CN110598625A - Identity recognition technology based on pulse wave non-reference characteristics - Google Patents
Identity recognition technology based on pulse wave non-reference characteristics Download PDFInfo
- Publication number
- CN110598625A CN110598625A CN201910855286.4A CN201910855286A CN110598625A CN 110598625 A CN110598625 A CN 110598625A CN 201910855286 A CN201910855286 A CN 201910855286A CN 110598625 A CN110598625 A CN 110598625A
- Authority
- CN
- China
- Prior art keywords
- pulse wave
- current user
- signal
- user
- pulse
- 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
- 238000005516 engineering process Methods 0.000 title description 5
- 238000000034 method Methods 0.000 claims abstract description 45
- 238000005259 measurement Methods 0.000 claims abstract description 14
- 230000000737 periodic effect Effects 0.000 claims abstract description 8
- 238000013186 photoplethysmography Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 230000008602 contraction Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000033001 locomotion Effects 0.000 claims description 3
- 230000003205 diastolic effect Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 claims 1
- 238000010408 sweeping Methods 0.000 abstract 1
- 210000004369 blood Anatomy 0.000 description 13
- 239000008280 blood Substances 0.000 description 13
- 210000001367 artery Anatomy 0.000 description 5
- 210000004204 blood vessel Anatomy 0.000 description 4
- 210000001519 tissue Anatomy 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000017531 blood circulation Effects 0.000 description 3
- 210000000988 bone and bone Anatomy 0.000 description 3
- 238000005336 cracking Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 210000000709 aorta Anatomy 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005021 gait Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 210000005240 left ventricle Anatomy 0.000 description 1
- 230000031700 light absorption Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 238000007430 reference method Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
- 210000000707 wrist Anatomy 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- 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
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- 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)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Veterinary Medicine (AREA)
- Physiology (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Cardiology (AREA)
- General Physics & Mathematics (AREA)
- Power Engineering (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 identifying the identity of a user based on pulse wave non-reference characteristics, which can effectively improve the accuracy of identifying the identity of the user by the pulse wave under the scenes of equipment unlocking, pulse sweeping payment and the like which need identity authentication, thereby improving the safety of the personal, property, information and the like of the user. The method comprises the following steps: acquiring a pulse wave measuring signal of a current user; removing various noises from the pulse wave measurement signal of the current user; segmenting the pulse wave signal by identifying a certain periodic characteristic of the pulse wave; statistically extracting non-reference characteristics of the segmented pulse waves based on the overall signal form; and judging whether the current user is the target user or not through the recognition model.
Description
Technical Field
The present application relates to the field of information and security, and more particularly, to a user identification method.
Background
The biometric identification techniques that are commonly used at present are fingerprint identification techniques and face identification techniques. The fingerprint and the face feature of the human body have long-term invariance and uniqueness, so that different people can be identified by using the features of the human body. These user identification technologies are most widely used in mobile phones and some access control systems. However, fingerprints can be copied by a method such as a mold, and face recognition can also be cracked by artificial videos or a 3D printing face mold.
With the rapid development of the biological information technology, people find that the heartbeat mode has certain uniqueness and can be used for identity recognition. And the pulse information can not be stolen and forged, so that the method is more suitable for being used as an identity identification method. However, a great defect of the current heartbeat mode is that the process is troublesome to adopt, the heartbeat mode is greatly changed by actions such as movement and sleep, and the accuracy of dynamic identity recognition is not high enough.
At present, watson's co-pending patent application CN108513665A by hua corporation utilizes a mode of detecting photoelectric volume pulse waves, and trains a model by using 7 feature values of main peak, main trough, sub-peak, sub-trough, main trough-main trough, main peak-main trough slope, and sub-peak-main trough slope of photoelectric volume pulse waves as input parameters of neural network modeling, thereby determining whether a current user is a target user. However, the accuracy of identification of such methods that rely on reference features (fiduciary features) obtained from PPG signals in the time domain is still low, especially for identification after sports, sleep or long time intervals.
Therefore, how to provide a new pulse wave pattern analysis technology to more accurately identify a user and further improve the safety of the user, such as personal safety, property safety, information safety, and the like is a problem to be solved.
Disclosure of Invention
In order to more accurately identify the user identity and further improve the safety of the person, property, information and the like of the user, the invention provides a method for identifying the user identity based on pulse wave non-reference characteristics.
The method comprises the following steps: acquiring a pulse wave measuring signal of a current user; removing various noises from the pulse wave measurement signal of the current user; segmenting the pulse wave signal by identifying a certain periodic characteristic of the pulse wave; statistically extracting Non-reference features (Non-custom features) from the segmented pulse wave based on the overall signal form; and judging whether the current user is the target user or not through the recognition model.
Optionally, in an implementation manner of the method, when the current user is a target user, the method further includes:
allowing payment (transfer) operations to be made or completed.
Optionally, in the method, the acquired pulse wave signals include, but are not limited to:
photoplethysmography (PPG).
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.
Drawings
Fig. 1 is a schematic flow chart of an identification technique based on pulse wave non-reference features according to the application.
Detailed Description
The technical solution in the present application will be described below with reference to the accompanying drawings.
Fig. 1 shows a schematic flow chart of a method 100 of user identification of the present invention. As shown in fig. 1, the method 100 includes the following:
in 110, a pulse wave measurement signal of a current user is acquired.
Optionally, the obtaining of the pulse wave measurement signal of the current user includes, but is 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.
Specifically, the pulse is an arterial pulse that can be felt on the surface of the human body. The blood is squeezed into the aorta by the contraction of the left ventricle of the heart and then delivered to the systemic arteries. When a large amount of blood enters the artery, the pressure of the artery increases and the caliber expands, so that the artery feels the expansion at a shallow body surface, namely the pulse. That is, the pulse wave is formed by the propagation of the pulsation (vibration) of the heart to the outer periphery along the arterial blood vessel and the blood flow. The pulse wave of each person has uniqueness due to differences in physical conditions of each person, such as differences in blood pumping ability, elasticity of arterial blood vessel walls, caliber and thickness, size of a lumen, density and viscosity of blood, and the like. Therefore, the identification of the user identity can be performed by analyzing the pulse wave signal.
The tissue of the human body is a stable system, but not a static system, as exemplified by wrist tissue, including skin tissue, bone, venous blood, and arterial blood. Among them, skin tissue, venous blood, and bone are relatively static. The blood flow of arterial blood is periodically changed along with heartbeat, when heart contracts, the blood is extruded to each organ of a body, and when a large amount of blood enters an artery, the arterial blood vessel is inflated, the pressure is increased, and the vessel diameter is expanded; when the heart relaxes, blood flows back into the heart from various organs of the body, and the arterial vessels contract, the pressure decreases and the vessel diameter contracts. This process can be detected by measuring the absorption of light by blood, the pressure of blood vessels, the skin micro-vibration caused by pulse beat, etc. to obtain stable pulse wave signals.
According to the above analysis process, the pulse wave contains two pieces of information: reflecting the influence of components such as skin tissues, muscles, bones, venous blood and the like which are kept unchanged on the measurement signal, wherein the components are direct current signal components in the pulse wave measurement signal; the influence of the periodically changing arterial blood on the measurement signal is reflected, and the influence is just an alternating current signal component in the pulse wave measurement signal.
At 120, various types of noise are removed from the pulse wave measurement signal of the current user.
In particular, the detected signal comprises some other noise signal in addition to the pulse wave signal. The noise signal is: chaotic signals, white noise, baseline drift, motion artifacts, respiratory artifacts, and other interfering signals. If the noise signal is not filtered, the accuracy of the recognition model is reduced. Therefore, it is necessary to obtain the pulse wave signal of the current user after denoising through a third-order Butterworth (Butterworth) band-pass filter from the pulse wave measurement signal.
It should be understood that the use of a third-order Butterworth (Butterworth) band-pass filter for filtering the signal in the present application is only an example and is not limiting, and various other filters or other ways to reduce or remove noise may be used, such as gaussian filtering, wavelet transform, fourier transform, etc.
At 130, the pulse wave signal is segmented by identifying some periodic feature of the pulse wave.
Specifically, after various types of noise are removed through filtering, the pulse wave signals are segmented according to the pulse period, and then the non-reference features of each segment of signals can be extracted on the whole waveform. The peak value is detected through a Pan Tompkins algorithm, the contraction peak of the pulse wave can be extracted, and then the pulse wave signal is segmented according to a single heartbeat period.
It should be understood that the detection of the peak by the Pan Tompkins algorithm is used in this application only as an example and is not limiting, and other methods may be used to identify a certain periodic characteristic of the pulse wave.
It should be understood that the segmentation of the pulse wave signal by identifying the systolic peaks of the pulse wave in the present application is only an example and does not constitute any limitation, and the pulse wave signal may also be segmented by identifying other periodic features of the pulse wave, such as major troughs, minor peaks (diastolic peaks), minor troughs, and the like.
It should be understood that the periodic characteristics of the pulse wave signal in the time domain are used in the present application, and are not limited in any way, and the frequency domain characteristics of the pulse wave signal may be used as well.
At 140, non-reference features are statistically extracted for the segmented pulse wave based on the overall signal morphology.
In particular, in the fiducial point method, the most commonly used feature is a local marker based on the heartbeat, such as the time or amplitude difference between successive fiducial markers. For a pulse wave signal, the reference feature is usually determined by the original pulse wave signal and its first and second derivatives, such as main peak (systolic peak), main trough, secondary peak, secondary trough, main trough-main trough, main peak-main trough slope, secondary peak-main trough slope, etc. However, even if the raw measurement signal is denoised or denoised, the peak detection may be unreliable, for example, noise at the reference point may affect the accuracy of the identification, resulting in false and false positives.
The feature extraction of the non-reference method can overcome the defects of the reference feature extraction. After identifying the systolic peak and segmenting the pulse wave signals, a Discrete Wavelet Transform (DWT) is used to perform a windowing process on each segment of the pulse wave signals. Wavelet transform is a local transformation in time and frequency that can effectively extract information from a signal. Thus, discrete wavelet transforms can be used to extract non-reference features of segmented pulse wave signals.
It should be understood that the discrete wavelet transform is used in the present application to extract the non-reference features by way of example only and is not limiting, and may be implemented by continuous wavelet transform, fourier transform, short-time fourier transform, Wigner-Ville distribution, hilbert-yellow transform, s-transform, generalized s-transform, and the like.
It should be understood that the non-reference feature of the pulse wave signal in the time domain is extracted in the present application, and does not constitute any limitation, and the non-reference feature of the pulse wave signal in the frequency domain may also be extracted.
At 150, it is determined whether the current user is a target user through the recognition model.
Specifically, the label value of the non-reference feature set of the pulse wave signal of the target user acquired when the information is entered is set to "1"; and setting the label value of the pre-stored non-reference feature set of other pulse wave signals as 0, and then performing neural network algorithm training by taking the label value as a training set to establish the recognition model.
And inputting the non-reference characteristics of the pulse wave signal of the current user into the identification model as parameters according to the pulse wave signal of the current user detected currently, and obtaining the label value output by the identification model. If the label value output by the identification model is '1', determining that the current user is the target user; and if the label value output by the identification model is 0, determining that the current user is not the target user.
It should be understood that the label values set to "1" and "0" in the present application do not constitute any limitation, and may be set to other label values such as "True" and "False" as well.
It should be understood that the identification model established by using the neural network algorithm is only used as an example in the present application, and is not limited in any way, and the identification model may also be established by using a machine learning or deep learning algorithm such as a Support Vector Machine (SVM), LDA, DLDA, KNN, PCA, and the like.
And identifying whether the current user is the target user or not based on the identification model, and correcting the identification model.
Optionally, the method further comprises: upon determining that the current user is the target user, a payment (transfer) operation is allowed or completed.
Because face identification, fingerprint identification all have comparatively ripe cracking means, password protection is forgotten comparatively easily and also has certain comparatively ripe cracking means, in this application, judges whether this current user is the target user through discerning this current user's pulse wave signal for payment or transfer process are more convenient and the security is higher.
In addition, for a high-volume account or sensitive operation with high safety requirements, a plurality of other protection schemes can be configured while pulse wave identification is performed, and equipment can be unlocked only by one or more verification modes of identification modes such as password verification, face identification, gait identification, fingerprint identification, iris identification and vein identification.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other ways. For example, the embodiments of the method described above are merely illustrative: for example, the division of the units is only one logical division, and the actual implementation may have another division, 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.
The units described as separate steps may or may not be physically separate, and components displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application 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 computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including 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 method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (11)
1. A method for user identity recognition based on pulse wave non-reference features is characterized by comprising the following steps: acquiring a pulse wave measuring signal of a current user; removing various noises from the pulse wave measurement signal of the current user; segmenting the pulse wave signal by identifying a certain periodic characteristic of the pulse wave; statistically extracting non-reference characteristics of the segmented pulse waves based on the overall signal form; and judging whether the current user is the target user or not through the recognition model.
2. The method according to claim 1, wherein when the current user is the target user, the method further comprises:
allowing payment (transfer) operations to be made or completed.
3. The method according to claims 1 to 2, wherein said obtaining a pulse wave measurement signal of a current user includes but is 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 removing of various types of noise from the pulse wave measurement signal of the current user includes but is not limited to:
and filtering low-frequency and high-frequency noise by using a filter or other modes, removing disordered signals, white noise, baseline drift, motion artifacts, respiration artifacts and other interference signals, and obtaining the noise-reduced pulse wave signal of the current user.
5. The method according to claims 1 to 4, wherein the pulse wave signal is segmented by identifying a certain periodic characteristic of the pulse wave, including but not limited to:
the algorithm detects one or some characteristics which periodically appear in the pulse wave, and then the pulse wave signal is segmented according to a single heartbeat period.
6. The method of claim 5, wherein the algorithm for detecting the periodically occurring features of the pulse wave includes, but is not limited to:
pan Tompkins algorithm.
7. The method of claim 5, wherein the periodically occurring features in the pulse wave include, but are not limited to:
major peaks (systolic peaks), major troughs, minor peaks (diastolic peaks), minor troughs, and the like.
8. The method as claimed in claims 1 to 7, wherein the pair of segmented pulse waves statistically extracts non-reference features based on overall signal morphology, including but not limited to:
after identifying the contraction peak and segmenting the pulse wave signals, performing window processing on each segment of pulse wave signals by Discrete Wavelet Transform (DWT) to extract the non-reference characteristics of each segment of pulse wave signals;
the extraction of the non-reference features can also be realized by methods such as continuous wavelet transform, Fourier transform, short-time Fourier transform, Wigner-Ville distribution, Hilbert-Huang transform, S transform, generalized S transform and the like.
9. The method of claims 1 to 8, wherein said determining whether the current user is the target user through the recognition model includes but is not limited to:
setting the label value of the non-reference characteristic set of the pulse wave signal of the target user, which is acquired during information input, as a first-class label, setting the label value of the pre-stored non-reference characteristic set of other pulse wave signals as a second-class label, and then performing algorithm training by taking the second-class label as a training set to establish the identification model;
inputting the non-reference characteristics of the pulse wave signal of the current user into the identification model as parameters according to the pulse wave signal of the current user detected currently to obtain a label value output by the identification model;
and if the label value output by the identification model is the first type of label, determining that the current user is the target user, and if the label value output by the identification model is the second type of label, determining that the current user is not the target user.
10. The method according to claims 1 to 9, characterized in that the extracted characteristic parameters of the user's pulse wave are:
non-reference features are statistically extracted based on the overall signal morphology of the pulse wave.
11. The method according to claims 1 to 10, wherein the parameters entered in the creation and use of the recognition model are:
non-reference features are statistically extracted based on the overall signal morphology of the pulse wave.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910855286.4A CN110598625A (en) | 2019-09-10 | 2019-09-10 | Identity recognition technology based on pulse wave non-reference characteristics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910855286.4A CN110598625A (en) | 2019-09-10 | 2019-09-10 | Identity recognition technology based on pulse wave non-reference characteristics |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110598625A true CN110598625A (en) | 2019-12-20 |
Family
ID=68858737
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910855286.4A Pending CN110598625A (en) | 2019-09-10 | 2019-09-10 | Identity recognition technology based on pulse wave non-reference characteristics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110598625A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111444489A (en) * | 2020-01-06 | 2020-07-24 | 北京理工大学 | Double-factor authentication method based on photoplethysmography sensor |
CN111507944A (en) * | 2020-03-31 | 2020-08-07 | 北京百度网讯科技有限公司 | Skin smoothness determination method and device and electronic equipment |
CN111783715A (en) * | 2020-07-10 | 2020-10-16 | 安徽建筑大学 | Identity recognition method based on pulse signal feature extraction |
CN113229787A (en) * | 2021-03-22 | 2021-08-10 | 安庆师范大学 | Blood vessel age estimation and effectiveness evaluation method based on pulse signal shape characteristics |
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 |
CN114158049A (en) * | 2021-12-14 | 2022-03-08 | 哈尔滨工业大学 | Bluetooth communication identity recognition method, system, computer and storage medium |
CN114239649A (en) * | 2021-07-15 | 2022-03-25 | 电子科技大学 | Identity recognition method for discovering and recognizing new user by facing photoelectric volume pulse wave signal of wearable device |
CN115040089A (en) * | 2022-08-16 | 2022-09-13 | 之江实验室 | Pulse wave peak value detection and classification method and device based on deep learning |
CN115830656A (en) * | 2022-12-08 | 2023-03-21 | 辽宁科技大学 | Identity recognition method and device based on pulse wave |
Citations (1)
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 |
-
2019
- 2019-09-10 CN CN201910855286.4A patent/CN110598625A/en active Pending
Patent Citations (1)
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 |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111444489B (en) * | 2020-01-06 | 2022-10-21 | 北京理工大学 | Double-factor authentication method based on photoplethysmography sensor |
CN111444489A (en) * | 2020-01-06 | 2020-07-24 | 北京理工大学 | Double-factor authentication method based on photoplethysmography sensor |
CN111507944A (en) * | 2020-03-31 | 2020-08-07 | 北京百度网讯科技有限公司 | Skin smoothness determination method and device and electronic equipment |
CN111507944B (en) * | 2020-03-31 | 2023-07-04 | 北京百度网讯科技有限公司 | Determination method and device for skin smoothness and electronic equipment |
CN111783715A (en) * | 2020-07-10 | 2020-10-16 | 安徽建筑大学 | Identity recognition method based on pulse signal feature extraction |
CN111783715B (en) * | 2020-07-10 | 2024-04-23 | 安徽建筑大学 | Identity recognition method based on pulse signal feature extraction |
CN113229787A (en) * | 2021-03-22 | 2021-08-10 | 安庆师范大学 | Blood vessel age estimation and effectiveness evaluation method based on pulse signal shape characteristics |
CN114239649A (en) * | 2021-07-15 | 2022-03-25 | 电子科技大学 | Identity recognition method for discovering and recognizing new user by facing photoelectric volume pulse wave signal of wearable device |
CN114239649B (en) * | 2021-07-15 | 2023-04-07 | 电子科技大学 | Identity recognition method for discovering and recognizing new user by photoelectric volume pulse wave signal of wearable device |
CN114158049A (en) * | 2021-12-14 | 2022-03-08 | 哈尔滨工业大学 | Bluetooth communication identity recognition method, system, computer and storage medium |
CN114158049B (en) * | 2021-12-14 | 2024-03-26 | 哈尔滨工业大学 | Bluetooth communication identity recognition method, system, computer and storage medium |
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 |
CN115040089A (en) * | 2022-08-16 | 2022-09-13 | 之江实验室 | Pulse wave peak value detection and classification method and device based on deep learning |
CN115830656A (en) * | 2022-12-08 | 2023-03-21 | 辽宁科技大学 | Identity recognition method and device based on pulse wave |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110598625A (en) | Identity recognition technology based on pulse wave non-reference characteristics | |
CN106473750B (en) | Personal identification method based on photoplethysmographic optimal period waveform | |
Bonissi et al. | A preliminary study on continuous authentication methods for photoplethysmographic biometrics | |
US8232866B2 (en) | Systems and methods for remote long standoff biometric identification using microwave cardiac signals | |
Tantawi et al. | A wavelet feature extraction method for electrocardiogram (ECG)-based biometric recognition | |
Iwasokun et al. | Fingerprint image enhancement: Segmentation to thinning | |
US20180068193A1 (en) | Method, Apparatus And System For Biometric Identification | |
Labati et al. | ECG biometric recognition: Permanence analysis of QRS signals for 24 hours continuous authentication | |
Ghofrani et al. | Reliable features for an ECG-based biometric system | |
Choudhary et al. | Robust photoplethysmographic (PPG) based biometric authentication for wireless body area networks and m-health applications | |
Choi et al. | User Authentication System Based on Baseline-corrected ECG for Biometrics. | |
KR20180072290A (en) | Method for generating electrocardiogram for identifying a person and method for identifying a person using the electrocardiogram | |
CN114638272B (en) | Identity recognition method and device based on fingertip pulse wave signals | |
CN113243902B (en) | Feature extraction method based on photoplethysmography | |
Bastos et al. | Double authentication model based on ppg and ecg signals | |
Hwang et al. | Variation-stable fusion for PPG-based biometric system | |
Bandyopadhyay et al. | An unsupervised learning for robust cardiac feature derivation from PPG signals | |
Zhang et al. | Biometric authentication via finger photoplethysmogram | |
Canento et al. | Review and comparison of real time electrocardiogram segmentation algorithms for biometric applications | |
Mesin et al. | A low cost ECG biometry system based on an ensemble of support vector machine classifiers | |
CN114259225B (en) | Identity recognition method and system based on millimeter wave radar | |
Kumar et al. | Analysis of Phonocardiogram signal for biometric identification system | |
Aghakabi et al. | Fusing dorsal hand vein and ECG for personal identification | |
Namini et al. | Implementation of artificial features in improvement of biometrics based PPG | |
Lynn et al. | ECG-based biometric human identification based on backpropagation neural network |
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 |