the detected person according to the classification result.
Furthermore, the single chip microcomputer is also connected with an alarm for alarming and reminding aiming at the unlocking instruction under the condition that the identity authentication fails.
In fig. 6, the interface of the safe has only three buttons, and the brain print reading, the identity authentication and the unlocking correspond to the brain print collection, the identity authentication and the safe state control, respectively. After clicking the brain print reading, the brain print acquisition equipment is converted and input, identity authentication is carried out for a series of identity recognition operations, unlocking is carried out for outputting an authentication result to a safe control circuit, and then the singlechip executes unlocking, alarming and other tasks according to instructions. Fig. 7 shows 3 kinds of authentication results, make full use of this brain print's of stress resistance important advantage, increase third kind authentication result, except that the alarm is sounded when the normal unblock of user's identity and intrusion system, third kind authentication result is that the user receives the threat and the emotional state is unusual, neither unblank nor report to the police at this moment, the user need log in again, can use MATLAB visual interface to carry out function integration in specifically realizing, in order to satisfy the succinct design of operation interface, the user only needs to wear brain print collection equipment and select the safe mode, and click the interface button in proper order and can realize the application, realize in the true sense that the intention unblock through "brain print". The universal single chip microcomputer STC12C5A60S2 can be used, as shown in figure 8, a circuit board mainly comprises a serial connector, the single chip microcomputer, an electromagnetic lock and an alarm, after an instruction output from a USB port of a computer is read, the instruction is input into the single chip microcomputer through a serial port to carry out instruction operation, the single chip microcomputer outputs and controls the electromagnetic lock and the alarm to be switched on and off, the input instruction can be divided into three types, unlocking, alarming and non-response are respectively carried out, the authentication in the identification result is correct, identity intrusion and state abnormity are respectively corresponded, and the electromagnetic lock and the alarm control device can be attached to a finished safe in actual use to form a double-safety-protection safe box with a brain print + password, so that the property safety of.
In order to verify the effectiveness of the technical scheme of the invention, the following traditional authentication results are combined to be compared with the technical scheme of the invention:
referring to fig. 9, the electroencephalogram signal is collected by using a custom electroencephalogram electrode; by collecting 64-channel identity authentication electroencephalogram signals for multiple users, combining a maximum correlation minimum redundancy algorithm with classification accuracy, selecting 8 leads which are distributed on the top leaves and the occipital leaves and have high authentication accuracy and good stability, and designing an 8-channel electroencephalogram cap according to the international 10-20 electrode arrangement standard, the equipment has the characteristics of low impedance, low noise and strong anti-interference capability, is convenient to wear and is more suitable for practical application. For the convenience of use of a user, two paradigms (a resting state paradigms and a human face stimulation paradigms) with different safety levels are adopted, for the resting state paradigms, the body and mind of the user are relaxed but the user does not enter a sleep state, and the actions of biting teeth, swallowing, eye movement, leg crossing and the like are avoided as much as possible in the data acquisition process; for the face stimulation paradigm, according to the difference of brain signals of different individuals watching the face of the user and the faces of other people, the face of the user is mixed with strange faces to form a face sequence group and the face sequence group is played quickly, and the identity of the user is determined by the individual brain wave reaction. The safe box operation interface based on the brain print is characterized in that the safe box operation interface is only provided with three buttons, brain print reading, identity authentication and unlocking correspond to brain print acquisition, an authentication algorithm and a safe box control state respectively, brain print acquisition equipment is converted and input into MATLAB after clicking brain print reading, a series of identity identification operations are performed through identity authentication, an authentication result is output to a safe box control circuit through unlocking, and then a single chip microcomputer executes unlocking, alarming and other tasks according to instructions. The safe hardware external device based on the brain veins transmits the result of the classifier and controls the switch of the brain vein lock, a singlechip universal for STC12C5A60S2 can be used, a circuit board mainly comprises a serial port connector, a singlechip, an electromagnetic lock and an alarm, after an instruction output from a USB port of a computer is read, the instruction is input into the singlechip through the serial port to carry out instruction operation, and the singlechip outputs the instruction to control the switch of the electromagnetic lock and the alarm. The electromagnetic lock and the alarm control device are attached to a finished safe to form a double-safety-protection safe with brain veins and passwords, so that the property safety of a user is protected to the maximum extent.
(1) Accuracy of two authentication modes:
the accuracy of both authentication modes was tested and stabilized to over 90%, where the accuracy of the resting mode was 91.42% and the accuracy of the facial visual stimulation mode was 92.74%, as shown in fig. 10.
(2) Compared with the prior results:
fig. 11 shows the result of identity authentication using brain print in recent years, and compared with the authentication method in the present invention, it is found that the authentication method has significant accuracy advantage, wherein two security modes in brain print authentication are unique.
(3) And (3) actual testing by a user:
and (3) inviting 42 users to carry out actual safety test of the system, wherein the authentication accuracy is between 81.37% and 96.84% due to the self difference of the users, the average accuracy is 91.52%, and the standard deviation is 3.56. It can be seen that although the system performance in the actual test is slightly degraded, the overall accuracy is still maintained above 90%, as shown in fig. 12.
Unless specifically stated otherwise, the relative steps, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of the present invention.
Based on the foregoing system, an embodiment of the present invention further provides a server, including: one or more processors; a storage device to store one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the system as described above.
Based on the above system, the embodiment of the present invention further provides a computer readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the above system.
The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the system embodiment, and for the sake of brief description, reference may be made to the corresponding content in the system embodiment for the part where the device embodiment is not mentioned.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing system embodiments, and are not described herein again.
In all examples shown and described herein, any particular value should be construed as merely exemplary, and not as a limitation, and thus other examples of example embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus, and system may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the system according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An identity authentication method based on an electroencephalogram signal is characterized by comprising the following contents:
acquiring electroencephalogram signals under visual playing paradigms under at least two different security levels by using wearable equipment, wherein the visual playing paradigms comprise a resting state paradigms and a face stimulation paradigms, and sample data of the face stimulation paradigms comprise a face image of a detected person and a strange face image which are used for acquiring the electroencephalogram signals and have known identity information;
respectively extracting features from a time domain, a frequency domain and a time-frequency domain aiming at the electroencephalogram signals, and classifying by utilizing an integrated classifier;
and judging the identity authentication of the detected person according to the classification result.
2. The EEG-based identity authentication method as claimed in claim 1, wherein the EEG electrodes for signal collection are set, the EEG cap is used to collect multi-channel EEG signals, and the lead signals distributed in the top leaf and occipital leaf for feature extraction are selected by the maximum correlation minimum redundancy algorithm.
3. The EEG-based identity authentication method according to claim 2, wherein an EEG cap conforming to the lead signal channel is used according to the international 10-20 electrode arrangement standard.
4. The EEG-based identity authentication method according to claim 1, wherein in the resting state paradigm, the detected person collects the connection relationship and the activity degree between the brain areas while keeping the resting state; in the face stimulation paradigm, the face image of the detected person is mixed with the face images of other people to form a face sequence group, and electroencephalogram signal acquisition is carried out on the detected person in the process of playing the face sequence group.
5. The electroencephalogram signal-based identity authentication method according to claim 1, wherein for the extracted electroencephalogram signal, preprocessing is firstly performed, and the preprocessing includes: signal data in the time period are removed according to the set transient time period, and artifact signal removal and low-pass filtering are sequentially carried out; and carrying out segmentation and baseline correction comparison on the signal data to obtain electroencephalogram signal data for feature extraction.
6. The EEG-based identity authentication method according to claim 1, wherein the classification is performed by using an integrated classifier, comprising the following steps: respectively utilizing a plurality of classifiers to classify the extracted electroencephalogram signal characteristics, wherein the plurality of classifiers at least comprise: a KNN classifier, an LDA classifier and an SVM classifier; and integrating the classification results of the plurality of classifiers, and using the classification result with the largest vote number as an identity authentication basis by using a voting strategy.
7. A safe unlocking method based on electroencephalogram authentication is characterized in that a first-layer identity authentication is carried out based on the electroencephalogram signal-based identity authentication method of any one of claims 1 to 6, a second-layer identity authentication is carried out in combination with a safe password, and a safe unlocking action is carried out after double identity authentication is passed.
8. The utility model provides a safe unblock system based on brain electricity authentication which characterized in that contains: the safe electromagnetic lock comprises an operation panel and a circuit board, wherein the operation panel is arranged on the safe and used for inputting instructions, and the circuit board is connected with the operation panel and used for controlling the electromagnetic lock of the safe to act according to the instruction input; the circuit board is provided with a singlechip for performing data operation processing according to instruction input, and the singlechip is also connected with an electroencephalogram authentication module; the operation panel is provided with an unlocking key, a brain print reading key, a password input keyboard and an identity authentication key, wherein the unlocking key is sequentially connected with the single chip microcomputer and used for inputting a safe unlocking instruction, the brain print reading key is used for inputting a first layer of identity authentication, the password input keyboard is used for inputting a second layer of identity authentication, and the identity authentication key is used for inputting an authentication instruction; the brain electricity authentication module comprises: a wearable device and a brain print authentication unit; wherein the content of the first and second substances,
the wearable device is used for reading a key instruction according to brain lines fed back by the single chip microcomputer and acquiring electroencephalograms under visual playing paradigms under at least two different security levels, wherein the visual playing paradigms comprise a resting state paradigms and a face stimulation paradigms, and sample data of the face stimulation paradigms comprise face images of a tested person and strange face images which are used for acquiring the electroencephalograms and have known identity information;
the brain print authentication unit is used for respectively extracting the characteristics of the extracted electroencephalogram signals from a time domain, a frequency domain and a time-frequency domain according to the identity authentication instruction fed back by the single chip microcomputer and classifying the electroencephalogram signals by using an integrated classifier; and judging the identity of the detected person according to the classification result.
9. The safe unlocking system based on electroencephalogram authentication as claimed in claim 8, wherein the single chip microcomputer is further connected with an alarm for alarming and reminding an unlocking instruction under the condition that the identity authentication fails.
10. A computer-readable medium, on which a computer program for execution by a processor is stored, the computer program being adapted to perform the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010275632.4A CN111653005A (en) | 2020-04-09 | 2020-04-09 | Identity authentication method based on electroencephalogram signal, and safe unlocking method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010275632.4A CN111653005A (en) | 2020-04-09 | 2020-04-09 | Identity authentication method based on electroencephalogram signal, and safe unlocking method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111653005A true CN111653005A (en) | 2020-09-11 |
Family
ID=72346118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010275632.4A Pending CN111653005A (en) | 2020-04-09 | 2020-04-09 | Identity authentication method based on electroencephalogram signal, and safe unlocking method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111653005A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113855019A (en) * | 2021-08-25 | 2021-12-31 | 杭州回车电子科技有限公司 | Expression recognition method and device based on EOG, EMG and piezoelectric signals |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1892674A1 (en) * | 2006-08-23 | 2008-02-27 | Siemens Aktiengesellschaft | Brain pattern based access control system |
| CN107045744A (en) * | 2017-04-14 | 2017-08-15 | 特斯联（北京）科技有限公司 | A kind of intelligent villa entrance guard authentication method and system |
| WO2018112799A1 (en) * | 2016-12-21 | 2018-06-28 | 华为技术有限公司 | Visual evoked potential-based identity verification method and device |
| CN108968954A (en) * | 2018-06-07 | 2018-12-11 | 杭州航弈生物科技有限责任公司 | Wearable EEG signals and electromyography signal amplifier based on ADS1299 |
| CN110135285A (en) * | 2019-04-26 | 2019-08-16 | 中国人民解放军战略支援部队信息工程大学 | It is a kind of to use the brain electrical silence state identity identifying method and device of singly leading equipment |
-
2020
- 2020-04-09 CN CN202010275632.4A patent/CN111653005A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1892674A1 (en) * | 2006-08-23 | 2008-02-27 | Siemens Aktiengesellschaft | Brain pattern based access control system |
| WO2018112799A1 (en) * | 2016-12-21 | 2018-06-28 | 华为技术有限公司 | Visual evoked potential-based identity verification method and device |
| CN107045744A (en) * | 2017-04-14 | 2017-08-15 | 特斯联（北京）科技有限公司 | A kind of intelligent villa entrance guard authentication method and system |
| CN108968954A (en) * | 2018-06-07 | 2018-12-11 | 杭州航弈生物科技有限责任公司 | Wearable EEG signals and electromyography signal amplifier based on ADS1299 |
| CN110135285A (en) * | 2019-04-26 | 2019-08-16 | 中国人民解放军战略支援部队信息工程大学 | It is a kind of to use the brain electrical silence state identity identifying method and device of singly leading equipment |
Non-Patent Citations (1)
| Title |
|---|
| 巫群健: "基于视觉诱发脑电信号的身份认证技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113855019A (en) * | 2021-08-25 | 2021-12-31 | 杭州回车电子科技有限公司 | Expression recognition method and device based on EOG, EMG and piezoelectric signals |
| CN113855019B (en) * | 2021-08-25 | 2023-12-29 | 杭州回车电子科技有限公司 | Expression recognition method and device based on EOG (Ethernet over coax), EMG (electro-magnetic resonance imaging) and piezoelectric signals |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Convolutional neural networks using dynamic functional connectivity for EEG-based person identification in diverse human states | |
| Vařeka et al. | Stacked autoencoders for the P300 component detection | |
| Wang et al. | Local temporal common spatial patterns for robust single-trial EEG classification | |
| CN111329474B (en) | Electroencephalogram identity recognition method and system based on deep learning and information updating method | |
| Puengdang et al. | EEG-based person authentication method using deep learning with visual stimulation | |
| CN109784023A (en) | Stable state vision inducting brain electricity personal identification method and system based on deep learning | |
| Lai et al. | Arrangements of resting state electroencephalography as the input to convolutional neural network for biometric identification | |
| Ravi et al. | Leave-one-out authentication of persons using 40 Hz EEG oscillations | |
| Tatar | Biometric identification system using EEG signals | |
| Gu et al. | A domain generative graph network for EEG-based emotion recognition | |
| CN111653005A (en) | Identity authentication method based on electroencephalogram signal, and safe unlocking method and system | |
| Rathi et al. | Towards a role-based authentication system based on SSVEP-P300 hybrid brain–computer interfacing | |
| Wang et al. | DE-CNN: An Improved Identity Recognition Algorithm Based on the Emotional Electroencephalography. | |
| Walia et al. | Human recognition via PPG signal using temporal correlation | |
| Attallah | Multi-tasks biometric system for personal identification | |
| Boubakeur et al. | EEG-based person recognition analysis and criticism | |
| Liu et al. | EEG-based familiar and unfamiliar face classification using differential entropy feature | |
| CN114931362A (en) | Cross-patient epileptic wave detection method and system based on differential matrix and storage medium | |
| Bak et al. | User biometric identification methodology via EEG-based motor imagery signals | |
| Kang et al. | EEG feature selection and the use of Lyapunov exponents for EEG-based biometrics | |
| Tong et al. | Sleep quality estimation with adversarial domain adaptation: From laboratory to real scenario | |
| Kolivand | Brain signals as a new biometric authentication method using brain-computer interface | |
| Liao et al. | Single-trial EEG predicts memory retrieval using leave-one-subject-out classification | |
| Singh et al. | P300 brain waves instigated semi supervised video surveillance for inclusive security systems | |
| Tangkraingkij et al. | An appropriate number of neurons in a hidden layer for personal authentication using delta brainwave signals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200911 |