CN104545890B - A kind of personal identification method and device based on electrocardiosignal - Google Patents
A kind of personal identification method and device based on electrocardiosignal Download PDFInfo
- Publication number
- CN104545890B CN104545890B CN201410853533.4A CN201410853533A CN104545890B CN 104545890 B CN104545890 B CN 104545890B CN 201410853533 A CN201410853533 A CN 201410853533A CN 104545890 B CN104545890 B CN 104545890B
- Authority
- CN
- China
- Prior art keywords
- electrocardiosignal
- characteristic vector
- heart cycle
- waveform
- characteristic
- 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.)
- Active
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/117—Identification of persons
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The embodiment of the invention discloses a kind of personal identification method based on electrocardiosignal, including：According to the generation method of the characteristic vector of specified electrocardiosignal, the characteristic vector of at least one electrocardiosignal is obtained, and is set to characteristic vector template and is stored in template database；According to the generation method of the characteristic vector of the electrocardiosignal specified, the characteristic vector of electrocardiosignal to be identified is obtained；The characteristic vector template close with the characteristic vector of the electrocardiosignal to be identified is inquired about in the template database, and is the corresponding user identity of this feature vector template by the corresponding user identity identification of the characteristic vector of the electrocardiosignal to be identified.Correspondingly, the embodiment of the invention also discloses a kind of identity recognition device based on electrocardiosignal.Using the present invention, it is possible to achieve carry out identification by electrocardiosignal, what is taken is minimal features point extraction scheme, have the advantages that simple to operate, operand is low and identification accuracy is high.
Description
Technical field
The present invention relates to technical field of biological information, more particularly to a kind of personal identification method and dress based on electrocardiosignal
Put.
Background technology
With the combination and development of biotechnology and information technology, living things feature recognition is most safe as what is generally acknowledged at present
With convenient identity recognizing technology, wherein, biological characteristic include electrocardio (Electrocardiogram, ECG) signal.Electrocardio is believed
Number it is the biopotential signals that human heart bounce is produced, reflects the electrical activity process of heart, it is cardiac due to different people
Put, size, shape, chest construction, age, sex, body weight, the factor such as mood and moving situation are different from, therefore electrocardio is believed
The characteristics of number having uniqueness, available for the identity of identification people, and is difficult to be imitated, steal and forge, with safe
The characteristics of.
What the existing identity recognizing technology based on electrocardiosignal was taken is multi-characteristic points extraction scheme, multi-characteristic points extraction side
Case complex operation, operand are huge.Also, the characteristic point that the existing identity recognizing technology based on electrocardiosignal is extracted does not carry out matter
Amount detection, the electrocardiosignal of Wave anomaly is not only difficult to extract, and can also reduce the accuracy of identification.
The content of the invention
Technical problem to be solved of the embodiment of the present invention is that there is provided a kind of personal identification method based on electrocardiosignal
And device, it is possible to achieve identification is carried out by electrocardiosignal, what is taken is minimal features point extraction scheme, with operation letter
The advantage that single, operand is low and identification accuracy is high.
In order to solve the above-mentioned technical problem, the embodiments of the invention provide a kind of identification side based on electrocardiosignal
Method, including：
According to the generation method of the characteristic vector of specified electrocardiosignal, obtain the feature of at least one electrocardiosignal to
Measure, and be set to characteristic vector template and be stored in template database；
According to the generation method of the characteristic vector of the electrocardiosignal specified, the feature of electrocardiosignal to be identified is obtained
Vector；
The characteristic vector close with the characteristic vector of the electrocardiosignal to be identified is inquired about in the template database
Template, and be that this feature vector template is corresponding by the corresponding user identity identification of the characteristic vector of the electrocardiosignal to be identified
User identity.
Correspondingly, the embodiment of the present invention additionally provides a kind of identity recognition device based on electrocardiosignal, including：
Template memory module, for the generation module of the characteristic vector according to the electrocardiosignal specified, obtains at least one
The characteristic vector of electrocardiosignal, and be set to characteristic vector template and be stored in template database；
Signal acquisition module, for the generation module of the characteristic vector according to the electrocardiosignal specified, obtains and waits to know
The characteristic vector of other electrocardiosignal；
Identification module, in the template database inquiry and the feature of the electrocardiosignal to be identified to
The close characteristic vector template of amount, and be the spy by the corresponding user identity identification of the characteristic vector of the electrocardiosignal to be identified
Levy the corresponding user identity of vector template.
Implement the embodiment of the present invention, have the advantages that：The embodiment of the present invention is first according to the electrocardiosignal specified
Characteristic vector generation method, obtain the characteristic vector of at least one electrocardiosignal, and be set to characteristic vector template and deposit
Then storage still obtains according to the generation method of the characteristic vector of the above-mentioned electrocardiosignal specified in template database and waits to know
The characteristic vector of other electrocardiosignal, and inquire about the characteristic vector template close with it to realize that identity is known in template database
Not, due to taking minimal features point extraction scheme, thus have the advantages that simple to operate, operand is low and identification accuracy is high.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of personal identification method based on electrocardiosignal provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic flow sheet for generating eigenvector method provided in an embodiment of the present invention；
Fig. 3 is a kind of schematic flow sheet for checking feature point methods provided in an embodiment of the present invention；
Fig. 4 is a kind of schematic flow sheet for calculating eigenvector method provided in an embodiment of the present invention；
Fig. 5 is a kind of structural representation of identity recognition device based on electrocardiosignal provided in an embodiment of the present invention；
Fig. 6 is a kind of structural representation of identification module provided in an embodiment of the present invention；
Fig. 7 is the structural representation of the generation module of a feature vectors provided in an embodiment of the present invention；
Fig. 8 is a kind of structural representation of vectorial generation unit provided in an embodiment of the present invention；
Fig. 9 is a kind of schematic diagram of average heart cycle oscillogram provided in an embodiment of the present invention；
Figure 10 is the schematic diagram of a kind of wavelet function provided in an embodiment of the present invention and wavelet scaling function.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Fig. 1 is a kind of schematic flow sheet of personal identification method based on electrocardiosignal in the embodiment of the present invention.As schemed
The flow of the personal identification method based on electrocardiosignal in shown the present embodiment can include：
S101, according to the generation method of the characteristic vector of specified electrocardiosignal, obtains the spy of at least one electrocardiosignal
Vector is levied, and is set to characteristic vector template and is stored in template database.
S102, according to the generation method of the characteristic vector of the electrocardiosignal specified, obtains electrocardiosignal to be identified
Characteristic vector.
S103, inquires about the feature close with the characteristic vector of the electrocardiosignal to be identified in the template database
Vector template, and be this feature vector template pair by the corresponding user identity identification of the characteristic vector of the electrocardiosignal to be identified
The user identity answered.
Specifically, the characteristic vector template in the characteristic vector and template database of electrocardiosignal to be identified is pressed from both sides
Angle cosine value contrast, obtains the maximum characteristic vector template of included angle cosine value, by the characteristic vector of the electrocardiosignal to be identified
Corresponding user identity identification is the corresponding user identity of this feature vector template.
It is pointed out that the generation method of the characteristic vector of the above-mentioned electrocardiosignal specified, what is taken is minimal features
Point extraction scheme, therefore, the embodiment of the present invention is reduced to electrocardiosignal in the case where ensureing high identification accuracy rate
Operation is extracted, operand is reduced.
Further, Fig. 2 is a kind of schematic flow sheet for generating eigenvector method in the embodiment of the present invention.It is of the invention real
Example is applied to carry out in detail for " generation method of the characteristic vector for the electrocardiosignal specified " in step S101 and step S102 in Fig. 1
Describe in detail bright, this method includes：
S201, the electrocardiosignal that collection user inputs in preset time.
The preset time is preset by designer or user, is not construed as limiting here, but in order to ensure the standard of test
True property, typically requires that preset time is more than 10 seconds.
S202, denoising is filtered to the electrocardiosignal of input.
S203, detects the characteristic point of the electrocardiosignal of input.
Detected specifically, carrying out R points (characteristic point) to the electrocardiosignal after denoising after filtering, and then obtain electrocardiosignal
Characteristic point.
S204, by checking the characteristic point of the electric signal, obtains the characteristic point for meeting preset quality requirement.
S205, according to the characteristic point for meeting preset quality requirement, generates the characteristic vector of the electrocardiosignal.
It is pointed out that because the electrocardiosignal of Wave anomaly is not only difficult to extract, can also reduce the standard of identification
True property, therefore, the embodiment of the present invention is by checking characteristic point, it is ensured that the accuracy of identification.
Further, Fig. 3 is a kind of schematic flow sheet for checking feature point methods in the embodiment of the present invention.The present invention is implemented
" characteristic point of the check electric signal " that example is directed in Fig. 2 in step S204 is described in detail, and this method includes：
The spy of S301, the average wave amplitude of the characteristic point of all electrocardiosignals of calculating, and the two neighboring electrocardiosignal
Levy interval duration a little.
S302, obtains wave amplitude higher than the 2/3 of the average wave amplitude, and be more than with the interval duration of adjacent electrocardiosignal or
Characteristic point equal to 0.6 second, this feature point is the characteristic point for meeting preset quality requirement.
It is pointed out that experiments verify that and summary of experience, be typically unsatisfactory for the R points of above-mentioned condition, be all that waveform is different
Normal electrocardiosignal, should skim.
Further, Fig. 4 is a kind of schematic flow sheet for calculating eigenvector method in the embodiment of the present invention.It is of the invention real
Example is applied for " according to the characteristic point for meeting preset quality requirement, generating the electrocardiosignal in step S204 in Fig. 2
Characteristic vector " is described in detail, and this method includes：
S401, is multiple heart cycle waveforms by the feature points segmentation for meeting preset quality requirement.
The multiple heart cycle waveform constitutes heart cycle waveform group.
S402, by default clustering algorithm, is divided into two classes by the multiple heart cycle waveform.
Optionally, the default clustering algorithm is K-means clustering algorithms.Calculated specifically, being clustered by K-means
Method, is divided into two subgroups by heart cycle waveform group.
S403, reservation includes an a fairly large number of class for the heart cycle waveform, and the heart cycle waveform in such is
The heart cycle waveform that waveform does not make a variation.
Specifically, comparing the waveform quantity of two subgroups, retain a wherein more subgroup of heart cycle waveform.Its
In, above-mentioned steps S402 to S403 is the process that multiple heart cycle waveforms are carried out with mode detection, and the purpose of mode detection exists
In the waveform for filtering off variation.
S404, calculates the average heart cycle waveform for the heart cycle waveform that the waveform does not make a variation.
Optionally, implementing process can be realized by following steps：
1. average is asked for the heart cycle waveform that waveform does not make a variation, obtains the first average heart cycle waveform；
2. the auto-correlation coefficient of the first average heart cycle waveform is calculated；
3. the order according to coefficient correlation from big to small, selects 10 maximum the first average heart cycle ripples of autocorrelation
Shape；
4. average is asked for this 10 the first average heart cycle waveforms, obtains the second average heart cycle waveform.Example
Such as, the oscillogram shown in Fig. 9 is referred to.
S405, carries out wavelet decomposition, and obtain the decomposition coefficient of wavelet decomposition to the average heart cycle waveform.
Specifically, carrying out wavelet decomposition to the second average heart cycle waveform, and obtain the decomposition coefficient of wavelet decomposition.
Further, referring to Fig. 10, the process of wavelet decomposition is as follows：
1. it is the similitude for meeting Selection of Wavelet Basis, selection db3 small echos carry out wavelet decomposition as wavelet basis.The small echo
Similar with the waveform of electrocardiosignal, bearing length is 5, and shorter bearing length consumes the shorter calculating time, higher disappearance
Square ensures that more wavelet coefficient is zero or is approximately zero, is conducive to feature extraction and data compression.
2. the second average heart cycle waveform is carried out by 5 grades of wavelet decompositions using db3 small echos, obtains each layer wavelet coefficient,
CA5, cD5, cD4, cD3, cD2 coefficient of decomposition coefficient are taken as characteristic vector.
S406, using the decomposition coefficient as the electrocardiosignal characteristic vector.
It is pointed out that the vectorial wave shape content being made up of cA5, cD5, cD4, cD3, cD2 coefficient of decomposition coefficient is rich
Richness, Different Individual coefficient of wavelet decomposition is more obvious compared with time domain waveform difference, and same individual coefficient of wavelet decomposition waveform is more
Plus stably.
Fig. 5 is a kind of structural representation of the identity recognition device based on electrocardiosignal in the embodiment of the present invention.As schemed
Show identity recognition device in the embodiment of the present invention can at least include template memory module 510, signal acquisition module 520 and
Identification module 530, wherein：
Template memory module 510, for the generation module of the characteristic vector according to the electrocardiosignal specified, obtains at least one
The characteristic vector of individual electrocardiosignal, and be set to characteristic vector template and be stored in template database.
Signal acquisition module 520, for the generation module of the characteristic vector according to the electrocardiosignal specified, acquisition is treated
The characteristic vector of the electrocardiosignal of identification.
Identification module 530, for the inquiry in the template database and the spy of the electrocardiosignal to be identified
The close characteristic vector template of vector is levied, and is by the corresponding user identity identification of the characteristic vector of the electrocardiosignal to be identified
The corresponding user identity of this feature vector template.In the specific implementation, the identification module 530 can enter one as shown in Figure 6
Step includes cosine value comparison unit 531 and template acquiring unit 532, wherein：
Cosine value comparison unit 531, for by the characteristic vector of the electrocardiosignal to be identified and the template data
Characteristic vector template in storehouse carries out included angle cosine value contrast.
Template acquiring unit 532, the characteristic vector template maximum for obtaining included angle cosine value.
It is pointed out that the generation method of the characteristic vector of the above-mentioned electrocardiosignal specified, what is taken is minimal features
Point extraction scheme, therefore, the embodiment of the present invention is reduced to electrocardiosignal in the case where ensureing high identification accuracy rate
Operation is extracted, operand is reduced.
Further, Fig. 7 is the structural representation of the generation module of a feature vectors in the embodiment of the present invention, can be wrapped
Include：
Signal acquiring unit 610, for gathering the electrocardiosignal that user inputs in preset time.
The preset time is preset by designer or user, is not construed as limiting here, but in order to ensure the standard of test
True property, typically requires that preset time is more than 10 seconds.
Signal filtering unit 620, denoising is filtered for the electrocardiosignal to input.
Feature point detection unit 630, the characteristic point of the electrocardiosignal for detecting input.
Detected specifically, carrying out R points (characteristic point) to the electrocardiosignal after denoising after filtering, and then obtain electrocardiosignal
Characteristic point.
Characteristic point checks unit 640, and for the characteristic point by checking the electric signal, acquisition meets preset quality requirement
Characteristic point.
Specifically, the average wave amplitude of the characteristic point of all electrocardiosignals is calculated, and the two neighboring electrocardiosignal
The interval duration of characteristic point, obtains wave amplitude higher than the 2/3 of the average wave amplitude, and is grown up during interval with adjacent electrocardiosignal
In or equal to the characteristic point of 0.6 second, this feature point was the characteristic point for meeting preset quality requirement.It is pointed out that through
Experimental verification and summary of experience, are typically unsatisfactory for the R points of above-mentioned condition, are all the electrocardiosignals of Wave anomaly, should skim.
Vectorial generation unit 650, the characteristic point for meeting preset quality requirement according to, generates the electrocardiosignal
Characteristic vector.In the specific implementation, the vectorial generation unit 650 can further comprise that waveform partition is single as shown in Figure 8
Member 651, waveform obtain subelement 652, waveshape subelement 653 and vector generation subelement 654, wherein：
Waveform partition subelement 651, for being multiple weeks aroused in interest by the feature points segmentation for meeting preset quality requirement
Phase waveform.
The multiple heart cycle waveform constitutes heart cycle waveform group.
Waveform obtains subelement 652, for by carrying out mode detection to the multiple heart cycle waveform, obtaining waveform
The heart cycle waveform not made a variation.
Specifically, by default clustering algorithm, the multiple heart cycle waveform is divided into two classes, retain described in including
An a fairly large number of class for heart cycle waveform, the heart cycle waveform in such is the heart cycle waveform that waveform does not make a variation.
Optionally, the default clustering algorithm is K-means clustering algorithms.Calculated specifically, being clustered by K-means
Method, is divided into two subgroups by heart cycle waveform group.
Waveshape subelement 653, the average heart cycle for calculating the heart cycle waveform that the waveform does not make a variation
Waveform.
Optionally, implementing process can be realized by following steps：
1. average is asked for the heart cycle waveform that waveform does not make a variation, obtains the first average heart cycle waveform；
2. the auto-correlation coefficient of the first average heart cycle waveform is calculated；
3. the order according to coefficient correlation from big to small, selects 10 maximum the first average heart cycle ripples of autocorrelation
Shape；
4. average is asked for this 10 the first average heart cycle waveforms, obtains the second average heart cycle waveform.Example
Such as, the oscillogram shown in Fig. 9 is referred to.
Vector generation subelement 654, for according to the average heart cycle waveform, generating the feature of the electrocardiosignal
Vector.
Specifically, carrying out wavelet decomposition to the average heart cycle waveform, and the decomposition coefficient of wavelet decomposition is obtained, will
The decomposition coefficient as the electrocardiosignal characteristic vector.
Wherein, referring to Fig. 10, the process of wavelet decomposition is as follows：
1. it is the similitude for meeting Selection of Wavelet Basis, selection db3 small echos carry out wavelet decomposition as wavelet basis.The small echo
Similar with the waveform of electrocardiosignal, bearing length is 5, and shorter bearing length consumes the shorter calculating time, higher disappearance
Square ensures that more wavelet coefficient is zero or is approximately zero, is conducive to feature extraction and data compression.
2. the second average heart cycle waveform is carried out by 5 grades of wavelet decompositions using db3 small echos, obtains each layer wavelet coefficient,
CA5, cD5, cD4, cD3, cD2 coefficient of decomposition coefficient are taken as characteristic vector.
It is pointed out that the vectorial wave shape content being made up of cA5, cD5, cD4, cD3, cD2 coefficient of decomposition coefficient is rich
Richness, Different Individual coefficient of wavelet decomposition is more obvious compared with time domain waveform difference, and same individual coefficient of wavelet decomposition waveform is more
Plus stably.
The part that the technical scheme of the embodiment of the present invention substantially contributes to prior art in other words can pass through meter
The form of calculation machine software product is embodied, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disc
Or CD) in, including some instructions are to the portion in the method described by control device execution embodiment of the present invention Fig. 1~Fig. 4
Divide or whole steps.
The embodiment of the present invention according to the generation method of the characteristic vector for the electrocardiosignal specified, obtains at least one heart first
The characteristic vector of electric signal, and be set to characteristic vector template and be stored in template database, then still according to above-mentioned finger
The generation method of the characteristic vector of fixed electrocardiosignal, obtains the characteristic vector of electrocardiosignal to be identified, and in template data
The characteristic vector template close with it is inquired about in storehouse to realize identification, due to taking minimal features point extraction scheme, thus
Have the advantages that simple to operate, operand is low and identification accuracy is high.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or the spy that the embodiment or example are described
Point is contained at least one embodiment of the present invention or example.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area
Art personnel can be tied the not be the same as Example or the feature of example and non-be the same as Example or example described in this specification
Close and combine.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or implying relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or
Implicitly include at least one this feature.In the description of the invention, " multiple " are meant that at least two, such as two, three
It is individual etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, represent to include
Module, fragment or the portion of the code of one or more executable instructions for the step of realizing specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not be by shown or discussion suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Represent in flow charts or logic and/or step described otherwise above herein, for example, being considered use
In the order list for the executable instruction for realizing logic function, it may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress for combining these instruction execution systems, device or equipment and using
Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following：Electricity with one or more wirings
Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, can even is that can be in the paper of printing described program thereon or other are suitable for computer-readable medium
Medium, because can then enter edlin, interpretation or if necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, the software that multiple steps or method can in memory and by suitable instruction execution system be performed with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, the application specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method is carried
Rapid to can be by program to instruct the hardware of correlation to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.In addition, in each embodiment of the invention
In each functional unit can be integrated in a processing module or unit is individually physically present, can also two
Individual or two or more unit is integrated in a module.Above-mentioned integrated module can both be realized in the form of hardware, also may be used
To be realized in the form of software function module.If the integrated module realized using in the form of software function module and as
Independent production marketing in use, can also be stored in a computer read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although having been shown and retouching above
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Above disclosure is only preferred embodiment of present invention, can not limit the right model of the present invention with this certainly
Enclose, therefore the equivalent variations made according to the claims in the present invention, still belong to the scope that the present invention is covered.
Claims (12)
1. a kind of personal identification method based on electrocardiosignal, it is characterised in that methods described includes：
According to the generation method of the characteristic vector of specified electrocardiosignal, the characteristic vector of at least one electrocardiosignal is obtained, and
Characteristic vector template is set to be stored in template database；
According to the generation method of the characteristic vector of the electrocardiosignal specified, obtain the feature of electrocardiosignal to be identified to
Amount；
The characteristic vector template close with the characteristic vector of the electrocardiosignal to be identified is inquired about in the template database,
And be the corresponding user of this feature vector template by the corresponding user identity identification of the characteristic vector of the electrocardiosignal to be identified
Identity；
Wherein, the generation method of the characteristic vector of the electrocardiosignal specified, including：
The electrocardiosignal that collection user inputs in preset time；
Detect the characteristic point of the electrocardiosignal of input；
By checking the characteristic point of the electrocardiosignal, the characteristic point for meeting preset quality requirement is obtained；
According to the characteristic point for meeting preset quality requirement, the characteristic vector of the electrocardiosignal is generated；
Wherein, the characteristic point by checking the electrocardiosignal, obtains the characteristic point for meeting preset quality requirement, including：
Calculate the average wave amplitude of the characteristic point of all electrocardiosignals, and the two neighboring electrocardiosignal characteristic point
It is spaced duration；
Wave amplitude is obtained higher than the 2/3 of the average wave amplitude, and be more than or equal to 0.6 second with the interval duration of adjacent electrocardiosignal
Characteristic point, this feature point is the characteristic point for meeting preset quality requirement.
2. the method as described in claim 1, it is characterised in that the characteristic point of the electrocardiosignal of the detection input it
Before, in addition to：
Denoising is filtered to the electrocardiosignal of input.
3. the method as described in claim 1, it is characterised in that meet the characteristic point of preset quality requirement described in the basis,
The characteristic vector of the electrocardiosignal is generated, including：
It is multiple heart cycle waveforms by the feature points segmentation for meeting preset quality requirement；
By carrying out mode detection to the multiple heart cycle waveform, the heart cycle waveform that waveform does not make a variation is obtained；
Calculate the average heart cycle waveform for the heart cycle waveform that the waveform does not make a variation；
According to the average heart cycle waveform, the characteristic vector of the electrocardiosignal is generated.
4. method as claimed in claim 3, it is characterised in that described by carrying out mode to the multiple heart cycle waveform
Detection, obtains the heart cycle waveform that waveform does not make a variation, including：
By default clustering algorithm, the multiple heart cycle waveform is divided into two classes；
Reservation include an a fairly large number of class for the heart cycle waveform, the heart cycle waveform in such for the waveform not
The heart cycle waveform of variation.
5. method as claimed in claim 3, it is characterised in that described according to the average heart cycle waveform, generation is described
The characteristic vector of electrocardiosignal, including：
Wavelet decomposition is carried out to the average heart cycle waveform, and obtains the decomposition coefficient of wavelet decomposition；
Using the decomposition coefficient as the electrocardiosignal characteristic vector.
6. the method as described in claim 1, it is characterised in that the inquiry in the template database with it is described to be identified
Electrocardiosignal the close characteristic vector template of characteristic vector, including：
Characteristic vector template in the characteristic vector of the electrocardiosignal to be identified and the template database is subjected to angle
Cosine value is contrasted；
Obtain the maximum characteristic vector template of included angle cosine value.
7. a kind of identity recognition device based on electrocardiosignal, it is characterised in that the identity recognition device includes：
Template memory module, for the generation module of the characteristic vector according to the electrocardiosignal specified, obtains at least one electrocardio
The characteristic vector of signal, and be set to characteristic vector template and be stored in template database；
Signal acquisition module, for the generation module of the characteristic vector according to the electrocardiosignal specified, is obtained to be identified
The characteristic vector of electrocardiosignal；
Identification module, for the inquiry in the template database and the characteristic vector phase of the electrocardiosignal to be identified
Near characteristic vector template, and by the corresponding user identity identification of the characteristic vector of the electrocardiosignal to be identified be this feature to
Measure the corresponding user identity of template；
Wherein, the generation module of the characteristic vector of the electrocardiosignal specified, including：
Signal acquiring unit, for gathering the electrocardiosignal that user inputs in preset time；
Feature point detection unit, the characteristic point of the electrocardiosignal for detecting input；
Characteristic point checks unit, for the characteristic point by checking the electrocardiosignal, obtains the spy for meeting preset quality requirement
Levy a little；
Vectorial generation unit, the characteristic point for meeting preset quality requirement according to, generates the feature of the electrocardiosignal
Vector；
Wherein, the characteristic point check unit, the average wave amplitude of the characteristic point specifically for calculating all electrocardiosignals, with
And the interval duration of the characteristic point of the two neighboring electrocardiosignal；Wave amplitude is obtained higher than the 2/3 of the average wave amplitude, and with phase
The interval duration of adjacent electrocardiosignal is more than or equal to the characteristic point of 0.6 second, and this feature point meets preset quality requirement to be described
Characteristic point.
8. identity recognition device as claimed in claim 7, it is characterised in that the characteristic vector of the electrocardiosignal specified
Generation module, in addition to：
Signal filtering unit, denoising is filtered for the electrocardiosignal to input.
9. identity recognition device as claimed in claim 7, it is characterised in that the vectorial generation unit, including：
Waveform partition subelement, for being multiple heart cycle waveforms by the feature points segmentation for meeting preset quality requirement；
Waveform obtains subelement, for by carrying out mode detection to the multiple heart cycle waveform, obtaining waveform and not making a variation
Heart cycle waveform；
Waveshape subelement, the average heart cycle waveform for calculating the heart cycle waveform that the waveform does not make a variation；
Vector generation subelement, for according to the average heart cycle waveform, generating the characteristic vector of the electrocardiosignal.
10. identity recognition device as claimed in claim 9, it is characterised in that the waveform obtains subelement, specifically for logical
Default clustering algorithm is crossed, the multiple heart cycle waveform is divided into two classes；Reservation includes the number of the heart cycle waveform
The more class of amount, the heart cycle waveform in such is the heart cycle waveform that the waveform does not make a variation.
11. identity recognition device as claimed in claim 9, it is characterised in that the vector generation subelement, specifically for right
The average heart cycle waveform carries out wavelet decomposition, and obtains the decomposition coefficient of wavelet decomposition；Using the decomposition coefficient as
The characteristic vector of the electrocardiosignal.
12. identity recognition device as claimed in claim 7, it is characterised in that the identification module, including：
Cosine value comparison unit, for by the spy in the characteristic vector of the electrocardiosignal to be identified and the template database
Levy vector template and carry out included angle cosine value contrast；
Template acquiring unit, the characteristic vector template maximum for obtaining included angle cosine value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410853533.4A CN104545890B (en) | 2014-12-30 | 2014-12-30 | A kind of personal identification method and device based on electrocardiosignal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410853533.4A CN104545890B (en) | 2014-12-30 | 2014-12-30 | A kind of personal identification method and device based on electrocardiosignal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104545890A CN104545890A (en) | 2015-04-29 |
| CN104545890B true CN104545890B (en) | 2017-08-25 |
Family
ID=53063747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410853533.4A Active CN104545890B (en) | 2014-12-30 | 2014-12-30 | A kind of personal identification method and device based on electrocardiosignal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104545890B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10123741B2 (en) * | 2016-11-30 | 2018-11-13 | Huami Inc. | Cardiac condition detection |
| CN106340138B (en) * | 2016-08-23 | 2019-08-27 | 深圳怡化电脑股份有限公司 | A kind of trading activity detection method and device |
| WO2018152724A1 (en) * | 2017-02-23 | 2018-08-30 | 深圳先进技术研究院 | Identity recognition method, device and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101467879A (en) * | 2007-12-26 | 2009-07-01 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for processing multi-lead synchronized electrocardiosignal |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101773394B (en) * | 2010-01-06 | 2011-09-07 | 中国航天员科研训练中心 | Identification method and identification system using identification method |
| CN102274029B (en) * | 2011-05-25 | 2013-10-02 | 中国科学院深圳先进技术研究院 | Identity recognition method and system |
| CN102289618A (en) * | 2011-07-19 | 2011-12-21 | 中山大学深圳研究院 | Electrocardiosignal-based identity recognition method and device |
| WO2013054242A1 (en) * | 2011-10-12 | 2013-04-18 | Koninklijke Philips Electronics N.V. | Method and system to fully-automatically measure the st-segment level of electrocardiograms in real-time ecg monitoring |
-
2014
- 2014-12-30 CN CN201410853533.4A patent/CN104545890B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101467879A (en) * | 2007-12-26 | 2009-07-01 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for processing multi-lead synchronized electrocardiosignal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104545890A (en) | 2015-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102451795B1 (en) | ECG signal detection method | |
| CN102835954B (en) | Method for generating heart beating waveform template and treating ventricular premature beat detection and device | |
| CN103714281B (en) | A kind of personal identification method based on electrocardiosignal | |
| CN109171712A (en) | Auricular fibrillation recognition methods, device, equipment and computer readable storage medium | |
| EP3040018A1 (en) | Method and apparatus for authenticating user based on biosignal | |
| CN100518624C (en) | Method and system for determining arbitrary cardiac phases using non-electrical signals | |
| CN109864736A (en) | Processing method, device, terminal device and the medium of electrocardiosignal | |
| CN108509823A (en) | The detection method and device of QRS complex | |
| CN108513665A (en) | The methods, devices and systems of user identity identification | |
| CN108158578A (en) | Noise segments recognition methods, ECG signal processing method and processing device | |
| CN109117730A (en) | Electrocardiogram auricular fibrillation real-time judge method, apparatus, system and storage medium | |
| CN107233093B (en) | R wave detection method and device and electronic equipment | |
| CN107273827B (en) | Electrocardiosignal R wave detection method and device | |
| CN104545890B (en) | A kind of personal identification method and device based on electrocardiosignal | |
| CN104546007B (en) | Anti-interference processing method and device for fetal movement detection | |
| US10163528B2 (en) | Determining user-interested information based on wearable device | |
| CN106725420A (en) | VPB recognition methods and VPB identifying system | |
| CN106485213B (en) | A kind of feature extracting method carrying out automatic identification using electrocardiosignal | |
| CN106874722A (en) | A kind of personal identification method and its device based on electrocardiosignal | |
| CN109077714B (en) | Signal identification method, device, equipment and storage medium | |
| CN109833034A (en) | The method and device of blood pressure data is extracted in a kind of pulse wave signal | |
| CN109044340B (en) | Electrocardiogram data classification method and device, electronic equipment and storage medium | |
| CN110786849A (en) | Electrocardiosignal identity recognition method and system based on multi-view discriminant analysis | |
| CN104202644A (en) | Standardized output method, device, set-top box and system for brain wave signals | |
| CN109106345A (en) | Pulse signal characteristic detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |