CN106295499A - Age estimation method and device - Google Patents
Age estimation method and device Download PDFInfo
- Publication number
- CN106295499A CN106295499A CN201610581752.0A CN201610581752A CN106295499A CN 106295499 A CN106295499 A CN 106295499A CN 201610581752 A CN201610581752 A CN 201610581752A CN 106295499 A CN106295499 A CN 106295499A
- Authority
- CN
- China
- Prior art keywords
- facial image
- age
- estimation
- similarity
- described target
- 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
-
- 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
- G06V40/168—Feature extraction; Face representation
Abstract
The disclosure provides a kind of age estimation method and device.Disclosure age estimation method, including: obtain target facial image；Based on default face recognition algorithms, extract the facial image feature that target facial image is corresponding；Compare facial image feature and presetting database have stored facial image feature, it is thus achieved that similarity；If similarity be more than or equal to predetermined threshold value, then according to obtain this similarity store the age information that facial image feature is corresponding, determine the estimation age of target facial image.The disclosure can improve the degree of accuracy of estimation of Age.
Description
Technical field
It relates to computer technology, particularly relate to a kind of age estimation method and device.
Background technology
Along with the development of face recognition technology, the age of people can be estimated by estimation of Age according to facial image identification
Meter.But at the estimation age using associated age method of estimation to be obtained, the most all fluctuating in actual age, degree of accuracy is relatively
Low.
Summary of the invention
For overcoming problem present in correlation technique, the disclosure provides a kind of age estimation method and device.Described technology
Scheme is as follows:
First aspect according to disclosure embodiment, it is provided that a kind of age estimation method, the method includes: obtain target person
Face image；Based on default face recognition algorithms, extract the facial image feature that described target facial image is corresponding；By described face
Characteristics of image and presetting database store facial image feature compare, it is thus achieved that similarity；If described similarity is more than
Or equal to predetermined threshold value, then store, according to obtain described similarity, the age information that facial image feature is corresponding, determine institute
State the estimation age of target facial image.
Embodiment of the disclosure that the technical scheme of offer can include following beneficial effect: store according to presetting database
Age information corresponding to facial image feature, determine the mesh having stored facial image characteristic similarity with this more than predetermined threshold value
The estimation age of mark facial image, to improve the degree of accuracy of estimation of Age.
Alternatively, above-mentioned according to obtain described similarity store the age information that facial image feature is corresponding, determine
At the estimation age of described target facial image, may include that according to the facial image feature pair of storage obtaining described similarity
The date of birth answered and the generation time of described target facial image, determine the estimation age of described target facial image.
Alternatively, above-mentioned according to obtain described similarity store the age information that facial image feature is corresponding, determine
At the estimation age of described target facial image, may include that according to the facial image feature pair of storage obtaining described similarity
Estimation age that the generation time of the facial image answered, described facial image are corresponding and described target facial image, determine described
The estimation age of target facial image.
Alternatively, above-mentioned according to the generation storing facial image corresponding to facial image feature obtaining described similarity
Estimation age that time, described facial image are corresponding and described target facial image, determine the estimation of described target facial image
At the age, may include that according to described target facial image, it is thus achieved that the first estimation age of described target facial image；According to obtaining
Generation time storing facial image corresponding to facial image feature of described similarity and described target facial image
The generation time, obtain very first time difference；Estimate that the age deducts described very first time difference by described first, obtained for the second time
Difference；Calculate the average estimating the age that described second time difference is corresponding with described facial image, obtain described target face
The estimation age of image.
Alternatively, after the above-mentioned estimation age determining described target facial image, this age estimation method can also wrap
Include: store the estimation age of described target facial image and described target facial image to described presetting database.
Embodiment of the disclosure that the technical scheme of offer can include following beneficial effect: by by target facial image and
The estimation age of target facial image stores to presetting database, can realize storing in presetting database the continuous renewal of data,
So that the quantity of the facial image of storage is gradually increased in presetting database, the estimation of Age result being also follow-up is more smart
Really.
Second aspect according to disclosure embodiment, it is provided that a kind of estimation of Age device, this estimation of Age device includes: obtain
Delivery block, is configured to obtain target facial image；Extraction module, is configured to, based on default face recognition algorithms, extract institute
State the facial image feature that the described target facial image of acquisition module acquisition is corresponding；Comparing module, is configured to carry described
Described facial image feature and presetting database that delivery block extracts store facial image feature compare, it is thus achieved that similar
Degree；Processing module, if the described similarity being configured to the acquisition of described comparing module is more than or equal to predetermined threshold value, then according to obtaining
Obtain described similarity stores the age information that facial image feature is corresponding, determines the estimation year of described target facial image
Age.
Embodiment of the disclosure that the technical scheme of offer can include following beneficial effect: store according to presetting database
Age information corresponding to facial image feature, determine the mesh having stored facial image characteristic similarity with this more than predetermined threshold value
The estimation age of mark facial image, to improve the degree of accuracy of estimation of Age.
Alternatively, above-mentioned processing module includes: first processes submodule, is configured to according to having obtained described similarity
Store date of birth corresponding to facial image feature and the generation time of described target facial image, determine described target face figure
The estimation age of picture.
Alternatively, above-mentioned processing module includes: second processes submodule, is configured to according to having obtained described similarity
Estimation age that the time that generates of storage facial image corresponding to facial image feature, described facial image are corresponding and described target
Facial image, determines the estimation age of described target facial image.
Alternatively, above-mentioned second process submodule is configured to: according to described target facial image, it is thus achieved that described target person
The first estimation age of face image；According to the life storing facial image corresponding to facial image feature obtaining described similarity
One-tenth time and the generation time of described target facial image, obtain very first time difference；Estimate that the age deducts institute by described first
State very first time difference, obtain the second time difference；Calculate the estimation that described second time difference is corresponding with described facial image
The average at age, obtains the estimation age of described target facial image.
Alternatively, above-mentioned estimation of Age device can also include: memory module, is configured to store described target face figure
The estimation age of picture and described target facial image is to described presetting database.
Embodiment of the disclosure that the technical scheme of offer can include following beneficial effect: by by target facial image and
The estimation age of target facial image stores to presetting database, can realize storing in presetting database the continuous renewal of data,
So that the quantity of the facial image of storage is gradually increased in presetting database, the estimation of Age result being also follow-up is more smart
Really.
In a kind of possible design, above-mentioned target facial image is that the mobile device with camera function is under preview mode
Obtain.
The third aspect according to disclosure embodiment, it is provided that a kind of estimation of Age device, this estimation of Age device includes: place
Reason device；For storing the memorizer of described processor executable；Wherein, described processor is configured to: obtain target person
Face image；Based on default face recognition algorithms, extract the facial image feature that described target facial image is corresponding；By described face
Characteristics of image and presetting database store facial image feature compare, it is thus achieved that similarity；If described similarity is more than
Or equal to predetermined threshold value, then store, according to obtain described similarity, the age information that facial image feature is corresponding, determine institute
State the estimation age of target facial image.
It should be appreciated that it is only exemplary and explanatory, not that above general description and details hereinafter describe
The disclosure can be limited.
Accompanying drawing explanation
In order to be illustrated more clearly that disclosure embodiment or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Discloseder embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, also may be used
To obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the flow chart according to a kind of age estimation method shown in an exemplary embodiment；
Fig. 2 is the flow chart according to a kind of age estimation method shown in another exemplary embodiment；
Fig. 3 is the structural representation according to a kind of estimation of Age device shown in an exemplary embodiment；
Fig. 4 is the structural representation according to a kind of estimation of Age device shown in another exemplary embodiment；
Fig. 5 is the structural representation according to a kind of estimation of Age device shown in further example embodiment；
Fig. 6 is the structural representation according to a kind of estimation of Age device shown in another exemplary embodiment；
Fig. 7 is according to a kind of estimation of Age device block diagram shown in an exemplary embodiment.
By above-mentioned accompanying drawing, it has been shown that the embodiment that the disclosure is clear and definite, hereinafter will be described in more detail.These accompanying drawings
With word, the scope being not intended to be limited disclosure design by any mode is described, but by with reference to specific embodiment being
Those skilled in the art illustrate the concept of the disclosure.
Detailed description of the invention
Here will illustrate exemplary embodiment in detail, its example represents in the accompanying drawings.Explained below relates to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represents same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the disclosure.On the contrary, they are only with the most appended
The example of the apparatus and method that some aspects that described in detail in claims, the disclosure are consistent.
Term " first " in the specification and claims of the disclosure, " second " etc. are similar right for distinguishing
As, without being used for describing specific order or precedence.Should be appreciated that the data of so use are the most permissible
Exchange, in order to described herein embodiment of the disclosure such as can suitable with in addition to those here illustrating or describing
Sequence is implemented.Additionally, term " includes " and " having " and their any deformation, it is intended that cover non-exclusive comprising, example
As, contain series of steps or the process of unit, method, system, product or equipment are not necessarily limited to those that clearly list
Step or unit, but can include the most clearly listing or for intrinsic other of these processes, method, product or equipment
Step or unit.
Fig. 1 is the flow chart according to a kind of age estimation method shown in an exemplary embodiment.The present embodiment provides one
Kind of age estimation method, the method can be performed by estimation of Age device, and this estimation of Age device can be by hardware and/or soft
The mode of part realizes, and can be integrated in mobile device, and this mobile device can be smart mobile phone or panel computer or individual number
PDA) (Personal Digital Assistant, is called for short word assistant: the electronic equipment such as.As it is shown in figure 1, this estimation of Age side
Method comprises the following steps:
In a step 101, target facial image is obtained.
Target facial image is by having the mobile device collection of camera function acquisition.Such as, target facial image can
Think what the mobile device with camera function obtained under preview mode.When user is in the coverage of mobile device,
Mobile device can search for and shoot the facial image of user automatically.
Target facial image can be still image or dynamic image.Wherein, dynamic image includes that user is in different positions
Put and/or image under different expression, different attitude.
Can be according to correlation technique, to still image or dynamic image advanced person's row recognition of face, such as every in video
One two field picture all carries out recognition of face, if recognizing a certain two field picture to include face, then intercepts this image and includes face
Image as target facial image.
It addition, after obtaining target facial image, target facial image can be carried out pretreatment.This is due to initially
Original image limited and random disturbances by various conditions, tend not to directly use, therefore need original image is carried out
The Image semantic classification such as gray correction, noise filtering.For facial image, its preprocessing process mainly includes facial image
Light compensation, greyscale transformation, histogram equalization, normalization, geometric correction, filter and sharpening etc..
In a step 102, based on default face recognition algorithms, extract facial image corresponding to this target facial image special
Levy.
Wherein, default face recognition algorithms can be specially recognizer based on features of human face images, based on view picture
The recognizer of facial image, recognizer based on template or the algorithm utilizing neutral net to be identified, etc..
Facial image feature for example, histogram feature, color characteristic, template characteristic, architectural feature and Haar feature etc..
Facial image feature extraction, is the process that face carries out feature modeling.The method of facial image feature extraction can
Think Knowledge based engineering characterizing method.Knowledge based engineering characterizing method is mainly according to shape description and the face of human face
Range performance between organ obtains the characteristic contributing to face classification, and its characteristic component generally includes between characteristic point
Euclidean distance, curvature and angle etc..Face is made up of local such as eyes, nose, mouth, chins, between these local and they
The geometric description of structural relation, can be as the key character identifying face.
In step 103, compare facial image feature and presetting database have stored facial image feature, obtain
Obtain similarity.
The facial image feature stored in facial image feature and presetting database that this step will be to be identified is carried out
Relatively, it is thus achieved that similarity.This process can be divided into two classes: a class is to confirm, is the process that image compares that carries out one to one；Separately
One class is identification, is the one-to-many process that carries out images match contrast.
Wherein, presetting database can include facial image feature and this people that facial image, this facial image are corresponding
The age information that face image is corresponding, this age information can be the date of birth of user's labelling in advance, it is also possible to be according to this people
The estimation age that face image is corresponding, or, date of birth and the combination estimating the age both.Alternatively, this age information also may be used
To include the identity marks of user, such as name or ID (identity number) card No., etc..Presetting database can be by training number in a large number
Obtain according to statistics.
Exemplary, presetting database can be specially face photograph album.Face photograph album refers to utilize image analysis technology, from
Cloud photograph album photo content is carried out carrying out taxonomic revision according to face by dynamic ground, thus is all organized in together by the photo of a people.
Meanwhile, user can in face photograph album the information such as everyone name of labelling and age.
At step 104, if this similarity is more than or equal to predetermined threshold value, then according to the people of storage obtaining this similarity
The age information that face characteristics of image is corresponding, determines the estimation age of target facial image.
Similarity is more than or equal to predetermined threshold value explanation target facial image and at least one face figure in presetting database
Picture is same person.Owing in presetting database, storage has the age information that facial image is corresponding, therefore, the disclosure can be according to obtaining
Obtain this similarity stores the age information that facial image feature is corresponding, determines the estimation age of target facial image.
Such as, in presetting database, storage has a facial image, facial image feature that this facial image is corresponding and target
The similarity of the facial image feature that facial image is corresponding is more than predetermined threshold value, and this face figure of storage in presetting database is described
Picture is same person with target facial image.Now, according to the age letter that this facial image of storage in presetting database is corresponding
Breath, such as age information is date of birth, determines the estimation age of target facial image.
In sum, the age estimation method that the present embodiment provides, special according to the facial image that presetting database has stored
Levy the age information of correspondence, determine the target facial image having stored facial image characteristic similarity with this more than predetermined threshold value
Estimate the age, to improve the degree of accuracy of estimation of Age.
On the basis of above-described embodiment, above-mentioned according to obtain this similarity store the year that facial image feature is corresponding
Information, determined the estimation age of target facial image, can be accomplished in several ways age, was exemplified below illustrating:
In a kind of specific implementation, age corresponding to facial image feature that store according to obtaining this similarity believes
Breath, determine target facial image estimates that the age may include that according to the facial image feature pair of storage obtaining this similarity
The date of birth answered and the generation time of target facial image, determine the estimation age of target facial image.
Such as, it is thus achieved that the date of birth corresponding to facial image feature that store of this similarity is on May 1st, 2016, mesh
The generation time of mark facial image is on July 1st, 2016, it is determined that the estimation age of target facial image is 0 year 62 days.
In another kind of specific implementation, age corresponding to facial image feature that store according to obtaining this similarity believes
Breath, determine target facial image estimates that the age may include that according to the facial image feature pair of storage obtaining this similarity
Estimation age that the generation time of the facial image answered, this facial image are corresponding and target facial image, determine target face figure
The estimation age of picture.
Wherein, according to obtaining the generation time storing facial image corresponding to facial image feature of this similarity, being somebody's turn to do
Estimation age that facial image is corresponding and target facial image, determine the estimation age of target facial image, can be particularly as follows: root
According to target facial image, it is thus achieved that the first estimation age of target facial image；According to the face figure of storage obtaining this similarity
The generation time of the facial image that picture feature is corresponding and the generation time of target facial image, obtain very first time difference；By
One estimates that the age deducts very first time difference, obtains the second time difference；Calculate the second time difference corresponding with facial image
Estimate the average at age, obtain the estimation age of target facial image.
For example, it is assumed that the estimation age that the generation time of this facial image is on May 1st, 2016, this facial image is corresponding
Be 25 years, the generation time of target facial image be on July 1st, 2016, the first estimation age of target facial image be 27 years,
Obtain very first time difference be 62 days, the second time difference be 26 years 303 days, the estimation age of target facial image be 25 years
334 days.
Above example illustrates as a example by a facial image, but the disclosure is not limited system.That is, it is thus achieved that should
The facial image corresponding to facial image feature that store of similarity can be one or more, and those skilled in the art can manage
Solve, when the facial image storing facial image feature corresponding obtaining this similarity is the most, the target face figure finally obtained
The estimation age of picture is the most relatively more accurate.
It should be noted that, " date of birth " mentioned in each embodiment of the disclosure, " generating the time ", " estimating the age ", " the
One time difference " etc., its unit is identical, in order to calculate.
Fig. 2 is the flow chart according to a kind of age estimation method shown in another exemplary embodiment.The method can be by
Estimation of Age device performs, and this estimation of Age device can realize by the way of hardware and/or software, and can be integrated in movement
In equipment, this mobile device can be smart mobile phone or the electronic equipment such as panel computer or PDA.As in figure 2 it is shown, shown in Fig. 1
On the basis of flow process, this age estimation method can also comprise the following steps:
In step 201, if similarity is less than predetermined threshold value, then according to target facial image, target facial image is determined
The estimation age.
It is appreciated that the estimate in age i.e. above-described embodiment first estimation age of goal facial image.
Owing to similarity is less than predetermined threshold value, it is same for illustrating not store in presetting database with this target facial image
The facial image of people, therefore, determines the estimation age of target facial image according to correlation technique.
Alternatively, if similarity is less than predetermined threshold value, the people that target tracking algorism is corresponding to target facial image can be used
Face carries out real-time tracking.Use target tracking algorism that face is tracked, the position of face in each two field picture can be obtained, no
With carrying out repeating the estimation age, raising speed.
Further, this age estimation method can also comprise the following steps:
In step 202., the estimation age of storage target facial image and target facial image is to presetting database.
In sum, the age estimation method that the present embodiment provides, by by target facial image and target facial image
The estimation age store to presetting database, can realize presetting database stores the continuous renewal of data so that preset
In data base, the quantity of the facial image of storage is gradually increased, and the estimation of Age result being also follow-up is more accurate.
Following for disclosure device embodiment, may be used for performing method of disclosure embodiment.Real for disclosure device
Execute the details not disclosed in example, refer to method of disclosure embodiment.
Fig. 3 is the structural representation according to a kind of estimation of Age device shown in an exemplary embodiment.With reference to Fig. 3, should
Estimation of Age device 30 includes acquisition module 31, extraction module 32, comparing module 33 and processing module 34.
This acquisition module 31, is configured to obtain target facial image.
This extraction module 32, is configured to, based on default face recognition algorithms, extract the target person that acquisition module 31 obtains
The facial image feature that face image is corresponding.
This comparing module 33, the facial image feature being configured to extract extraction module 32 is deposited in presetting database
Storage facial image feature is compared, it is thus achieved that similarity.
This processing module 34, if being configured to the similarity of comparing module 33 acquisition more than or equal to predetermined threshold value, then root
According to obtain this similarity store the age information that facial image feature is corresponding, determine the estimation age of target facial image.
In sum, the estimation of Age device that the present embodiment provides, special according to the facial image that presetting database has stored
Levy the age information of correspondence, determine the target facial image having stored facial image characteristic similarity with this more than predetermined threshold value
Estimate the age, to improve the degree of accuracy of estimation of Age.
Fig. 4 is the structural representation according to a kind of estimation of Age device shown in another exemplary embodiment.With reference to Fig. 4,
On the basis of structure shown in Fig. 3, in a kind of implementation, processing module 34 includes: first processes submodule 341.
This first process submodule 341, is configured to according to the facial image feature pair of storage obtaining described similarity
The date of birth answered and the generation time of target facial image, determine the estimation age of target facial image.
In another kind of implementation, processing module 34 includes: second processes submodule 342.
This second process submodule 342, is configured to according to the facial image feature pair of storage obtaining described similarity
Estimation age that the generation time of the facial image answered, described facial image are corresponding and target facial image, determine target face
The estimation age of image.
In this implementation, further, second processes submodule 342 is configured to: according to described target facial image,
Obtain the first estimation age of described target facial image；Corresponding according to the facial image feature of storage obtaining described similarity
Facial image generate time and the generation time of described target facial image, obtain very first time difference；By described first
Estimate that the age deducts described very first time difference, obtain the second time difference；Calculate described second time difference and described face
The average estimating the age that image is corresponding, obtains the estimation age of described target facial image.
Fig. 5 is the structural representation according to a kind of estimation of Age device shown in further example embodiment.With reference to Fig. 5,
On the basis of structure shown in Fig. 3, estimation of Age device 40 can also include another processing module 41 and tracking module 42.Its
In, tracking module 42 is optional module, say, that estimation of Age device 40 can not also include tracking module 42.
This processing module 41, if the described similarity being configured to comparing module 33 acquisition is less than described predetermined threshold value, then
According to target facial image, determine the estimation age of target facial image.
This tracking module 42, if the described similarity being configured to comparing module 33 acquisition is less than described predetermined threshold value, adopts
With target tracking algorism, the face that target facial image is corresponding is tracked.
In sum, the estimation of Age device that the present embodiment provides, use target tracking algorism face is carried out in real time with
Track, can obtain the position of face in each two field picture, need not carry out repeating to estimate the age, improve speed.
Fig. 6 is the structural representation according to a kind of estimation of Age device shown in another exemplary embodiment.With reference to Fig. 6,
(illustrating as a example by Fig. 3 here) on the basis of structure shown in Fig. 3 or Fig. 4 or Fig. 5, estimation of Age device 50 can also wrap
Include memory module 51.
This memory module 51, is configured to store the estimation age of target facial image and target facial image to present count
According to storehouse.
If as a example by structure shown in Fig. 5, memory module couples with processing module 34 and processing module 41 respectively.
In sum, the estimation of Age device that the present embodiment provides, by by target facial image and target facial image
The estimation age store to presetting database, can realize presetting database stores the continuous renewal of data so that preset
In data base, the quantity of the facial image of storage is gradually increased, and the estimation of Age result being also follow-up is more accurate.
In the above-described embodiments, target facial image is that the mobile device with camera function obtains under preview mode
's.
It should be noted that, the function of the acquisition module mentioned by disclosure embodiment and functioning as in mobile device
Receptor, extraction module, tracking module, the function of processing module and the processor functioned as in mobile device, comparison
The function of module and the processor that functions as in mobile device or comparator, the function of memory module and function as shifting
Memorizer in dynamic equipment.
Fig. 7 is according to a kind of estimation of Age device block diagram shown in an exemplary embodiment.With reference to Fig. 7, estimation of Age fills
Put 800 and can include following one or more assembly: process assembly 802, memorizer 804, power supply module 806, multimedia groupware
808, audio-frequency assembly 810, (input/output is called for short: I/O) interface 812, sensor cluster 814, Yi Jitong in input/output
Letter assembly 816.
Process assembly 802 and generally control the integrated operation of estimation of Age device 800, such as with display, data communication, camera
The operation that operation and record operation are associated.Process assembly 802 and can include that one or more processor 820 performs instruction,
To complete all or part of step of above-mentioned method.Additionally, process assembly 802 can include one or more module, it is simple to
Process between assembly 802 and other assemblies is mutual.Such as, process assembly 802 and can include multi-media module, to facilitate many matchmakers
Body assembly 808 and process between assembly 802 mutual.
Memorizer 804 is configured to store various types of data to support the operation at estimation of Age device 800.These
The example of data includes any application program for operation on estimation of Age device 800 or the instruction of method, contacts number
According to, telephone book data, message, picture, video etc..Memorizer 804 can be by any kind of volatibility or non-volatile memories
Equipment or combinations thereof realize, as static RAM (Static Random Access Memory, is called for short:
SRAM), Electrically Erasable Read Only Memory (Electrically Erasable Programmable Read-Only
Memory, is called for short: EEPROM), Erasable Programmable Read Only Memory EPROM (Erasable Programmable Read Only
Memory, is called for short: EPROM), programmable read only memory (Programmable Red-Only Memory, is called for short: PROM),
(Read-Only Memory is called for short: ROM), magnetic memory, flash memory, disk or CD read only memory.
The various assemblies that power supply module 806 is estimation of Age device 800 provide electric power.Power supply module 806 can include electricity
Management system, one or more power supplys, and other with generate, manage and distribute electric power for estimation of Age device 800 and be associated
Assembly.
One output interface of offer that multimedia groupware 808 is included between described estimation of Age device 800 and user
Screen.In certain embodiments, screen can include liquid crystal display (Liquid Crystal Display, be called for short: LCD) and
(Touch Panel is called for short: TP) touch panel.If screen includes that touch panel, screen may be implemented as touch screen, with
Receive the input signal from user.Touch panel includes that one or more touch sensor touches with sensing, slides and touch
Gesture on panel.Described touch sensor can not only sense touch or the border of sliding action, but also detection is with described
Touch or persistent period that slide is relevant and pressure.In certain embodiments, multimedia groupware 808 includes that one preposition is taken the photograph
As head and/or post-positioned pick-up head.When age estimation unit 800 is in operator scheme, during such as screening-mode or video mode, preposition
Photographic head and/or post-positioned pick-up head can receive the multi-medium data of outside.Each front-facing camera and post-positioned pick-up head are permissible
It is a fixing optical lens system or there is focal length and optical zoom ability.
Audio-frequency assembly 810 is configured to output and/or input audio signal.Such as, audio-frequency assembly 810 includes a Mike
(Microphone is called for short: MIC), when age estimation unit 800 is in operator scheme, such as call model, logging mode and language wind
During sound recognition mode, mike is configured to receive external audio signal.The audio signal received can be further stored
Send at memorizer 804 or via communications component 816.In certain embodiments, audio-frequency assembly 810 also includes a speaker,
For exporting audio signal.
I/O interface 812 provides interface for processing between assembly 802 and peripheral interface module, above-mentioned peripheral interface module can
To be keyboard, put striking wheel, button etc..These buttons may include but be not limited to: home button, volume button, start button and lock
Set button.
Sensor cluster 814 includes one or more sensor, for providing various aspects for estimation of Age device 800
State estimation.Such as, what sensor cluster 814 can detect estimation of Age device 800 opens/closed mode, the phase of assembly
To location, the most described assembly is display and the keypad of estimation of Age device 800, and sensor cluster 814 can also detect
Estimation of Age device 800 or the position change of 800 1 assemblies of estimation of Age device, user contacts with estimation of Age device 800
Presence or absence, estimation of Age device 800 orientation or acceleration/deceleration and the variations in temperature of estimation of Age device 800.Sensing
Device assembly 814 can include proximity transducer, is configured to when not having any physical contact depositing of object near detection
?.Sensor cluster 814 can also include optical sensor, such as complementary metal oxide semiconductors (CMOS) (Complementary Metal
Oxide Semiconductor, be called for short: CMOS) or charge coupled cell (Charge-coupled Device, be called for short: CCD)
Photosensitive imaging element, for using in imaging applications.In certain embodiments, this sensor cluster 814 can also include adding
Velocity sensor, gyro sensor, Magnetic Sensor, pressure transducer or temperature sensor.
Communications component 816 is configured to facilitate wired or wireless mode between estimation of Age device 800 and other equipment
Communication.Estimation of Age device 800 can access wireless network based on communication standard, such as Wireless Fidelity (Wireless-
Fidelity, is called for short: Wi-Fi), 2G or 3G, or combinations thereof.In one exemplary embodiment, communications component 816 via
Broadcast channel receives the broadcast singal from external broadcasting management system or broadcast related information.An exemplary embodiment
In, described communications component 816 also includes that (Near Field Communication, is called for short: NFC) module near-field communication, to promote
Enter junction service.Such as, NFC module can based on RF identification (Radio Frequency Identification, be called for short:
RFID) technology, (Infrared Data Association is called for short: IrDA) technology, ultra broadband (Ultra in Infrared Data Association
Wideband, is called for short: UWB) technology, and (Bluetooth is called for short: BT) technology and other technologies realize bluetooth.
In the exemplary embodiment, estimation of Age device 800 can be by one or more application specific integrated circuits
ASIC), digital signal processor (Digital (Application Specific Integrated Circuit is called for short:
Signal Processor, be called for short: DSP), digital signal processing appts (Digital Signal Processing Device,
PLD), field-programmable gate array it is called for short: DSPD), (Programmable Logic Device is called for short: PLD
Row (Field Programmable Gate Array, be called for short: FPGA), controller, microcontroller, microprocessor or other electricity
Sub-element realizes, and is used for performing said method.
In the exemplary embodiment, a kind of non-transitory computer-readable recording medium including instruction, example are additionally provided
As included the memorizer 804 of instruction, above-mentioned instruction can have been performed above-mentioned side by the processor 820 of estimation of Age device 800
Method.Such as, described non-transitory computer-readable recording medium can be ROM, random access memory (Random Access
CD-ROM), tape, soft Memory, is called for short: RAM), (Compact Disc Read-Only Memory, is called for short read-only optical disc:
Dish and optical data storage devices etc..
A kind of non-transitory computer-readable recording medium, when the instruction in described storage medium is by estimation of Age device
When the processor of 800 performs so that estimation of Age device 800 is able to carry out a kind of age estimation method, and described method includes: obtain
Take target facial image；Based on default face recognition algorithms, extract the facial image feature that described target facial image is corresponding；Will
Described facial image feature and presetting database store facial image feature compare, it is thus achieved that similarity；If described phase
Like degree more than or equal to predetermined threshold value, then believe according to age corresponding to facial image feature that store obtaining described similarity
Breath, determines the estimation age of described target facial image.
Those skilled in the art, after considering description and putting into practice invention disclosed herein, will readily occur to its of the disclosure
Its embodiment.The application is intended to any modification, purposes or the adaptations of the disclosure, these modification, purposes or
Person's adaptations is followed the general principle of the disclosure and includes the undocumented common knowledge in the art of the disclosure
Or conventional techniques means.Description and embodiments is considered only as exemplary, and the true scope of the disclosure and spirit are by following
Claims are pointed out.
It should be appreciated that the disclosure is not limited to precision architecture described above and illustrated in the accompanying drawings, and
And various modifications and changes can carried out without departing from the scope.The scope of the present disclosure is only limited by appending claims
System.
Claims (13)
1. an age estimation method, it is characterised in that including:
Obtain target facial image；
Based on default face recognition algorithms, extract the facial image feature that described target facial image is corresponding；
Compare described facial image feature and presetting database have stored facial image feature, it is thus achieved that similarity；
If described similarity is more than or equal to predetermined threshold value, then according to the facial image feature pair of storage obtaining described similarity
The age information answered, determines the estimation age of described target facial image.
Method the most according to claim 1, it is characterised in that described according to the face figure of storage obtaining described similarity
As the age information that feature is corresponding, determine the estimation age of described target facial image, including:
Date of birth corresponding to facial image feature and described target facial image is stored according to obtain described similarity
The generation time, determine the estimation age of described target facial image.
Method the most according to claim 1, it is characterised in that described according to the face figure of storage obtaining described similarity
As the age information that feature is corresponding, determine the estimation age of described target facial image, including:
According to obtaining the generation time storing facial image corresponding to facial image feature of described similarity, described face figure
As corresponding estimation age and described target facial image, determine the estimation age of described target facial image.
Method the most according to claim 3, it is characterised in that described according to the face figure of storage obtaining described similarity
The estimation age corresponding as the time that generates of facial image corresponding to feature, described facial image and described target facial image,
Determine the estimation age of described target facial image, including:
According to described target facial image, it is thus achieved that the first estimation age of described target facial image；
According to obtaining the generation time storing facial image corresponding to facial image feature of described similarity and described target
The generation time of facial image, obtain very first time difference；
Estimate that the age deducts described very first time difference by described first, obtain the second time difference；
Calculate the average estimating the age that described second time difference is corresponding with described facial image, obtain described target face figure
The estimation age of picture.
Method the most according to any one of claim 1 to 4, it is characterised in that described determine described target facial image
The estimation age after, described method also includes:
Store the estimation age of described target facial image and described target facial image to described presetting database.
Method the most according to any one of claim 1 to 4, it is characterised in that described target facial image is taken the photograph for having
The mobile device of picture function obtains under preview mode.
7. an estimation of Age device, it is characterised in that including:
Acquisition module, is configured to obtain target facial image；
Extraction module, is configured to, based on default face recognition algorithms, extract the described target face that described acquisition module obtains
The facial image feature that image is corresponding；
Comparing module, the described facial image feature being configured to extract described extraction module stores in presetting database
Facial image feature is compared, it is thus achieved that similarity；
Processing module, if being configured to the described similarity of described comparing module acquisition more than or equal to predetermined threshold value, then basis
Obtain described similarity stores the age information that facial image feature is corresponding, determines the estimation year of described target facial image
Age.
Device the most according to claim 7, it is characterised in that described processing module includes:
First processes submodule, is configured to according to obtaining when storing birth corresponding to facial image feature of described similarity
Between and the generation time of described target facial image, determine the estimation age of described target facial image.
Device the most according to claim 7, it is characterised in that described processing module includes:
Second process submodule, be configured to according to obtain described similarity store the face figure that facial image feature is corresponding
Picture generate estimation age corresponding to time, described facial image and described target facial image, determine described target face figure
The estimation age of picture.
Device the most according to claim 9, it is characterised in that described second processes submodule is configured to:
According to described target facial image, it is thus achieved that the first estimation age of described target facial image；
According to obtaining the generation time storing facial image corresponding to facial image feature of described similarity and described target
The generation time of facial image, obtain very first time difference；
Estimate that the age deducts described very first time difference by described first, obtain the second time difference；
Calculate the average estimating the age that described second time difference is corresponding with described facial image, obtain described target face figure
The estimation age of picture.
11. according to the device according to any one of claim 7 to 10, it is characterised in that described device also includes:
Memory module, is configured to the estimation age storing described target facial image and described target facial image to described pre-
If data base.
12. according to the device according to any one of claim 7 to 10, it is characterised in that described target facial image is for having
The mobile device of camera function obtains under preview mode.
13. 1 kinds of estimation of Age devices, it is characterised in that including:
Processor；
For storing the memorizer of described processor executable；
Wherein, described processor is configured to:
Obtain target facial image；
Based on default face recognition algorithms, extract the facial image feature that described target facial image is corresponding；
Compare described facial image feature and presetting database have stored facial image feature, it is thus achieved that similarity；
If described similarity is more than or equal to predetermined threshold value, then according to the facial image feature pair of storage obtaining described similarity
The age information answered, determines the estimation age of described target facial image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610581752.0A CN106295499B (en) | 2016-07-21 | 2016-07-21 | Age estimation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610581752.0A CN106295499B (en) | 2016-07-21 | 2016-07-21 | Age estimation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106295499A true CN106295499A (en) | 2017-01-04 |
| CN106295499B CN106295499B (en) | 2019-10-11 |
Family
ID=57651955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610581752.0A Active CN106295499B (en) | 2016-07-21 | 2016-07-21 | Age estimation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106295499B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133576A (en) * | 2017-04-17 | 2017-09-05 | 北京小米移动软件有限公司 | Age of user recognition methods and device |
| CN107194868A (en) * | 2017-05-19 | 2017-09-22 | 成都通甲优博科技有限责任公司 | A kind of Face image synthesis method and device |
| CN107192542A (en) * | 2017-05-19 | 2017-09-22 | 北京车和家信息技术有限责任公司 | Feel detection means, method, system, computer equipment and readable storage medium storing program for executing |
| CN107590464A (en) * | 2017-09-12 | 2018-01-16 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
| CN108197592A (en) * | 2018-01-22 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| WO2019000466A1 (en) * | 2017-06-30 | 2019-01-03 | 广东欧珀移动通信有限公司 | Face recognition method and apparatus, storage medium, and electronic device |
| CN109190449A (en) * | 2018-07-09 | 2019-01-11 | 北京达佳互联信息技术有限公司 | Age recognition methods, device, electronic equipment and storage medium |
| CN109459722A (en) * | 2018-10-23 | 2019-03-12 | 同济大学 | Voice interactive method based on face tracking device |
| CN110008926A (en) * | 2019-04-15 | 2019-07-12 | 北京字节跳动网络技术有限公司 | The method and apparatus at age for identification |
| CN110909597A (en) * | 2019-10-14 | 2020-03-24 | 深圳市元征科技股份有限公司 | Vehicle child lock falling control method and device and vehicle-mounted equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101584575A (en) * | 2009-06-19 | 2009-11-25 | 无锡骏聿科技有限公司 | Age assessment method based on face recognition technology |
| CN102508606A (en) * | 2011-11-10 | 2012-06-20 | 广东步步高电子工业有限公司 | Method and system for subdividing belonged groups of users by face recognition and setting corresponding functions of mobile handsets |
| CN104992151A (en) * | 2015-06-29 | 2015-10-21 | 华侨大学 | Age estimation method based on TFIDF face image |
| CN105069083A (en) * | 2015-07-31 | 2015-11-18 | 小米科技有限责任公司 | Determination method and device of associated user |
| CN105069016A (en) * | 2015-07-13 | 2015-11-18 | 小米科技有限责任公司 | Photograph album management method, photograph album management apparatus and terminal equipment |
-
2016
- 2016-07-21 CN CN201610581752.0A patent/CN106295499B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101584575A (en) * | 2009-06-19 | 2009-11-25 | 无锡骏聿科技有限公司 | Age assessment method based on face recognition technology |
| CN102508606A (en) * | 2011-11-10 | 2012-06-20 | 广东步步高电子工业有限公司 | Method and system for subdividing belonged groups of users by face recognition and setting corresponding functions of mobile handsets |
| CN104992151A (en) * | 2015-06-29 | 2015-10-21 | 华侨大学 | Age estimation method based on TFIDF face image |
| CN105069016A (en) * | 2015-07-13 | 2015-11-18 | 小米科技有限责任公司 | Photograph album management method, photograph album management apparatus and terminal equipment |
| CN105069083A (en) * | 2015-07-31 | 2015-11-18 | 小米科技有限责任公司 | Determination method and device of associated user |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133576A (en) * | 2017-04-17 | 2017-09-05 | 北京小米移动软件有限公司 | Age of user recognition methods and device |
| CN107194868A (en) * | 2017-05-19 | 2017-09-22 | 成都通甲优博科技有限责任公司 | A kind of Face image synthesis method and device |
| CN107192542A (en) * | 2017-05-19 | 2017-09-22 | 北京车和家信息技术有限责任公司 | Feel detection means, method, system, computer equipment and readable storage medium storing program for executing |
| WO2019000466A1 (en) * | 2017-06-30 | 2019-01-03 | 广东欧珀移动通信有限公司 | Face recognition method and apparatus, storage medium, and electronic device |
| US11380131B2 (en) | 2017-06-30 | 2022-07-05 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method and device for face recognition, storage medium, and electronic device |
| CN107590464A (en) * | 2017-09-12 | 2018-01-16 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
| CN108197592B (en) * | 2018-01-22 | 2022-05-27 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| CN108197592A (en) * | 2018-01-22 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| CN109190449A (en) * | 2018-07-09 | 2019-01-11 | 北京达佳互联信息技术有限公司 | Age recognition methods, device, electronic equipment and storage medium |
| CN109459722A (en) * | 2018-10-23 | 2019-03-12 | 同济大学 | Voice interactive method based on face tracking device |
| CN110008926B (en) * | 2019-04-15 | 2020-06-26 | 北京字节跳动网络技术有限公司 | Method and device for identifying age |
| CN110008926A (en) * | 2019-04-15 | 2019-07-12 | 北京字节跳动网络技术有限公司 | The method and apparatus at age for identification |
| CN110909597A (en) * | 2019-10-14 | 2020-03-24 | 深圳市元征科技股份有限公司 | Vehicle child lock falling control method and device and vehicle-mounted equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106295499B (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106295499A (en) | Age estimation method and device | |
| CN110602527B (en) | Video processing method, device and storage medium | |
| CN105512685B (en) | Object identification method and device | |
| CN106228556B (en) | image quality analysis method and device | |
| CN106548145A (en) | Image-recognizing method and device | |
| CN107832741A (en) | The method, apparatus and computer-readable recording medium of facial modeling | |
| CN105631406B (en) | Image recognition processing method and device | |
| CN105205479A (en) | Human face value evaluation method, device and terminal device | |
| CN105631408A (en) | Video-based face album processing method and processing device | |
| CN107463903B (en) | Face key point positioning method and device | |
| CN105631403A (en) | Method and device for human face recognition | |
| CN110503023A (en) | Biopsy method and device, electronic equipment and storage medium | |
| CN105678242B (en) | Focusing method and device under hand-held certificate mode | |
| CN104408402A (en) | Face identification method and apparatus | |
| CN105095881A (en) | Method, apparatus and terminal for face identification | |
| CN112258381A (en) | Model training method, image processing method, device, equipment and storage medium | |
| CN104077563B (en) | Face identification method and device | |
| CN106295515A (en) | Determine the method and device of human face region in image | |
| CN106355549A (en) | Photographing method and equipment | |
| CN106980840A (en) | Shape of face matching process, device and storage medium | |
| CN105335713A (en) | Fingerprint identification method and device | |
| CN107886070A (en) | Verification method, device and the equipment of facial image | |
| CN103886284B (en) | Character attribute information identifying method, device and electronic equipment | |
| CN105654039A (en) | Image processing method and device | |
| CN106250921A (en) | Image processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |