CN109086748A - A kind of method and device of member identities' identification - Google Patents
A kind of method and device of member identities' identification Download PDFInfo
- Publication number
- CN109086748A CN109086748A CN201811055411.5A CN201811055411A CN109086748A CN 109086748 A CN109086748 A CN 109086748A CN 201811055411 A CN201811055411 A CN 201811055411A CN 109086748 A CN109086748 A CN 109086748A
- Authority
- CN
- China
- Prior art keywords
- spectrum data
- reflected spectrum
- data
- characteristic value
- skin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Abstract
The invention discloses a kind of method and devices of member identities identification, this method includes obtaining the reflected spectrum data of the skin of member to be identified, the reflected spectrum data for treating the skin of identification member pre-processes, according to pretreated reflected spectrum data and pre-stored member's related information, corresponding member is identified.It is compared by pretreated reflected spectrum data and pre-stored member's related information, can effectively identify corresponding member, compare the advantages that face characteristic identification is small with data volume, and identification is quick, and crypticity is good.
Description
Technical field
The present embodiments relate to identity identifying technology fields more particularly to a kind of member identities to know method for distinguishing and dress
It sets.
Background technique
Currently, a kind of the use of more mode being identified using face characteristic for identification.Face characteristic is known
Camera can not be used, as under toilet usage scenario under home environment, since light condition is not good enough, obtained facial image
It is unintelligible, lead to identification inaccuracy；The improper use of especially camera may invade individual privacy.It is protected for privacy
Shield, if the camera low using pixel, it is low on the one hand to will lead to face characteristic recognition accuracy, on the other hand still cannot be fine
Ground solves the problems, such as secret protection.
Summary of the invention
The embodiment of the present invention provides a kind of method and device of member identities' identification, meets in member's identification process to solve
The problem of secret protection arrived.
A kind of member identities provided in an embodiment of the present invention know method for distinguishing, comprising:
Obtain the reflected spectrum data of the skin of member to be identified；
The reflected spectrum data of the skin of the member to be identified is pre-processed；
According to pretreated reflected spectrum data and pre-stored member's related information, corresponding member is identified.
It is compared, can effectively be identified by pretreated reflected spectrum data and pre-stored member's related information
Corresponding member out.It in the case where number of members is few, is identified compared to face characteristic, due between member between reflected spectrum data
It differs greatly, identification error rate is low, and recognition speed is fast, and can also apply under the scene for needing secret protection.
Optionally, member's related information is member's identification model；
Pre-stored member's identification model is determined according to following step:
History spectra database is obtained, the history spectra database is repeatedly to be acquired reflectance spectrum to all members
What data obtained, wherein the same family member carries out independent acquisition in different time points；
Reflected spectrum data in the history spectra database is pre-processed；
Reflected spectrum data in the pretreated history spectra database is input in preset learning model
It is trained study, generates member's identification model；
It is described according to pretreatment back reflection spectroscopic data and pre-stored member's related information, identify it is corresponding at
Member, comprising:
The pretreated reflected spectrum data is input to member's identification model, mould is identified by the member
Type identifies corresponding member.
By being trained study to a large amount of history spectroscopic data of member, the Spectral Properties of each member can be effectively obtained
Sign provides basic data for member's identification, to improve the accuracy and efficiency of identification.
Optionally, member's related information is characterized Value Data library；
Pre-stored characteristic value data library is determined according to following step:
History spectra database is obtained, the history spectra database is to all member's multi collect reflected spectrum datas
It obtains, wherein same member carries out independent acquisition in different time points；
Reflected spectrum data in the history spectra database is pre-processed, and extracts each reflected spectrum data pair
The characteristic value answered；
According to the corresponding characteristic value of each reflected spectrum data of the extraction, the characteristic value data library is generated；
It is described according to pretreated reflected spectrum data and pre-stored member's related information, identify it is corresponding at
Member, comprising:
Extract the characteristic value of pretreated reflected spectrum data；
The characteristic value of the reflected spectrum data is compared with the characteristic value in the characteristic value data library, is identified
Corresponding member.
By the way that the characteristic value in characteristic value data library to be compared with the characteristic value of member to be identified, identification can be improved
Accuracy and efficiency.
Optionally, it is described identify corresponding member after, further includes:
Pretreated reflected spectrum data is stored in the history spectra database, is associated with letter to update the member
Breath.
Optionally, the characteristic value can be one of following characteristics or any combination:
The wave for reflecting peak valley wavelength location, curve of spectrum shape, the intensity of specific wavelength and its ratio, spectrum of spectrum
Long range, the body fat of skin, pachylosis value.
Optionally, the reflected spectrum data of the skin for obtaining member to be identified, comprising:
The reflected spectrum data of the skin of the member to be identified is acquired by spectral measuring devices.
Optionally, the member is kinsfolk.
Optionally, the reflected spectrum data is near-infrared spectral reflectance data.
Correspondingly, the embodiment of the invention also provides a kind of devices of member identities identification, comprising:
Acquiring unit, the reflected spectrum data of the skin for obtaining member to be identified；
Spectroscopic data processing unit, the reflected spectrum data for the skin to the member to be identified pre-process；
Recognition unit, for according to pretreated reflected spectrum data and pre-stored member's related information, identification
Corresponding member out.
Optionally, member's related information is member's identification model；Described device further includes model generation unit；
The acquiring unit is also used to obtain history spectra database, and the history spectra database is more to all members
What secondary acquisition reflected spectrum data obtained, wherein same member carries out independent acquisition in different time points；
The spectroscopic data processing unit is also used to carry out the reflected spectrum data in the history spectra database pre-
Processing；
The model generation unit is specifically used for the reflectance spectrum number in the pretreated history spectra database
It is trained study according to being input in preset learning model, generates member's identification model；
The recognition unit is specifically used for for the pretreated reflected spectrum data being input to member's identification mould
Type identifies corresponding member by member's identification model.
Optionally, member's related information is characterized Value Data library；Described device further includes database generation unit；
The acquiring unit is also used to obtain history spectra database, and the history spectra database is more to all members
What secondary acquisition reflected spectrum data obtained, wherein same member carries out independent acquisition in different time points；
The spectroscopic data processing unit is also used to carry out the reflected spectrum data in the history spectra database pre-
Processing, and extract the corresponding characteristic value of each reflected spectrum data；
The database generation unit is specifically used for the corresponding characteristic value of each reflected spectrum data according to the extraction, raw
At the characteristic value data library；
The recognition unit is specifically used for extracting the characteristic value of pretreated reflected spectrum data；By the reflectance spectrum
The characteristic value of data is compared with the characteristic value in the characteristic value data library, identifies corresponding member.
It optionally, further include storage unit；
The storage unit is used for after the recognition unit identifies corresponding member, will be described pretreated anti-
It penetrates spectroscopic data and is stored in the history spectra database, to update member's related information.
Optionally, the characteristic value can be one of following characteristics or any combination:
The wave for reflecting peak valley wavelength location, curve of spectrum shape, the intensity of specific wavelength and its ratio, spectrum of spectrum
Long range, the body fat of skin, pachylosis value.
Optionally, the acquiring unit is spectral measuring devices；The spectral measuring devices be specifically used for acquisition it is described to
Identify the reflected spectrum data of the skin of member.
Optionally, the member is kinsfolk.
Optionally, the reflected spectrum data is near-infrared spectral reflectance data.
Correspondingly, the closestool is equipped with above-mentioned member identities identification the embodiment of the invention also provides a kind of closestool
Device.
Correspondingly, the embodiment of the invention also provides a kind of calculating equipment, comprising:
Memory, for storing program instruction；
Processor executes above-mentioned member according to the program of acquisition for calling the program instruction stored in the memory
The method of identification.
Correspondingly, the embodiment of the invention also provides a kind of computer-readable non-volatile memory medium, including computer
Readable instruction, when computer is read and executes the computer-readable instruction, so that computer executes above-mentioned member identities and knows
Method for distinguishing.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is a kind of schematic diagram of system architecture provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic diagram of skin model provided in an embodiment of the present invention；
Fig. 3 is the flow diagram that a kind of member identities provided in an embodiment of the present invention know method for distinguishing；
Fig. 4 is a kind of structural schematic diagram of the device of member identities' identification provided in an embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that described embodiments are only a part of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
All other embodiment, shall fall within the protection scope of the present invention.
Fig. 1 illustratively shows member identities provided in an embodiment of the present invention and knows a kind of system that method for distinguishing is applicable in
Framework reflecting spectrograph 100 and is known as shown in Figure 1, the system architecture may include reflecting spectrograph 100 and identification terminal 200
Other terminal 200 is communicated by wired or wireless way.
The emission spectrometer 100 be mainly used for the human skin of member to be identified emit light, then acquire it is to be identified at
The spectroscopic data of the human skin reflected light of member, and the spectroscopic data of acquisition is sent to the identification terminal 200.
The identification terminal 200 can be the equipment for being able to carry out member identities' identification process, and specifically it can be to reflection
The spectroscopic data of the light of the human skin reflection for the member that spectrometer 100 acquires pre-processes, then according to pretreated
Member's related information that spectroscopic data and identification terminal 200 prestore itself can identify corresponding member.
It should be noted that above-mentioned reflecting spectrograph 100 and identification terminal 200 can be two separated equipment, it can also
To be integrated in an equipment together.During concrete application, selected according to actual needs.
Fig. 2 shows human skin model, human skin can be divided into cuticula, epidermis, corium and subcutaneous tissue etc., no
Its corresponding spectroscopic data of the skin texture of same layer is also different.The reflected spectrum data of the skin of different people is also different
, which can be used curve and is indicated.
Based on foregoing description, Fig. 3 illustratively shows a kind of side of member identities' identification provided in an embodiment of the present invention
Method, the device which can be identified by member identities execute, which can be provided separately with above-mentioned identification terminal, can also be with
It is integrated on the identification terminal.
As shown in figure 3, this method specifically includes:
Step 301, the reflected spectrum data of the skin of member to be identified is obtained.
The reflected spectrum data can be the reflected spectrum data from visible light near infrared light.Optionally, the reflected light
Modal data can be the reflected spectrum data of near infrared light.The near infrared light is the electromagnetism between visible light and mid-infrared light
Wave refers to electromagnetic wave of the wavelength within the scope of 780~2526nm, and near infrared region is traditionally divided into near-infrared shortwave (780 again
~1100nm) and two regions of near-infrared long wave (1100~2526nm).
When obtaining the reflected spectrum data of skin of member to be identified, it can be and acquired by spectral measuring devices.It should
Spectral measuring devices can be above-mentioned reflecting spectrograph.In specific application, which can be with identification terminal
Integration apparatus is also possible to seperated equipment.
Step 302, the reflected spectrum data for treating the skin of identification member pre-processes.
Here pretreatment, which can be, does the processing such as smooth, denoising to reflected spectrum data, naturally it is also possible to carry out other
Such as repeatedly measurement is averaged for the pretreatment of the reflected spectrum data of form, in the specific implementation, can empirically be selected
It selects.
This feature value can be one of characteristic value of following multiple dimensions or any combination: the reflection peak valley wavelength position of spectrum
It sets, curve of spectrum shape, the intensity of specific wavelength and its ratio, the wave-length coverage of spectrum, the body fat of skin, pachylosis
Value.The embodiment of the present invention is only example effect to this feature value, without limitation, in specific application can be empirically right
The range of selected characteristic value is adjusted, and is increased new characteristic value or is removed original characteristic value.
Step 303, according to pretreated reflected spectrum data and pre-stored member's related information, correspondence is identified
Member.
In embodiments of the present invention, pre-stored member's related information can pass through member's identification model and characteristic value number
It is embodied according to two kinds of library form.When member's related information is member's identification model, which can pass through
Model is practised to the history spectroscopic data training study of each member to obtain.It specifically can be with are as follows:
The history spectra database of member is first obtained, which repeatedly adopted respectively to all members
What the spectrum of reflected light of the collection from visible light near infrared light obtained, wherein the same family member is carried out in different time points
Independent acquisition.That is, a member needs to be acquired at multiple time points, each acquisition time acquisition is primary；Or
In order to increase sample, each acquisition time can also carry out multi collect, can increase in history spectra database in this way person
Sample size.More to the quantity of the near infrared spectrum of same member acquisition, time point is more, knows after learning to it
Other accuracy rate is also higher.
After obtaining history spectra database, need to locate the reflected spectrum data in history spectra database in advance
Reason, pretreatment here, which can be, is averaged the reflected spectrum data of multiple repairing weld, further can also be flat to this
Mean value does smooth, denoising etc..
Finally pretreated each reflected spectrum data is input in preset learning model and is trained study, is generated
Member's identification model.The preset learning model can be neural network model, such as deep learning network model etc..It will be each anti-
It penetrates after spectroscopic data is input to the preset learning model, by adjusting model parameter model is tended towards stability, to obtain
The member's identification model needed.
It for example, will be at firstly, the weight to each neuron in learning model assigns the random value in (0,1) section
The reflected spectrum data of member " A " inputs in learning model, reflected spectrum data weighted sum and door of the learning model by input
Limit compares, carries out nonlinear operation again, obtains the output of learning model.In the case, learning model output is " 1 " and " 0 "
Probability be respectively 50%, that is to say, that be completely random.At this moment if output is " 1 " (result is correct), increase weight,
When to make learning model encounter the reflected spectrum data input of member " A " again, correct judgement still can be made.If defeated
It is out " 0 " (i.e. result mistake) then the weight of learning model to be adjusted towards the direction for reducing comprehensive weighted input value, purpose
When being the reflected spectrum data for making learning model encounter member " A " next time again input, a possibility that same wrong, is made in reduction.Such as
This operation adjustment, after learning model learn several times by the above learning method, the accuracy of learning model judgement will
It greatly improves.This illustrates that learning model has been obtained for success to the study of the reflected spectrum data of these members, it is by this
The reflected spectrum data distribution ground memory of a little members is on each neuron of learning model.When learning model encounters wherein again
When the reflected spectrum data of any one member, rapid, accurate judgement and identification can be made.It is, in general, that learning model
Contained in neuron number it is more, then it can remember, the member that identifies it is also more.
In step 303, after the reflected spectrum data for treating identification member pre-processes, by pretreated reflection
Spectroscopic data is input in member's identification model that the training succeeds in school, and member's identification model passes through to pretreated reflected light
Modal data is analyzed, so that it may automatically identify the corresponding member of the reflected spectrum data.This mode, which can be improved, to be treated
Identify the accuracy rate and speed of the identification of member.
In embodiments of the present invention, spectroscopic data is curve data, obtains member after being trained study to spectroscopic data
What is remembered in identification model is also curve, and spectroscopic data is input to member's identification model, member identities is identified, is substantially
The accuracy of the comparison of curve and curve, the comparison of analog signal, identification is higher.
In another implementation, when above-mentioned member's related information is characterized Value Data library, this feature Value Data library
The process of foundation is as follows:
The history spectra database of member is first obtained, which repeatedly adopted respectively to all members
What the spectrum of reflected light of the collection from visible light near infrared light obtained, wherein the same family member is carried out in different time points
Independent acquisition.That is, a member needs to be acquired at multiple time points, each acquisition time can also carry out one
Secondary or multi collect, multi collect can increase the sample size in history spectra database.To the close of same member acquisition
The quantity of infrared spectroscopy is more, and time point is more, and the characteristic value obtained after extracting to it is also more, so that characteristic value comparison is more
It is accurate to add.
After obtaining history spectra database, need to locate the reflected spectrum data in history spectra database in advance
Reason, pretreatment here, which can be, is averaged the reflected spectrum data of multiple repairing weld, further can also be flat to this
Mean value does smooth, denoising etc..Then the corresponding characteristic value of average value of aforementioned reflected spectrum data is extracted, such as based on upper
State the corresponding characteristic value of average value that skin model shown in Fig. 2 extracts aforementioned reflected spectrum data.According to the reflection of each member
The corresponding characteristic value of the average value of spectroscopic data, can establish characteristic value data library, and in this feature Value Data library, same member is same
One feature can have multiple characteristic values according to the difference of time, and the success rate of identification can be improved in this way.
It, can variation in chemistry, environmentally since skin model has the uncertainties such as standard curve, thickness, color
The multi-angles such as variation the different characteristic value of selection, to increase the distinguishing characteristics of member.
This feature value can be one of characteristic value of following multiple dimensions or any combination: the reflection peak valley wavelength position of spectrum
It sets, curve of spectrum shape, the intensity of specific wavelength and its ratio, the wave-length coverage of spectrum, the body fat of skin, pachylosis
Value.The embodiment of the present invention is only example effect to this feature value, without limitation, in specific application can be empirically right
The range of selected characteristic value is adjusted, and is increased new characteristic value or is removed original characteristic value.
In step 303, characteristic value is extracted to reflected spectrum data pretreated in step 302, reflected light will be extracted
The characteristic value of modal data is compared with the characteristic value in preceding feature Value Data library, so that it may quickly recognize this it is to be identified at
The corresponding member of reflected spectrum data of the skin of member.
It in specific implementation, is the accuracy rate for improving identification, preferably by the way that the characteristic value of multiple dimensions to be compared
It is identified, if the member identified has multiple, can further be selected here by given threshold or interval range
It takes, that is, chooses comparison result and be greater than threshold value or fall in the member of a certain interval range, to complete identification.Or it is logical
It crosses and selects more characteristic values to be screened more preferably to identify member identities.
It, can also be further by the reflected spectrum data of this pretreated member after successfully identifying member
It is stored in the corresponding position of the member in history spectra database, to update member's related information, increases the sample of the member
Capacity, the accuracy rate that the raising later period identifies it.
It should be noted that when acquiring the reflectance spectrum of skin without limitation to the position of skin, difference can be acquired
The near infrared spectrum of the skin at position.Preparation rate is identified to improve, it is preferable that when carrying out identification, the skin of acquisition is close
Ir data and history spectra database it is associated be the same physical feeling skin.In addition, human skin is possible to
It varies over, therefore, prompting can be set, periodically more new historical spectra database.
In embodiments of the present invention, above-mentioned member can be kinsfolk, it may also be said to, the embodiment of the present invention is suitable for house
Member identities' identification in the environment of front yard.Present inventor is by making great efforts discovery, since the spectroscopic data of skin changes greatly, phase
Be not compared with the modes accuracy rate such as iris, fingerprint, personal recognition it is very high, in practical applications, technical staff is in identification
When do not take into account that this thinking generally, but due in home environment number of members be units, and adult, child, old man
Diversity ratio it is larger, the difference of male and female is also larger, thus identification mistake a possibility that very low, the spectrum of the near infrared light
Identification is suitable for the identification of this small sample amount.And its image for not needing acquisition member protects the privacy of member
Shield is more preferable, so that the identification is more suitable for needing the environment of secret protection.
Above-described embodiment shows the reflected spectrum data of the skin by obtaining member to be identified, treats identification member's
The reflected spectrum data of skin is pre-processed, and is associated with letter with pre-stored member according to pretreated reflected spectrum data
Breath, identifies corresponding member.It is compared by pretreated reflected spectrum data and pre-stored member's related information,
It can effectively identify corresponding member.In the case where number of members is few, identified compared to face characteristic, due to being reflected between member
Difference is big between spectroscopic data, and identification error rate is low, and recognition speed is fast, and can also answer under the scene for needing secret protection
With.
Based on the same technical idea, Fig. 4 illustratively shows a kind of member identities provided in an embodiment of the present invention and knows
Other device, the device can execute the process of above-mentioned member identities identification, which can be above-mentioned identification terminal, can also be with
In the identification terminal.
As shown in figure 4, the device includes:
Acquiring unit 401, the reflected spectrum data of the skin for obtaining member to be identified；
Spectroscopic data processing unit 402 is pre-processed for treating the reflected spectrum data of skin of identification member；
Recognition unit 403, for knowing according to pretreated reflected spectrum data and pre-stored member's related information
It Chu not corresponding member.
Optionally, member's related information is member's identification model；Device further includes model generation unit 404；
Acquiring unit 401 is also used to obtain history spectra database, and history spectra database is repeatedly adopted to all members
Collection reflected spectrum data obtains, wherein same member carries out independent acquisition in different time points；
Spectroscopic data processing unit 402 is also used to pre-process the reflected spectrum data in history spectra database；
Model generation unit 404 is specifically used for inputting the reflected spectrum data in pretreated history spectra database
To study is trained in preset learning model, member's identification model is generated；
Recognition unit 403 is specifically used for pretreated reflected spectrum data being input to member's identification model, passes through into
Member's identification model identifies corresponding member.
Optionally, member's related information is characterized Value Data library；Device further includes database generation unit 405；
Acquiring unit 401 is also used to obtain history spectra database, and history spectra database is repeatedly adopted to all members
Collection reflected spectrum data obtains, wherein carries out independent acquisition in different time points to same member；
Spectroscopic data processing unit 402 is also used to pre-process the reflected spectrum data in history spectra database,
And extract the corresponding characteristic value of each reflected spectrum data；
Database generation unit 405 is specifically used for the corresponding characteristic value of each reflected spectrum data according to extraction, generates special
Value indicative database；
Recognition unit 403 is specifically used for extracting the characteristic value of pretreated reflected spectrum data；By reflected spectrum data
Characteristic value be compared with the characteristic value in characteristic value data library, identify corresponding member.
Optionally, the device of member identities' identification can include model generation unit 404 and database generation unit simultaneously
405。
It optionally, further include storage unit 406；
Storage unit 406 is used for after recognition unit 403 identifies corresponding member, by pretreated reflectance spectrum
Data are stored in history spectra database, to update member's related information.
Optionally, characteristic value can be one of following characteristics or any combination:
The wave for reflecting peak valley wavelength location, curve of spectrum shape, the intensity of specific wavelength and its ratio, spectrum of spectrum
Long range, the body fat of skin, pachylosis value.
Optionally, acquiring unit 401 is spectral measuring devices；Spectral measuring devices are specifically used for acquiring member's to be identified
The reflected spectrum data of skin.
Optionally, member is kinsfolk.
Optionally, reflected spectrum data is near-infrared spectral reflectance data.
Based on the same technical idea, the embodiment of the invention also provides a kind of closestool, which is equipped with above-mentioned member
The device of identification.Such as in toilet lid or cistern cover be equipped with the member identities identification device, Ke Yigen
According to the corresponding operating mode of the member identified, to carry out corresponding operation.The horse of the device of member identities identification is installed
The individual privacy of member can be effectively protected while carrying out identification in bucket.
Based on the same technical idea, the embodiment of the invention also provides a kind of calculating equipment, comprising:
Memory, for storing program instruction；
Processor executes above-mentioned member identities according to the program of acquisition for calling the program instruction stored in memory
Know method for distinguishing.
Based on the same technical idea, the embodiment of the invention also provides a kind of computer-readable non-volatile memories to be situated between
Matter, including computer-readable instruction, when computer is read and executes computer-readable instruction so that computer execute it is above-mentioned at
The method of member's identification.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (16)
1. a kind of member identities know method for distinguishing characterized by comprising
Obtain the reflected spectrum data of the skin of member to be identified；
The reflected spectrum data of the skin of the member to be identified is pre-processed；
According to pretreated reflected spectrum data and pre-stored member's related information, corresponding member is identified.
2. the method as described in claim 1, which is characterized in that member's related information is member's identification model；
Pre-stored member's identification model is determined according to following step:
History spectra database is obtained, the history spectra database is obtained to all member's multi collect reflected spectrum datas
, wherein same member carries out independent acquisition in different time points；
Reflected spectrum data in the history spectra database is pre-processed；
Reflected spectrum data in the pretreated history spectra database is input in preset learning model and is carried out
Training study, generates member's identification model；
It is described that corresponding member is identified according to pretreatment back reflection spectroscopic data and pre-stored member's related information, it wraps
It includes:
The pretreated reflected spectrum data is input to member's identification model, is known by member's identification model
It Chu not corresponding member.
3. the method as described in claim 1, which is characterized in that member's related information is characterized Value Data library；
Pre-stored characteristic value data library is determined according to following step:
History spectra database is obtained, the history spectra database is obtained to all member's multi collect reflected spectrum datas
, wherein same member carries out independent acquisition in different time points；
Reflected spectrum data in the history spectra database is pre-processed, and it is corresponding to extract each reflected spectrum data
Characteristic value；
According to the corresponding characteristic value of each reflected spectrum data of the extraction, the characteristic value data library is generated；
It is described that corresponding member is identified according to pretreated reflected spectrum data and pre-stored member's related information,
Include:
Extract the characteristic value of pretreated reflected spectrum data；
The characteristic value of the reflected spectrum data is compared with the characteristic value in the characteristic value data library, identifies correspondence
Member.
4. method as claimed in claim 2 or claim 3, which is characterized in that it is described identify corresponding member after, further includes:
The pretreated reflected spectrum data is stored in the history spectra database, is associated with letter to update the member
Breath.
5. method as claimed in claim 4, which is characterized in that the characteristic value can be one of following characteristics or any group
It closes:
The wavelength model for reflecting peak valley wavelength location, curve of spectrum shape, the intensity of specific wavelength and its ratio, spectrum of spectrum
It encloses, the body fat of skin, pachylosis value.
6. method as claimed in claim 4, which is characterized in that the reflectance spectrum number of the skin for obtaining member to be identified
According to, comprising:
The reflected spectrum data of the skin of the member to be identified is acquired by spectral measuring devices.
7. method as claimed in claim 4, which is characterized in that the member is kinsfolk.
8. method as claimed in claim 4, which is characterized in that the reflected spectrum data is the reflectance spectrum number of near infrared light
According to.
9. a kind of device of member identities' identification characterized by comprising
Acquiring unit, the reflected spectrum data of the skin for obtaining member to be identified；
Spectroscopic data processing unit, the reflected spectrum data for the skin to the member to be identified pre-process；
Recognition unit identifies pair for according to pretreated reflected spectrum data and pre-stored member's related information
The member answered.
10. device as claimed in claim 9, which is characterized in that the characteristic value can be one of following characteristics or any group
It closes:
The wavelength model for reflecting peak valley wavelength location, curve of spectrum shape, the intensity of specific wavelength and its ratio, spectrum of spectrum
It encloses, the body fat of skin, pachylosis value.
11. device as claimed in claim 9, which is characterized in that the acquiring unit is spectral measuring devices；The spectrum is surveyed
Equipment is measured to be specifically used for acquiring the reflected spectrum data of the skin of the member to be identified.
12. such as the described in any item devices of claim 9 to 11, which is characterized in that the member is kinsfolk.
13. such as the described in any item devices of claim 9 to 11, which is characterized in that the reflected spectrum data is that near-infrared is anti-
Penetrate spectroscopic data.
14. a kind of closestool, which is characterized in that the closestool is equipped with such as the described in any item member identities of claim 9 to 13
The device of identification.
15. a kind of calculating equipment characterized by comprising
Memory, for storing program instruction；
Processor requires 1 to 8 according to the program execution benefit of acquisition for calling the program instruction stored in the memory
The method of any one.
16. a kind of computer-readable non-volatile memory medium, which is characterized in that be stored with computer-readable instruction, work as calculating
It is machine-readable when taking and executing the computer-readable instruction, so that computer executes the method such as any one of claim 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811055411.5A CN109086748A (en) | 2018-09-11 | 2018-09-11 | A kind of method and device of member identities' identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811055411.5A CN109086748A (en) | 2018-09-11 | 2018-09-11 | A kind of method and device of member identities' identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109086748A true CN109086748A (en) | 2018-12-25 |
Family
ID=64841184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811055411.5A Pending CN109086748A (en) | 2018-09-11 | 2018-09-11 | A kind of method and device of member identities' identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086748A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI750604B (en) * | 2020-03-06 | 2021-12-21 | 南臺學校財團法人南臺科技大學 | Photoelectric identity recognition system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1420746A (en) * | 1999-10-08 | 2003-05-28 | 卢米迪格姆公司 | Apparatus and method for identification of individuals by near-infrared spectrum |
| CN1509153A (en) * | 2001-04-11 | 2004-06-30 | ���ױ�ʶ��˾ | Apparatus and method for biometric identification or verification of individuals using optical spectroscopy |
| CN1516564A (en) * | 2001-06-05 | 2004-07-28 | ���ױ�ʶ��˾ | Apparatus and method of biometric determination on basis of spectral optical measurements |
-
2018
- 2018-09-11 CN CN201811055411.5A patent/CN109086748A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1420746A (en) * | 1999-10-08 | 2003-05-28 | 卢米迪格姆公司 | Apparatus and method for identification of individuals by near-infrared spectrum |
| CN1509153A (en) * | 2001-04-11 | 2004-06-30 | ���ױ�ʶ��˾ | Apparatus and method for biometric identification or verification of individuals using optical spectroscopy |
| CN1516564A (en) * | 2001-06-05 | 2004-07-28 | ���ױ�ʶ��˾ | Apparatus and method of biometric determination on basis of spectral optical measurements |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI750604B (en) * | 2020-03-06 | 2021-12-21 | 南臺學校財團法人南臺科技大學 | Photoelectric identity recognition system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105138993B (en) | Establish the method and device of human face recognition model | |
| CN110516576B (en) | Near-infrared living body face recognition method based on deep neural network | |
| You et al. | On hierarchical palmprint coding with multiple features for personal identification in large databases | |
| CN106326886B (en) | Finger vein image quality appraisal procedure based on convolutional neural networks | |
| CN101359365B (en) | Iris positioning method based on maximum between-class variance and gray scale information | |
| CN106778525A (en) | Identity identifying method and device | |
| CN104077579B (en) | Facial expression recognition method based on expert system | |
| CN104732200B (en) | A kind of recognition methods of skin type and skin problem | |
| US20060222212A1 (en) | One-dimensional iris signature generation system and method | |
| CN106156702A (en) | Identity identifying method and equipment | |
| CN108124486A (en) | Face living body detection method based on cloud, electronic device and program product | |
| CN110084149B (en) | Face verification method based on hard sample quadruple dynamic boundary loss function | |
| Kang et al. | A study on performance evaluation of fingerprint sensors | |
| CN106682473A (en) | Method and device for identifying identity information of users | |
| CN109446948A (en) | A kind of face and voice multi-biological characteristic fusion authentication method based on Android platform | |
| CN104809450B (en) | Wrist vena identification system based on online extreme learning machine | |
| CN110520865A (en) | The method, apparatus and electronic equipment of recognition of face | |
| CN109145716B (en) | Boarding gate verifying bench based on face recognition | |
| Rathgeb et al. | Bit reliability-driven template matching in iris recognition | |
| CN113221086A (en) | Offline face authentication method and device, electronic equipment and storage medium | |
| Villariña et al. | Palm vein recognition system using directional coding and back-propagation neural network | |
| CN109086748A (en) | A kind of method and device of member identities' identification | |
| Tukur | Fingerprint recognition and matching using Matlab | |
| CN104361339A (en) | Palm image extracting and identification method | |
| Al-Nima | Human authentication with earprint for secure telephone system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181225 |