CN107819926A - Electrocardio identification authentication system and method based on mobile phone - Google Patents
Electrocardio identification authentication system and method based on mobile phone Download PDFInfo
- Publication number
- CN107819926A CN107819926A CN201610822348.8A CN201610822348A CN107819926A CN 107819926 A CN107819926 A CN 107819926A CN 201610822348 A CN201610822348 A CN 201610822348A CN 107819926 A CN107819926 A CN 107819926A
- Authority
- CN
- China
- Prior art keywords
- ripples
- module
- crests
- mobile phone
- electrocardiosignal
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
-
- 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
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- 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
- A61B5/7235—Details of waveform analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
- H04L9/3231—Biological data, e.g. fingerprint, voice or retina
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/02—Constructional features of telephone sets
- H04M1/0202—Portable telephone sets, e.g. cordless phones, mobile phones or bar type handsets
- H04M1/026—Details of the structure or mounting of specific components
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
Abstract
A kind of electrocardio identification authentication system and method based on mobile phone, the device includes ecg signal acquiring module and ECG's data compression and authentication module, ecg signal acquiring module includes being used for the sensor for gathering electrocardiosignal, ECG's data compression and authentication module include pretreatment module, characteristic extracting module and authentication module, pretreatment module is used to be filtered processing to the electrocardiosignal of sensor collection to eliminate interference, each datum mark that characteristic extracting module is used to detect in electrocardiosignal is used as original electrocardiographicdigital feature using the heartbeat signal for extracting quasi periodic, after segmented waveform correction being carried out to heartbeat, recycle PCA dimensionality reductions and extraction coefficient feature is as final ecg characteristics, authentication module is used for discriminating test sample, and whether authentication is successful.The present invention can ensure the authenticity of authenticating user identification, and the professional equipment cost needed for existing scheme is reduced while realizing living body biological reliable recognition.
Description
Technical field
The present invention relates to identity identifying technology field, more particularly to the electrocardio identification authentication system based on mobile phone and side
Method.
Background technology
Today's society is growing for the demand of living things feature recognition, the various methods using living things feature recognition identity
Emerge in an endless stream.It is most common to have following several ways：
1. fingerprint, personal recognition
Fingerprint and personal recognition are of long standing and well established.Fingerprint is because it has unchangeable property, uniqueness and convenience, suitable
Long a period of time value almost turns into the synonym of living things feature recognition.Fingerprint refers to that the positive surface skin of the finger tips of people is convex recessed
Streakline caused by injustice.The different line type of the regular arrangement form of streakline.Starting point, terminal, binding site and the bifurcation of streakline,
The referred to as details (minutiae) of fingerprint.
2. iris recognition
Eye structure by sclera, iris, pupil crystalline lens, retina etc. part form.Iris is to be located at black pupil
Annular formations between white sclera, it includes many interlaced spots, filament, coronal, striped, crypts etc.
Minutia.And iris will be to maintain constant after prenatal development stage is formed in whole life course.These features
The uniqueness of iris feature is determined, while also determines the uniqueness of identification.Therefore, can be by the iris feature of eyes
As everyone identification object.
3. recognition of face
Recognition of face, refer in particular to the computer technology using com-parison and analysis.Recognition of face is a popular computer technology
Research field, face tracking detecting, adjust automatically image zoom, night infrared detecting, adjust automatically exposure intensity；It belongs to raw
Thing feature recognition, it is individual to distinguish organism to organism (typically the refering in particular to people) biological characteristic of itself.
Except mode identified above, the also identification method such as vocal print, gait, person's handwriting.
The existing most Shortcomings of identification method, in addition to iris recognition, other are not live body collections, can
Pretended to be with certain mode.It is higher to technical requirements and iris recognition needs professional equipment.So, it would be desirable to Yi Zhongke
Have to carry out live body collection for the relatively low identification method of equipment requirement.
The content of the invention
It is a primary object of the present invention to overcome the deficiencies in the prior art, there is provided the electrocardio identification authentication system based on mobile phone
And method, vivo identification is carried out, and the requirement to identification equipment is reduced, improve the security and convenience of identification.
To achieve the above object, the present invention uses following technical scheme：
A kind of electrocardio identification authentication system based on mobile phone, including in the front of mobile phone, the back side and/or the week side of boss
Ecg signal acquiring module and ECG's data compression and authentication module in mobile phone, the ecg signal acquiring mould
Block includes being used for gathering the sensor of electrocardiosignal, the ECG's data compression and authentication module include pretreatment module,
Characteristic extracting module and authentication module, wherein the pretreatment module is used to filter the electrocardiosignal of sensor collection
To eliminate interference, the characteristic extracting module is used to detect each datum mark in electrocardiosignal to extract paracycle for ripple processing
Property heartbeat signal as original electrocardiographicdigital feature, after carrying out segmented waveform correction to heartbeat, recycle PCA dimensionality reductions and extraction coefficient
Feature as final ecg characteristics, the authentication module using based on the method for template matches come discriminating test sample whether identity
Certification success.
Preferably, wherein the sensor of the ecg signal acquiring module includes at least one pair of electrode, the pair of electrode
Mobile phone front and back centre position is distributed in, is either distributed in the side of mobile phone two or is distributed in the top and bottom of mobile phone
Portion, either it is distributed in the top both ends of mobile phone or is distributed in the bottom both ends of mobile phone, or is distributed in front or the back of the body of mobile phone
The angle of top two in face, be either distributed in mobile phone front or the back side the angle of lower section two or be distributed in mobile phone front or
Two diagonally opposing corners at the back side.The electrode includes the contacting surface layer being packaged as a whole by flexible material and electrically connected with the contacting surface layer
Connection terminal, the contacting surface layer is used to contact with finger skin to gather electrocardiosignal, and the connection terminal is by the electrocardio
Signal is sent to interior of mobile phone circuit, and the flexible material is the liquid-state silicon gel or the full Bao Mi of solid-state silica gel of food-grade or medical grade
Envelope shaping, the contacting surface layer are stainless steel, copper sheet, nickel strap, iron or the manganese steel of food-grade or medical grade.
The ecg signal acquiring module also includes the touch inductor being correspondingly arranged according to the distributing position of each electrode, institute
Touch inductor is stated to be used to detect whether finger contacts electrode, and the processor when detecting that finger contacts electrode into mobile phone
Signal is sent, processor controls the ecg signal acquiring module to carry out signal acquisition after detecting signal.
Each datum mark includes the P ripples starting point (Ps) of heartbeat, P ripples terminal (Pe), R crests (R), J ripples starting point (J), T
Crest (Tp) and T ripples terminal (Te).
The characteristic extracting module includes Trigger jitter detection and segmentation module, segmented waveform rectification module and PCA dimensionality reductions
And characteristic extracting module, the Trigger jitter detection and segmentation module are used to detect each datum mark in electrocardiosignal and are based on base
On schedule to waveform segments, the segmented waveform rectification module is used to carry out segmented waveform correction to eliminate the heart that heart rate variability is brought
Difference, the PCA dimensionality reductions and the characteristic extracting module of fighting carry out dimensionality reduction using principal component analysis and extraction coefficient feature is as final
Ecg characteristics；
Wherein described Trigger jitter detection and segmentation module carry out Trigger jitter detection and waveform segments in the following manner：
Electrocardiosignal determines the position of the R ripples of heartbeat, or the second differnce with electrocardiosignal by wavelet transformation mode
The minimum of signal determines the rough position of the R ripples of heartbeat, then determines that the first-order difference signal at the rough position of R ripples most connects
Zero that point is bordering on, positions the position of R crests (R) accordingly；
Using at one in the range of the 160-180 milliseconds on the left of each R crests (R) as P ripples starting point (Ps)；With apart from each R ripples
On the left of peak (R) in the range of 80-100 milliseconds one at be P ripples terminal (Pe)；With apart from 80-100 millisecond scopes on the right side of each R crests
It is J ripples starting point (J) at interior one；So that, as T crests (Tp), this section of region is from J at the maximum in one section of region on the right side of each R crests
Ripple starting point (J) starts at the phase between 2/3 current RR cut-off；With first-order difference signal on the right side of T crests (Tp) first by bearing just
Opening position be T ripples terminal (Te).
The segmented waveform rectification module carries out segmented waveform correction in the following manner：
Segmentation resampling is carried out to heartbeat signal, wherein being up-sampled to each pattern-band, extends P ripples after up-sampling
Duan Shichang, each pattern-band duration is set to be unified for 460-500 milliseconds；Keep constant for each QRS wave section duration；For each T wave bands,
Down-sampling is carried out to J~Tp sections and Tp~Tp sections respectively so that each duration is unified for two segments after each T wave bands resampling
10-20 milliseconds.
The PCA dimensionality reductions and characteristic extracting module extraction keep each shafting number of the contribution rate more than given threshold as system
Number feature, given threshold is preferably 99%.
The sensor includes the strip sensor for being arranged on mobile phone frame both sides.
A kind of electrocardio identity identifying method based on mobile phone, uses described electrocardio identification authentication system, methods described bag
Pre-treatment step, characteristic extraction step and authenticating step are included, wherein the pre-treatment step is included to sensor collection
Electrocardiosignal is filtered processing to eliminate interference, and the characteristic extraction step includes each datum mark in detection electrocardiosignal
Heartbeat signal to extract quasi periodic after carrying out segmented waveform correction to heartbeat, recycles PCA as original electrocardiographicdigital feature
Dimensionality reduction and extraction coefficient feature are as final ecg characteristics, and the authenticating step based on the method for template matches including the use of being sentenced
Determining test sample, whether authentication is successful.
Preferably, each datum mark includes the P ripples starting point (Ps) of heartbeat, P ripples terminal (Pe), R crests (R), and J ripples rise
Point (J), T crests (Tp) and T ripples terminal (Te).
In the characteristic extraction step, Trigger jitter detection and waveform segments are carried out in the following manner：
The rough position of the R ripples of heartbeat is determined with the minimum of the second differnce signal of electrocardiosignal, then is determined in R ripples
That point of first-order difference signal at rough position closest to zero, the position of R crests (R) is positioned accordingly；
Using at one in the range of the 160-180 milliseconds on the left of each R crests (R) as P ripples starting point (Ps)；With apart from each R ripples
On the left of peak (R) in the range of 80-100 milliseconds one at be P ripples terminal (Pe)；With apart from 80-100 millisecond scopes on the right side of each R crests
It is J ripples starting point (J) at interior one；So that, as T crests (Tp), this section of region is from J at the maximum in one section of region on the right side of each R crests
Ripple starting point (J) starts at the phase between 2/3 current RR cut-off；With first-order difference signal on the right side of T crests (Tp) first by bearing just
Opening position be T ripples terminal (Te).
In the characteristic extraction step, segmented waveform correction is carried out in the following manner：
Segmentation resampling is carried out to heartbeat signal, wherein being up-sampled to each pattern-band, extends P ripples after up-sampling
Duan Shichang, each pattern-band duration is set to be unified for 460-500 milliseconds；Keep constant for each QRS wave section duration；For each T wave bands,
Down-sampling is carried out to J~Tp sections and Tp~Tp sections respectively so that each duration is unified for two segments after each T wave bands resampling
10-20 milliseconds.
In the characteristic extraction step, extraction keeps each shafting number of the contribution rate more than given threshold special as coefficient
Sign, given threshold is preferably 99%.
Beneficial effects of the present invention：
The present invention utilizes the ecg signal acquiring module and the electrocardiosignal in mobile phone being arranged on phone housing
Processing and authentication module, living things feature recognition is carried out using electrocardiosignal, the authenticity of authenticating user identification is ensure that, keeps away
The problem of having exempted to pretend to be existing for the identification methods such as present fingerprint, and reduce professional equipment needed for iris recognition etc. into
This, realizes living body biological identification, all has very big lifting than conventional identification method in security or efficiency-cost ratio.Pass through
Electrocardiosignal is pre-processed, feature extraction, especially detect each datum mark in electrocardiosignal to extract paracycle
Property heartbeat signal as original electrocardiographicdigital feature, after carrying out segmented waveform correction to heartbeat, recycle PCA dimensionality reductions and extraction coefficient
Feature is as final ecg characteristics, and with very high uniqueness and identifiability, realization carries out identity with electrocardiosignal
Checking, ensure that the reliability and security of identification.Moreover, carry out authentication using electrocardiosignal, it is ensured that right
The collection and checking of live body identity.
Brief description of the drawings
Fig. 1 is a kind of electrocardio identification authentication system schematic perspective view based on mobile phone of an embodiment of the present invention；
Fig. 2 is a kind of electrocardio identification authentication system front schematic view based on mobile phone of an embodiment of the present invention；
Fig. 3 is the ecg signal acquiring modular structure block diagram in an embodiment of the present invention.
Fig. 4 is the ECG's data compression and authentication module structured flowchart in an embodiment of the present invention；
Fig. 5 is that the electrocardiosignal datum mark in an embodiment of the present invention extracts schematic diagram, illustrated therein is two quasi- weeks
The heartbeat of phase property；
Fig. 6 is the ECG's data compression and authentication module structured flowchart in another embodiment of the present invention.
Embodiment
Embodiments of the present invention are elaborated below.It is emphasized that what the description below was merely exemplary,
The scope being not intended to be limiting of the invention and its application.
Refering to Fig. 1 to Fig. 4, in one embodiment, a kind of electrocardio identification authentication system based on mobile phone, including installed in
Ecg signal acquiring mould in the front of mobile phone 1, the back side and/or the week side of boss (the week side of boss of mobile phone includes two sides, top and bottom)
Block and ECG's data compression and authentication module in mobile phone, the ecg signal acquiring module include being used to gather
The sensor of electrocardiosignal, the ECG's data compression and authentication module include pretreatment module, characteristic extracting module and
Authentication module, wherein the pretreatment module is dry to eliminate for being filtered processing to the electrocardiosignal of sensor collection
Disturb, the characteristic extracting module is used to detect each datum mark in electrocardiosignal to extract the heartbeat signal of quasi periodic work
For original electrocardiographicdigital feature, after carrying out segmented waveform correction to heartbeat, recycle PCA dimensionality reductions and extraction coefficient feature is as the final heart
Electrical feature, come discriminating test sample, whether authentication is successful using based on the method for template matches for the authentication module.
Preferably, the sensor of the ecg signal acquiring module includes at least one pair of electrode 2,2 ＇, the pair of electrode
Mobile phone front and back centre position can be distributed in, be either distributed in the side of mobile phone two or be distributed in mobile phone top and
Bottom, be either distributed in the top both ends of mobile phone or be distributed in the bottom both ends of mobile phone, or be distributed in mobile phone front or
The angle of top two at the back side, either it is distributed in the front of mobile phone or the angle of lower section two at the back side or the front for being distributed in mobile phone
Or two diagonally opposing corners at the back side.
In an embodiment as illustrated in figure 2, a pair of electrodes 2,2 ＇ are distributed in the angle of positive lower section two of mobile phone.
In a preferred embodiment, the electrode 2,2 ＇ include the contacting surface layer being packaged as a whole by flexible material and touched with described
The connection terminal of surface layer electrical connection, the contacting surface layer are used to contact with finger skin to gather electrocardiosignal, the connection terminal
The electrocardiosignal is sent to interior of mobile phone circuit, the flexible material is the liquid-state silicon gel or solid-state of food-grade or medical grade
The full bag sealing injection shaping of silica gel, the contacting surface layer is stainless steel, copper sheet, nickel strap, iron or the manganese steel of food-grade or medical grade.
As shown in Figures 2 and 3, in a preferred embodiment, the ecg signal acquiring module also include according to each electrode 2,
Touch inductor 3 that 2 ＇ distributing position is correspondingly arranged, 3 ＇, the touch inductor 3,3 ＇ are used to detect whether finger contacts electricity
Pole 2,2 ＇, and the processor when detecting finger contact electrode 2,2 ＇ into mobile phone sends signal, processor detects signal
After control the ecg signal acquiring module to carry out signal acquisition.Because there is provided touch sensor, ecg signal acquiring module
The working condition of collection electrocardiosignal need not be maintained all the time, only when finger touches electrode i.e. touch sensor region
When, mobile phone just controls ecg signal acquiring module to work, and commencing signal collection, therefore, this design advantageously reduces power consumption simultaneously
And reduce device loss.Certainly, touch inductor is not limited to form shown in Fig. 2, energy relative to the positions and dimensions of electrode
The set-up mode enough functioned as described above can use.
In a preferred embodiment, each datum mark includes the P ripples starting point (Ps) of heartbeat, P ripples terminal (Pe), R ripples
Peak (R), J ripples starting point (J), T crests (Tp) and T ripples terminal (Te).
As shown in figure 4, in a preferred embodiment, the characteristic extracting module include Trigger jitter detection and segmentation module,
Segmented waveform rectification module and PCA dimensionality reductions and characteristic extracting module, the Trigger jitter detection and segmentation module are used to detect the heart
Each datum mark in electric signal and based on datum mark to waveform segments, the segmented waveform rectification module is used to carry out segmentation ripple
Shape is corrected to eliminate the heartbeat difference that heart rate variability is brought, and the PCA dimensionality reductions and characteristic extracting module are entered using principal component analysis
Row dimensionality reduction and extraction coefficient feature are as final ecg characteristics；
As shown in figure 5, wherein described Trigger jitter detection and segmentation module carry out Trigger jitter detection and ripple in the following manner
Shape is segmented：
Electrocardiosignal determines the position of the R ripples of heartbeat by wavelet transformation mode, or is believed with the second differnce of electrocardiosignal
Number minimum determine heartbeat R ripples rough position, then determine that the first-order difference signal at the rough position of R ripples is closest
In the position of zero that point, accordingly positioning R crests (R)；
Using at one in the range of the 160-180 milliseconds on the left of each R crests (R) as P ripples starting point (Ps)；With apart from each R ripples
On the left of peak (R) in the range of 80-100 milliseconds one at be P ripples terminal (Pe)；With apart from 80-100 millisecond scopes on the right side of each R crests
It is J ripples starting point (J) at interior one；Using at the maximum in one section of region on the right side of each R crests (R) as T crests (Tp), this section of region
End since J ripples starting point (J) to from the phase (duration i.e. two neighboring R crests) between 2/3 current RR；With T crests
(Tp) right side first-order difference signal is first T ripples terminal (Te) by bearing positive opening position.
In a preferred embodiment, the segmented waveform rectification module carries out segmented waveform correction in the following manner：
Segmentation resampling is carried out to heartbeat signal, wherein being up-sampled to each pattern-band, extends P ripples after up-sampling
Duan Shichang, each pattern-band duration is set to be unified for 460-500 milliseconds；Keep constant for each QRS wave section duration；For each T wave bands,
Down-sampling is carried out to J~Tp sections and Tp~Tp sections respectively so that each duration is unified for two segments after each T wave bands resampling
10-20 milliseconds.
In a preferred embodiment, the PCA dimensionality reductions and characteristic use principal component analysis carry out dimensionality reduction and extract holding tribute
Each shafting number of the rate more than given threshold is offered as coefficient characteristics, given threshold is preferably 99%.
The sensor includes the strip sensor for being arranged on mobile phone frame both sides.
A kind of electrocardio identity identifying method based on mobile phone, uses described electrocardio identification authentication system, methods described bag
Pre-treatment step, characteristic extraction step and authenticating step are included, wherein the pre-treatment step is included to sensor collection
Electrocardiosignal is filtered processing to eliminate interference, and the characteristic extraction step includes each datum mark in detection electrocardiosignal
Heartbeat signal to extract quasi periodic after carrying out segmented waveform correction to heartbeat, recycles PCA as original electrocardiographicdigital feature
Dimensionality reduction and extraction coefficient feature are as final ecg characteristics, and the authenticating step based on the method for template matches including the use of being sentenced
Determining test sample, whether authentication is successful.As shown in Figure 5, it is preferable that each datum mark includes the P ripple starting points of heartbeat
(Ps), P ripples terminal (Pe), R crest (R), J ripples starting point (J), T crests (Tp) and T ripples terminal (Te).
In a preferred embodiment, in the characteristic extraction step, Trigger jitter detection and waveform are carried out in the following manner
Segmentation：
Electrocardiosignal determines the position of the R ripples of heartbeat by wavelet transformation mode, or is believed with the second differnce of electrocardiosignal
Number minimum determine heartbeat R ripples rough position, then determine that the first-order difference signal at the rough position of R ripples is closest
In the position of zero that point, accordingly positioning R crests (R)；
Using at one in the range of the 160-180 milliseconds on the left of each R crests (R) as P ripples starting point (Ps)；With apart from each R ripples
On the left of peak (R) in the range of 80-100 milliseconds one at be P ripples terminal (Pe)；With apart from 80-100 millisecond scopes on the right side of each R crests
It is J ripples starting point (J) at interior one；So that, as T crests (Tp), this section of region is from J at the maximum in one section of region on the right side of each R crests
Ripple starting point (J) starts at the phase between 2/3 current RR cut-off；With first-order difference signal on the right side of T crests (Tp) first by bearing just
Opening position be T ripples terminal (Te).
In a preferred embodiment, in the characteristic extraction step, segmented waveform correction is carried out in the following manner：
Segmentation resampling is carried out to heartbeat signal, wherein being up-sampled to each pattern-band, extends P ripples after up-sampling
Duan Shichang, each pattern-band duration is set to be unified for 460-500 milliseconds；Keep constant for each QRS wave section duration；For each T wave bands,
Down-sampling is carried out to J~Tp sections and Tp~Tp sections respectively so that each duration is unified for two segments after each T wave bands resampling
10-20 milliseconds.
In a preferred embodiment, in the characteristic extraction step, extraction keeps contribution rate each more than given threshold
For shafting number as coefficient characteristics, given threshold is preferably 99%.
The feature and its advantage of the embodiment of the present invention are further illustrated below in conjunction with accompanying drawing.
The electrocardio identification authentication system of specific embodiment includes ecg signal acquiring module and ECG's data compression and identity
Authentication module；Ecg signal acquiring module can use the sensor collection electrocardiosignal for being placed on mobile phone frame both sides, for electrocardio
Signal transacting and authentication module use；ECG's data compression and authentication module are by the electrocardiosignal collected
Reason, and carry out authentication.Specifically include following aspect：
1. ecg signal acquiring
Electrocardiogram (ECG) data can be gathered in the strip sensor of mobile phone frame both sides.The sensor of this position can make difference
The custom of user is met, and fully improves Consumer's Experience.Two hands are pressed on the sensor at both ends respectively, utilize left limb and the right side
The potential difference of limb is acquired.
2. ECG's data compression
A. pre-process
Processing mainly is filtered to original electrocardiosignal, to eliminate common interference.
B. feature extraction
As shown in figure 5, each datum mark is detected in electrocardiosignal first to extract the heartbeat of quasi periodic as original
Ecg characteristics.Electrocardiosignal is a kind of quasi-periodic signal, but is not that composition in the whole cardiac cycle all has specificity,
P ripples, QRS complex and T ripples in wherein each cardiac cycle contain most electrocardio specificity information.The embodiment of the present invention
The wave band cut in each cardiac cycle from continuous electrocardiosignal is as original ecg characteristics.Therefore, to orient the heart
The datum mark fought.In addition, in follow-up wave shape correcting link, it is also necessary to further P ripples and T ripples are handled.Therefore, it is necessary to
The key position of these waveforms is oriented, these points are referred to as datum mark.The embodiment of the present invention is for the detection of each heartbeat
Datum mark includes：P ripples starting point (Ps) and P ripples terminal (Pe), R crests (R), J ripples starting point (J), T crests (Tp) and T ripple terminals
(Te), 6 class datum mark altogether.
Wherein, electrocardiosignal totally relatively relaxes, and R ripples are most sharp part.R ripples are located at the minimum of signal second differnce
It is worth position, and first-order difference is 0.The embodiment of the present invention determines the thick of R ripples with the minimum of the second differnce signal of original signal
Slightly position.After the rough position for orienting R ripples, maximum position this feature is in further according to R-wave amplitude, its first derivative is
0, in the discrete case, i.e., first-order difference signal closest to zero that, R crest locations of registration accordingly.
Further, with the range of 160-180 milliseconds on the left of each R ripples one preferably as at 170 milliseconds for P ripple starting points Ps；
With in the range of 80-100 milliseconds on the left of each R ripples one preferably as at 90 milliseconds for P ripple terminals Pe；With 80-100 on the right side of each R crests
Preferably as being J ripples starting point (J) at 90 milliseconds at one in the range of millisecond；Using the maximum in one section of region on the right side of each R crests (R) as
T crests (Tp), this section of region is since J ripple starting points to from the phase (duration i.e. two neighboring R crests) between 2/3 current RR
Cut-off；Using first-order difference signal on the right side of T crests (Tp) first by bearing positive position as T ripples terminal (Te).
Due to the change of heart rate, heartbeat in each paracycle simultaneously differs, therefore the embodiment of the present invention proposes one kind
The method of segmented waveform correction eliminates the influence of heart rate variability, and the basic skills of correction is that segmentation weight is carried out to former heartbeat signal
Sampling, specifically, being up-sampled to pattern-band, extend pattern-band duration after up-sampling, be unified for 460-500 milliseconds, it is excellent
Such as 480 milliseconds of choosing；Keep constant for QRS wave section, for example, it is long 180 milliseconds；For T wave bands, respectively to wherein J-Tp sections and Tp-
Tp sections carry out down-sampling so that each duration of two segments is unified for 10-20 milliseconds after resampling, preferably such as 15 milliseconds.Finally, correct
Heartbeat overall length afterwards is basically identical, for example, 690 milliseconds.Due to people, in different time and after different motion, heart rate is to differ
Sample, and the difference of this heart rate should not turn into the standard for weighing people's identity characteristic.The present invention is on the basis of QRS wave section, generation
A kind of signal of convenient detection, cardiac cycle length is consistent, so as to eliminate the difference that heart rate variability is brought.
Finally, final ecg characteristics are used as by the use of PCA dimensionality reductions and extraction coefficient feature；PCA principal component analysis will can be believed
Number energy focuses on direct current and low frequency part, and the present invention carries out feature extraction and feature to the heartbeat after PCA is smooth whereby
Dimensionality reduction.Preferably, each shafting number of the extraction holding contribution rate more than given threshold is preferably as coefficient characteristics, given threshold
99%.Experiment test finds that the coefficient vector registration of heartbeat is higher, and inter- object distance is small between showing them；Energy mainly divides
Cloth is in preceding 80 dimensions.
C, certification
The Identity claims of acceptance test sample are determined whether based on the method for template matches.The specific method of template matches
Prior art well known to those skilled in the art can be used, is repeated no more herein.
Preferably, using the electro-cardiologic template previously generated, repeatedly matching judgement is carried out to the waveform of multiple heartbeats of user,
Only certification accuracy is more than 80% and just thinks the electrocardiosignal of user the match is successful to the electro-cardiologic template.
As shown in fig. 6, in another embodiment, it is that the present embodiment is to adopting with the embodiment difference shown in Fig. 4
Collect user a series of heartbeats pre-processed after, first detect the R ripples positions of these heartbeats, and mark off according to the phase between RR more
After individual heartbeat, then the fiducial features extraction that these heartbeats are set respectively, then using difference generated in advance
N electro-cardiologic template, template matches are carried out to these heartbeats, the matching result for being finally based on n electro-cardiologic template judges the user
Electrocardio identity authentication result.In a preferred embodiment, it can use and final certification is obtained to the method for matching result ballot
As a result.The preferred of final identification procedure is carried out by matching result ticket to be voted using highest entropy, counts preliminary identity
Entropy of all categories in identification, according to the entropy counted, final recognition result is used as using classification number corresponding to maximum entropy.Pass through
When highest entropy vote module carries out the ballot of highest entropy, adoptable entropy such as frequency.Each electrocardio mould is corresponded in statistics preliminary classification
The number of the appearance of each classification of plate, calculate the frequency of each classification in preliminary classification.According to the entropy counted, search
Maximum entropy, such as highest frequency.Classification number corresponding to maximum entropy is the final recognition result of system.
In certain embodiments, user needs to register when using first, can generate user template during registration.Each recognizes
Card link is most freshly harvested electrocardio and user template electrocardio matching.
In another aspect of this invention, a kind of electrocardio identification authentication system based on mobile phone, it, which has, is arranged on mobile phone
Quick electrocardio identification system, the quick electrocardio identification system be the applicant in application for a patent for invention
(201610698195.0) the quick electrocardio identity proposed in " a kind of method and its system of quick electrocardio identification " is known
Other system.
In another aspect of this invention, a kind of electrocardio identity identifying method based on mobile phone, it uses this Shen on mobile phone
Ask someone to be carried in application for a patent for invention (201610698195.0) " a kind of method and its system of quick electrocardio identification "
The quick electrocardio personal identification method gone out.
The applicant application for a patent for invention (201610698195.0) " a kind of method of quick electrocardio identification and its
The full content of system " is merged into herein in entirety by reference.
Above content is to combine specific/preferred embodiment further description made for the present invention, it is impossible to is recognized
The specific implementation of the fixed present invention is confined to these explanations.For general technical staff of the technical field of the invention,
Without departing from the inventive concept of the premise, it can also make some replacements or modification to the embodiment that these have been described,
And these are substituted or variant should all be considered as belonging to protection scope of the present invention.
Claims (10)
- A kind of 1. electrocardio identification authentication system based on mobile phone, it is characterised in that including installed in the front of mobile phone, the back side and/ Or the ecg signal acquiring module in the week side of boss and the ECG's data compression and authentication module in mobile phone, the electrocardio Signal acquisition module includes being used for the sensor for gathering electrocardiosignal, and the ECG's data compression and authentication module include pre- Processing module, characteristic extracting module and authentication module, wherein the pretreatment module is used for the electrocardio to sensor collection Signal is filtered processing to eliminate interference, and the characteristic extracting module is used to detect each datum mark in electrocardiosignal to carry The heartbeat signal of quasi periodic is taken out as original electrocardiographicdigital feature, after carrying out segmented waveform correction to heartbeat, recycles PCA dimensionality reductions And extraction coefficient feature is as final ecg characteristics, the authentication module using based on the method for template matches come discriminating test sample Whether authentication is successful for this.
- 2. the electrocardio identification authentication system based on mobile phone as claimed in claim 1, it is characterised in that the electrode is included by soft Property the material package contacting surface layer the being integrated and connection terminal electrically connected with the contacting surface layer, the contacting surface layer is used for and finger skin Skin is contacted to gather electrocardiosignal, and the electrocardiosignal is sent to interior of mobile phone circuit, the flexible material by the connection terminal Expect the liquid-state silicon gel or the full bag sealing moulding of solid-state silica gel for food-grade or medical grade, the contacting surface layer is food-grade or medical grade Stainless steel, copper sheet, nickel strap, iron or manganese steel.
- 3. the electrocardio identification authentication system based on mobile phone as claimed in claim 1, it is characterised in that the ecg signal acquiring Module also includes the touch inductor being correspondingly arranged according to the distributing position of each electrode, and the touch inductor is used to detect finger Whether electrode is contacted, and the processor when detecting that finger contacts electrode into mobile phone sends signal, processor detects letter The ecg signal acquiring module is controlled to carry out signal acquisition after number.
- 4. the electrocardio identification authentication system based on mobile phone as claimed in claim 1, it is characterised in that each datum mark bag Include P ripples starting point (Ps), the P ripples terminal (Pe) of heartbeat, R crests (R), J ripples starting point (J), T crests (Tp) and T ripples terminal (Te), institute Stating characteristic extracting module includes Trigger jitter detection and segmentation module, segmented waveform rectification module and PCA dimensionality reductions and feature extraction Module, the Trigger jitter detection and segmentation module are used to detect each datum mark in electrocardiosignal and based on datum mark to waveform Segmentation, the segmented waveform rectification module are used to carry out segmented waveform correction to eliminate the heartbeat difference that heart rate variability is brought, institute PCA dimensionality reductions and characteristic extracting module are stated using principal component analysis progress dimensionality reduction and extraction coefficient feature is as final ecg characteristics；Wherein described Trigger jitter detection and segmentation module carry out Trigger jitter detection and waveform segments in the following manner：Electrocardiosignal determines the position of the R ripples of heartbeat by wavelet transformation mode, or with the second differnce signal of electrocardiosignal Minimum determines the rough position of the R ripples of heartbeat, then determines first-order difference signal at the rough position of R ripples closest to zero That point, accordingly position R crests (R) position；Using at one in the range of the 160-180 milliseconds on the left of each R crests (R) as P ripples starting point (Ps)；With apart from each R crests (R) In the range of the 80-100 milliseconds of left side one at be P ripples terminal (Pe)；With one in the range of 80-100 milliseconds on the right side of each R crests Locate as J ripples starting point (J)；So that as T crests (Tp), this section of region is from J ripples at the maximum in one section of region on the right side of each R crests (R) Starting point (J) starts at the phase between 2/3 current RR cut-off；It is positive by bearing first with first-order difference signal on the right side of T crests (Tp) Opening position is T ripples terminal (Te).
- 5. the electrocardio identification authentication system based on mobile phone as claimed in claim 4, it is characterised in that the segmented waveform correction Module carries out segmented waveform correction in the following manner：Segmentation resampling is carried out to heartbeat signal, wherein being up-sampled to each pattern-band, when extending pattern-band after up-sampling It is long, each pattern-band duration is unified for 460-500 milliseconds；Keep constant for each QRS wave section duration；For each T wave bands, difference Down-sampling is carried out to J~Tp sections and Tp~Tp sections so that each duration is unified for 10-20 to two segments after each T wave bands resampling Millisecond.
- 6. the electrocardio identification authentication system based on mobile phone as described in any one of claim 4 to 5, it is characterised in that the PCA Dimensionality reduction and characteristic extracting module extraction keep each shafting number of the contribution rate more than given threshold as coefficient characteristics, given threshold Preferably 99%.
- 7. a kind of electrocardio identity identifying method based on mobile phone, it is characterised in that using as described in any one of claim 1 to 6 Electrocardio identification authentication system, methods described includes pre-treatment step, characteristic extraction step and authenticating step, wherein the pre- place Reason step includes being filtered processing to the electrocardiosignal of sensor collection to eliminate interference, the characteristic extraction step bag Each datum mark in detection electrocardiosignal is included to extract the heartbeat signal of quasi periodic as original electrocardiographicdigital feature, to heartbeat After carrying out segmented waveform correction, recycle PCA dimensionality reductions and extraction coefficient feature is as final ecg characteristics, the authenticating step bag Include whether authentication is successful come discriminating test sample using based on the method for template matches.
- 8. the electrocardio identity identifying method based on mobile phone as claimed in claim 7, it is characterised in that, it is preferable that it is described each Datum mark includes the P ripples starting point (Ps) of heartbeat, P ripples terminal (Pe), and R crests (R), J ripples starting point (J), T crests (Tp) and T ripples are whole Point (Te), in the characteristic extraction step, Trigger jitter detection and waveform segments are carried out in the following manner：Electrocardiosignal determines the position of the R ripples of heartbeat by wavelet transformation mode, or with the second differnce signal of electrocardiosignal Minimum determines the rough position of the R ripples of heartbeat, then determines first-order difference signal at the rough position of R ripples closest to zero That point, accordingly position R crests (R) position；Using at one in the range of the 160-180 milliseconds on the left of each R crests (R) as P ripples starting point (Ps)；With apart from each R crests (R) In the range of the 80-100 milliseconds of left side one at be P ripples terminal (Pe)；With one in the range of 80-100 milliseconds on the right side of each R crests Locate as J ripples starting point (J)；So that as T crests (Tp), this section of region is from J ripples at the maximum in one section of region on the right side of each R crests (R) Starting point (J) starts at the phase between 2/3 current RR cut-off；It is positive by bearing first with first-order difference signal on the right side of T crests (Tp) Opening position is T ripples terminal (Te).
- 9. the electrocardio identification authentication system based on mobile phone as claimed in claim 7, it is characterised in that the characteristic extraction step In, segmented waveform correction is carried out in the following manner：Segmentation resampling is carried out to heartbeat signal, wherein being up-sampled to each pattern-band, when extending pattern-band after up-sampling It is long, each pattern-band duration is unified for 460-500 milliseconds；Keep constant for each QRS wave section duration；For each T wave bands, difference Down-sampling is carried out to J~Tp sections and Tp~Tp sections so that each duration is unified for 10-20 to two segments after each T wave bands resampling Millisecond.
- 10. the electrocardio identification authentication system based on mobile phone as described in any one of claim 7 to 9, it is characterised in that the spy Levy in extraction step, extraction keeps each shafting number of the contribution rate more than given threshold preferred as coefficient characteristics, given threshold For 99%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610822348.8A CN107819926B (en) | 2016-09-13 | 2016-09-13 | Electrocardio identity authentication device and method based on mobile phone |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610822348.8A CN107819926B (en) | 2016-09-13 | 2016-09-13 | Electrocardio identity authentication device and method based on mobile phone |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107819926A true CN107819926A (en) | 2018-03-20 |
| CN107819926B CN107819926B (en) | 2020-04-21 |
Family
ID=61600607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610822348.8A Active CN107819926B (en) | 2016-09-13 | 2016-09-13 | Electrocardio identity authentication device and method based on mobile phone |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107819926B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109497990A (en) * | 2018-12-27 | 2019-03-22 | 山东大学 | A kind of electrocardiosignal personal identification method and system based on canonical correlation analysis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003000015A2 (en) * | 2001-06-25 | 2003-01-03 | Science Applications International Corporation | Identification by analysis of physiometric variation |
| CN101773394A (en) * | 2010-01-06 | 2010-07-14 | 中国航天员科研训练中心 | Identification method and identification system using identification method |
| CN102866843A (en) * | 2011-06-29 | 2013-01-09 | Lg电子株式会社 | Mobile terminal with at least a body sensor |
| CN103610457A (en) * | 2013-11-19 | 2014-03-05 | 深圳先进技术研究院 | Electrocardiosignal processing method and electrocardiosignal processing system |
| CN105286909A (en) * | 2015-11-04 | 2016-02-03 | 杜晓松 | Wearable heart sound and electrocardio feature information collecting and monitoring system |
-
2016
- 2016-09-13 CN CN201610822348.8A patent/CN107819926B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003000015A2 (en) * | 2001-06-25 | 2003-01-03 | Science Applications International Corporation | Identification by analysis of physiometric variation |
| CN101773394A (en) * | 2010-01-06 | 2010-07-14 | 中国航天员科研训练中心 | Identification method and identification system using identification method |
| CN102866843A (en) * | 2011-06-29 | 2013-01-09 | Lg电子株式会社 | Mobile terminal with at least a body sensor |
| CN103610457A (en) * | 2013-11-19 | 2014-03-05 | 深圳先进技术研究院 | Electrocardiosignal processing method and electrocardiosignal processing system |
| CN105286909A (en) * | 2015-11-04 | 2016-02-03 | 杜晓松 | Wearable heart sound and electrocardio feature information collecting and monitoring system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109497990A (en) * | 2018-12-27 | 2019-03-22 | 山东大学 | A kind of electrocardiosignal personal identification method and system based on canonical correlation analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107819926B (en) | 2020-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pinto et al. | Evolution, current challenges, and future possibilities in ECG biometrics | |
| WO2018153060A1 (en) | Patch-type device for use in physiological multi-parameter collection and monitoring | |
| Singh et al. | ECG to individual identification | |
| CN102542258B (en) | Imaging device based on finger biometric information and multimoding identity recognition method | |
| AU2003256693B2 (en) | Method and apparatus for electro-biometric identiy recognition | |
| CN109620262A (en) | A kind of Emotion identification system and method based on wearable bracelet | |
| Singh et al. | Correlation-based classification of heartbeats for individual identification | |
| Lourenço et al. | Outlier detection in non-intrusive ECG biometric system | |
| Silva et al. | ECG biometrics: Principles and applications | |
| CN107980151B (en) | Access control system based on electrocardio authentication and authentication method thereof | |
| Singh | Human recognition using Fisher׳ s discriminant analysis of heartbeat interval features and ECG morphology | |
| Chauhan et al. | A survey of emerging biometric modalities | |
| Sasikala et al. | Identification of individuals using electrocardiogram | |
| CN108460318A (en) | Authentication/recognition methods based on electrocardiosignal and equipment | |
| CN106874722A (en) | A kind of personal identification method and its device based on electrocardiosignal | |
| Dey et al. | Retention of electrocardioGram features insiGnificantly devalorized as an effect of watermarkinG for | |
| Islam et al. | Selection of heart-biometric templates for fusion | |
| KR101578167B1 (en) | self-organized real-time authentication method using ECG signal | |
| CN109840451A (en) | A kind of wearable ring of intelligence payment and its method of payment based on electrocardio identification | |
| Safie et al. | ECG biometric authentication using Pulse Active Width (PAW) | |
| Jekova et al. | Personal verification/identification via analysis of the peripheral ECG leads: influence of the personal health status on the accuracy | |
| Zhang et al. | Practical human authentication method based on piecewise corrected Electrocardiogram | |
| CN107819926A (en) | Electrocardio identification authentication system and method based on mobile phone | |
| Pouryayevali | ECG biometrics: new algorithm and multimodal biometric system | |
| Liwen et al. | A dual-biometric-modality identification system based on fingerprint and EEG |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |