CN110598626A - Unlocking method based on pulse wave - Google Patents
Unlocking method based on pulse wave Download PDFInfo
- Publication number
- CN110598626A CN110598626A CN201910855287.9A CN201910855287A CN110598626A CN 110598626 A CN110598626 A CN 110598626A CN 201910855287 A CN201910855287 A CN 201910855287A CN 110598626 A CN110598626 A CN 110598626A
- Authority
- CN
- China
- Prior art keywords
- pulse wave
- signal
- password
- pulse
- current user
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012545 processing Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000000737 periodic effect Effects 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 238000013186 photoplethysmography Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims 4
- 238000002790 cross-validation Methods 0.000 claims 2
- 230000001121 heart beat frequency Effects 0.000 claims 1
- 230000002787 reinforcement Effects 0.000 claims 1
- 238000005728 strengthening Methods 0.000 claims 1
- 238000000605 extraction Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 3
- 238000005316 response function Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 210000001765 aortic valve Anatomy 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 230000008321 arterial blood flow Effects 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000036581 peripheral resistance Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000002861 ventricular Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- 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
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- 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
- G06F2218/16—Classification; Matching by matching signal segments
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Physiology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Cardiology (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention provides a method for unlocking based on pulse waves, which can be applied to the protection of various confidential documents and private information and effectively improve the protection degree of the confidential information. The method comprises an acquisition module, an identification module and an unlocking module.
Description
Technical Field
The present application relates to the field of information and security, and more particularly, to an unlocking method for designing a physical lock device and an electronic lock device
Background
The conventional unlocking technology comprises a key and other object understanding locking tools and electronic unlocking tools such as electronic passwords and face recognition, and the purpose of unlocking target equipment can be achieved by applying the corresponding correct key and the electronic unlocking tools, so that the target environment is entered. Is also two unlocking means which are most widely applied at present. However, the physical understanding lock means can be easily and directly imitated by a lock hole die and the like, and the key itself as a solid object has the risk of losing or being stolen; electronic passwords are becoming more susceptible to cracking by network hackers and the like due to the increasing development of computer technology; the face recognition can also be cracked in a mode of artificial video or 3D printing of a mold, so that certain influence is caused on information or other safety.
With the continuous development of the biological information technology, people find that the heartbeat pattern is also unique and can utilize the heartbeat pattern to carry out the characteristic of identity recognition. Different from the traditional unlocking means, the pulse information is difficult to steal and cannot be counterfeited, and the unlocking tool is more suitable for being used as an unlocking tool in safety. However, a great defect of the existing heartbeat mode is that the process is troublesome to adopt, the heartbeat mode is greatly changed due to actions such as movement, and the accuracy of dynamic identity recognition is not high enough.
Disclosure of Invention
The invention provides an unlocking method based on pulse waves, which aims to solve the problems existing in the current stages of a physical lock and an electronic coded lock and improve the safety in the aspects of property, information and the like.
The method comprises an acquisition module (acquiring a password pulse wave signal, segmenting the password pulse wave signal, carrying out algorithm processing and feature extraction, establishing a feature set of the password pulse wave, acquiring a pulse wave signal of a current user), an identification module (judging whether the current pulse wave signal is consistent with the password pulse wave feature) and an unlocking module (unlocking equipment when the feature consistent degree reaches a preset value)
Drawings
Fig. 1 is a schematic flow chart of an unlocking method based on pulse wave non-reference characteristics according to the application.
Detailed Description
The technical solution of the present application will be described below with reference to the accompanying drawings.
Fig. 1 shows a schematic flow diagram of a method 100 for unlocking according to the invention. As shown in fig. 1, the method 100 includes the following:
at 110, the obtaining module includes, but is not limited to, obtaining the password pulse wave signal, segmenting the password pulse wave signal and performing algorithm processing and feature extraction, establishing a feature set of the password pulse wave, obtaining the pulse wave signal of the current user
Optionally, a cryptographically encrypted pulse wave measurement signal is obtained, including but not limited to:
photoplethysmography signals.
The pulse beat signals are identified by various pressure sensors.
The pulse beat identified by various micro-vibration sensors leads to signals of micro-vibration of the skin.
The pulse formation depends on the cardiac relaxation and the distensibility and elasticity of the arterial wall, and the two indexes are different from person to person, so that pulses with different forms are formed. Every pulse wave trace curve of human pulse signals recorded by the existing pulse scanner is composed of ascending branch A and descending branch K, the ascending branch reflects passive expansion of the artery in the ventricular rapid ejection blood, and the descending branch reflects retraction of the blood in the later period. The ventricles then relax and the pressure in the ventricles is lower than the aortic pressure, and the arterial blood flows back, causing the aortic valve to close, forming a descending branch notch N, also called the descending isthmus or heavy trough, on the curve. The retrograde blood flow continues forward due to the closure of the aortic valve and a rising wavelet, called falling wavelet or heavy pulse, appears after the notch. The shape of the descending branch is related to the size of the peripheral resistance; if the resistance is large, the descending slope is gentle, and the position of the notch is high; otherwise, the position of the notch is lower. It should be understood that the pulse scanner is used in the present application for signal acquisition of human body pulse, which is only an example and not a limitation, and other various methods for acquiring human body pulse signals, such as a pressure sensor, an infrared sensor, etc., may also be used.
Specific characteristics can be separated by recording pulse signals with the set password and carrying out non-reference characteristic analysis on the pulse signals, so that the characteristics are used as an important standard for judging the password, and the effect same as that of the current common password is achieved.
Segmenting password pulse wave signals, algorithm processing and feature extraction
Specifically, after the acquired pulse signal of the human body, the pulse signal needs to be segmented, feature extraction is performed by using a single-period or multi-period pulse signal waveform, the feature extraction can perform multi-dimensional feature extraction on a frequency domain by using fourier transform, and a multi-dimensional gaussian function is generated by using gaussian distribution analysis and is used as a judgment standard of the similarity.
It should be understood that the feature extraction performed by using the single-period or multi-period pulse signal in the present application is not limited, and the feature extraction may be performed by using a method including, but not limited to, a pulse peak value, a peak-to-peak value difference, a waveform area, and the like
It should be understood that the multi-dimensional feature extraction in the frequency domain is performed by fourier transform in the present application, and is not limited in any way, and wavelet transform, laplace transform, and the like may be used as well.
It should be understood that, in the present application, the multidimensional gaussian function generated by using gaussian distribution analysis is used as the criterion for evaluation, and the final criterion for evaluation may also be performed by using an optimal interval classifier, factor analysis, a gaussian mixture model, principal component analysis, and the like.
Establishing a set of features for a cryptographic pulse wave
For the gaussian distribution analysis method, the formed main feature set is: after the waveform is subjected to segmented periodic Fourier transform, the formed amplitude-frequency is considered to be positioned in a multi-dimensional space, and because the frequency and the intensity characteristic of a pulse wave signal generated in each period of a human body are approximately similar under the condition that the state of the human body is not greatly transformed, a multi-dimensional Gaussian function with a mean value point as the center is generated around the mean value point in a multi-dimensional space data set, wherein the main parameters are space dimensions, data set mean values, data set covariance matrixes and the like
It should be understood that, in the present application, the gaussian distribution method is only used as an example and is not limited in any way, and the feature extraction may also be performed by using naive bayes, a filtering algorithm, a support vector machine, or the like.
It should be understood that, in the present application, the waveform is subjected to the piecewise periodic fourier transform, which is not limited at all, and the piecewise periodic signal, such as characteristic information of a peak value, a waveform area, and the like, may be used, and the processing method may be a processing method such as laplace transform, short-time fourier transform, wavelet transform, and the like.
It should be understood that, in the present application, the main parameters are spatial dimension, mean value of data set, covariance matrix of data set, etc., and do not constitute any limitation, and parameters such as centroid of class, tilt value in principal component analysis, etc. of clustering algorithm may also be used
The method and principle for obtaining the pulse wave signal of the current user are the same as those for obtaining the password pulse wave measurement signal, and are not described herein again.
In 120, the identification module determines whether the current pulse wave signal matches the password pulse wave characteristics, and determines whether the current user is the target user
Optionally, for the known feature set and the fitting function after the parameters are optimized, a regular response function may be used for feature inspection, and when the inner product of the parameters and the features is greater than 0, the regular response function may determine that the similarity requirement standard is met, so that the password authentication is passed.
It should be understood that, in the present application, the feature similarity may be verified by using a regular response function, which is not limited in any way, and may also be verified by using a multidimensional gaussian distribution function, a weighted analysis, or the like.
It should be understood that in the present application, the criterion for determining the load similarity is required so as to pass the password authentication, and is not limited in any way. Besides direct verification, subsequent or preliminary verification methods can also be adopted, including but not limited to re-verification for special cases with 100% pulse wave similarity, and the like.
At 130, the unlocking module includes unlocking the device when the degree of feature compliance reaches a predetermined value
If the degree of matching of the feature set is higher than 97%, the current user can basically be considered as the target user. For the electromagnetic lock, after the matching signal is sent out, the electromagnet can temporarily cut off the power supply, and the electromagnet is invalid, so that the aim of unlocking is fulfilled.
It should be understood that, in the present application, the matching degree is higher than 97%, which is not limited in any way, and other threshold values or a varying matching degree function may be set by using the specific feature number of the feature set.
It should be understood that in the present application, the electromagnetic lock is only used as an example and is not limited in any way, and a mechanical lock, a gear lock or other various lock types capable of applying electronic unlocking may be used.
Claims (12)
1. An unlocking method based on pulse waves is characterized by comprising the following steps: the device comprises an acquisition module, an identification module and an unlocking module.
2. The method of claim 1, wherein the pulse wave signal of the current user is acquired using an acquisition module.
3. The method according to claims 1 to 2, wherein the acquisition module acquires the pulse wave measurement signal of the current user, including but not limited to:
photoplethysmography (PPG);
pulse beat signals identified by various pressure sensors;
the pulse beat identified by various micro-vibration sensors leads to signals of micro-vibration of the skin.
4. The method according to claims 1 to 3, wherein the acquisition module segments and processes the acquired pulse wave signals, including but not limited to:
the specific heartbeat frequency period of the pulse is segmented, the periodic characteristics appearing in the pulse wave are detected through an algorithm, and the pulse wave is extracted to include but not limited to peak value, area, pulse width and the like.
5. The method of claims 1 to 4, wherein the signal periodicity characteristics are processed, including but not limited to:
and the characteristic processing is realized by methods such as discrete wavelet transform, continuous wavelet transform, Fourier transform, short-time Fourier transform, S transform, generalized S transform and the like.
6. The method according to claims 1 to 5, wherein the obtaining module processes the features of the obtained password pulse wave and then generates a feature set through an algorithm, including but not limited to:
carrying out segmentation and feature processing on the password signals with different lengths, training by using algorithms such as Gaussian distribution analysis, a support vector machine, a clustering algorithm, reinforcement learning and the like, carrying out self-inspection on the algorithms by using methods such as cross validation and the like, obtaining optimized parameters, and establishing a feature recognition model;
and (3) carrying out segmentation processing of different lengths based on the pulse wave overall signal and statistically extracting features.
7. The method of claim 1, wherein the determining whether the current user is the target user is performed by identifying a feature set, including but not limited to:
and performing algorithm processing on the pulse wave of the user when the password is set, extracting a feature set of the pulse wave, setting feature set data as a feature vector space, performing strengthening training by using algorithms such as cross validation and the like, and establishing an identification model of the system.
And according to the currently acquired pulse wave signal, performing feature processing on the pulse wave signal to obtain a feature set of the pulse wave signal, and comparing the feature set with the feature set of the password pulse wave signal to judge whether the current user is a target user.
8. The method as claimed in claims 1 to 7, wherein the identification module performs the same processing on the acquired pulse wave signal as the password signal, compares the processed signal characteristics with the characteristic set of the password signal, and determines whether the current user is the target user through the identification model.
9. The method as claimed in claim 1, wherein the unlocking module determines whether the current user is the target user by recognizing the pulse wave signal of the current user, and when the similarity degree of the features is higher than a predetermined threshold, the current user is considered to be the password signal input person, and the password device is turned on.
10. A method as claimed in any one of claims 1 to 9, wherein when the degree of similarity of features does not reach a threshold value, the user is alerted of a match error and asked to enter again.
11. The method according to claims 1 to 10, characterized in that the characteristic parameters extracted for the user's pulse wave are:
and carrying out segmentation processing of different lengths based on the overall signal of the pulse wave and statistically extracting features.
12. The method of any one of claims 1 to 11, wherein the parameters entered in the creation and use of the recognition model are:
and carrying out segmentation processing of different lengths based on the overall signal of the pulse wave and statistically extracting features.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910855287.9A CN110598626A (en) | 2019-09-10 | 2019-09-10 | Unlocking method based on pulse wave |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910855287.9A CN110598626A (en) | 2019-09-10 | 2019-09-10 | Unlocking method based on pulse wave |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110598626A true CN110598626A (en) | 2019-12-20 |
Family
ID=68858978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910855287.9A Pending CN110598626A (en) | 2019-09-10 | 2019-09-10 | Unlocking method based on pulse wave |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110598626A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114098691A (en) * | 2022-01-26 | 2022-03-01 | 之江实验室 | Pulse wave identity authentication method, device and medium based on Gaussian mixture model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108513665A (en) * | 2017-02-07 | 2018-09-07 | 华为技术有限公司 | The methods, devices and systems of user identity identification |
| CN110123289A (en) * | 2019-04-08 | 2019-08-16 | 清华大学深圳研究生院 | A kind of biometric discrimination method and relevant apparatus based on pulse wave |
-
2019
- 2019-09-10 CN CN201910855287.9A patent/CN110598626A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108513665A (en) * | 2017-02-07 | 2018-09-07 | 华为技术有限公司 | The methods, devices and systems of user identity identification |
| CN110123289A (en) * | 2019-04-08 | 2019-08-16 | 清华大学深圳研究生院 | A kind of biometric discrimination method and relevant apparatus based on pulse wave |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114098691A (en) * | 2022-01-26 | 2022-03-01 | 之江实验室 | Pulse wave identity authentication method, device and medium based on Gaussian mixture model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102367481B1 (en) | Method and device to authenticate living body | |
| Choraś | Ear biometrics based on geometrical feature extraction | |
| Vyas et al. | Iris recognition using 2-D Gabor filter and XOR-SUM code | |
| Yang et al. | A new mixed-mode biometrics information fusion based-on fingerprint, hand-geometry and palm-print | |
| Elgamal et al. | An efficient feature extraction method for iris recognition based on wavelet transformation | |
| Nait-Ali | Hidden biometrics: Towards using biosignals and biomedical images for security applications | |
| Bassiouni et al. | A machine learning technique for person identification using ECG signals | |
| Abikoye Oluwakemi et al. | Iris feature extraction for personal identification using fast wavelet transform (FWT) | |
| Ahmadi et al. | Iris Texture Recognition based on Multilevel 2-D Haar Wavelet Decomposition and Hamming Distance Approach. | |
| Kusban et al. | Combination a skeleton filter and reduction dimension of kernel pca based on palmprint recognition | |
| CN110598626A (en) | Unlocking method based on pulse wave | |
| Khan et al. | Representation of hand dorsal vein features using a low dimensional representation integrating cholesky decomposition | |
| Basit et al. | Iris localization via intensity gradient and recognition through bit planes | |
| Rossan et al. | Impact of changing parameters when preprocessing dorsal hand vein pattern | |
| CN110599188A (en) | Payment means based on pulse wave | |
| Moorthy et al. | Biometric authentication for safety lockers using cardiac vectors | |
| Patil et al. | Iris recognition using gray level co-occurrence matrix and hausdorff dimension | |
| Huang et al. | Iris recognition based on adjustable scale wavelet transform | |
| Yang et al. | Iris recognition based on location of key points | |
| Khan et al. | Feature Extraction of Dorsal Hand Vein Pattern using a fast modified PCA algorithm based on Cholesky decomposition and Lanczos technique | |
| Mobarakeh et al. | Improvement of the Identification Rate using Finger Veins based on the Enhanced Maximum Curvature Method using Morphological Operators | |
| El-Sayed et al. | New approach for identity verification system using the vital features based on entropy | |
| Kamboj et al. | A Review on Segmentation techniques for Iris Recognition System | |
| Choraś | Multimodal biometric personal authentication integrating iris and retina images | |
| Ibrahim et al. | Biometric recognition for safe transaction using vein authentication system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191220 |
|
| WD01 | Invention patent application deemed withdrawn after publication |