CN109858379A - Smile's sincerity degree detection method, device, storage medium and electronic equipment - Google Patents
Smile's sincerity degree detection method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN109858379A CN109858379A CN201910003267.9A CN201910003267A CN109858379A CN 109858379 A CN109858379 A CN 109858379A CN 201910003267 A CN201910003267 A CN 201910003267A CN 109858379 A CN109858379 A CN 109858379A
- Authority
- CN
- China
- Prior art keywords
- micro
- smile
- expression
- expressive features
- sincerity degree
- 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
Landscapes
- Image Analysis (AREA)
Abstract
This disclosure relates to micro- Expression Recognition technical field, a kind of smile's sincerity degree detection method and device, storage medium and electronic equipment are disclosed.Smile's sincerity degree detection method includes: to acquire micro- expression of user；Feature extraction is carried out to micro- expression, to obtain micro- expressive features data with multiple default dimensions；Mapping model is obtained, the mapping model is formed based on micro- expressive features data sample and the training of corresponding smile's sincerity degree；By the mapping model, smile's sincerity degree of the user is obtained using micro- expressive features data described in extraction with multiple default dimensions.The disclosure is based on micro- Expression Recognition technology, according to the corresponding smile's sincerity degree of the corresponding micro- micro- expression of expressive features data acquisition of micro- expression, improves the accuracy for judging smile's sincerity degree.
Description
Technical field
This disclosure relates to micro- Expression Recognition technical field, more specifically, disclosing a kind of smile's sincerity degree detection method, laughing at
Hold sincerity degree detection device, storage medium and electronic equipment.
Background technique
In daily life, either daily communication or business meeting etc. are various contacts the industry linked up with people, links up
Whether whether the sense of reality of both sides smoothly succeed with business for linking up, and plays the role of to despise；Meanwhile with society
Development, requirement of the people to the quality of service industry is higher and higher, such as requires server that must keep smile etc., therefore, can
Realizing is particularly important the identification for linking up both sides smile.
Currently, only may determine that whether expression belongs to smile's expression using face recognition technology, and have ignored different laugh at
Hold expression between otherness, cannot by various smile's expressions carry out level differentiation, and then can not identify smile's expression whether be
Smile from the deep of the heart.For example, in order to complete the smile that a certain task haves no alternative but show, although by face recognition technology
The expression belongs to smile's expression, but can not judge the sincerity degree of smile.
Therefore, there is a need in the field to provide a kind of smile's sincerity degree detection methods.
It should be noted that the information in the invention of above-mentioned background technology part is only used for reinforcing the reason to the background of the disclosure
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure is designed to provide a kind of smile's sincerity degree detection method and device, storage medium and electronic equipment,
And then caused by overcoming the problems, such as the differentiation since various smiles can not be carried out to otherness at least to a certain extent, such as examine
Core personnel cannot be distinguished by the otherness of examination personnel smile, and subjective emotion is generated to by the smile result of appraisal of examination personnel
It influences, is unfavorable for the management and progress of relevant enterprise and industry；Job hunter's smile's otherness cannot be distinguished, influence related enterprise
Recruitment quality of industry, etc..To realize that the above technical effect, the disclosure adopt the following technical scheme that.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to one aspect of the disclosure, a kind of smile's sincerity degree detection method is provided, comprising: acquire micro- table of user
Feelings；Feature extraction is carried out to micro- expression, to obtain micro- expressive features data with multiple default dimensions；Obtain mapping mould
Type, the mapping model are formed based on micro- expressive features data sample and the training of corresponding smile's sincerity degree；By described
Mapping model, the smile for obtaining the user using micro- expressive features data described in extraction with multiple default dimensions are sincere
Degree.
In a kind of exemplary embodiment of the disclosure, the method also includes: obtain a plurality of training data, the training
Data include micro- expressive features data sample and the corresponding smile's sincerity degree of micro- expressive features data sample；It will be described micro-
Expressive features data sample is input to a machine learning model as output vector as input vector, smile's sincerity degree,
The machine learning model is trained, to generate the mapping model.
In a kind of exemplary embodiment of the disclosure, a plurality of training data of acquisition includes: according to predeterminable area
Expressive features information screens the micro- expression of smile, from a variety of micro- expressions to obtain the micro- expression sample of smile；It is micro- based on the smile
Expression sample extracts micro- expressive features data according to the multiple default dimension, to obtain micro- expressive features data
Sample；The corresponding smile's sincerity degree of the micro- expression of smile in the micro- expression sample of the smile is obtained, according to micro- expressive features
Data sample and smile's sincerity degree obtain the training data.
In a kind of exemplary embodiment of the disclosure, the expressive features information of the predeterminable area include eyes narrowed,
One of palpebra inferior protrusion, orbicular muscle of eye contraction, corners of the mouth tilting, cheek protrusion or chin expansion are a variety of；The basis is pre-
If the expressive features information in region, the micro- expression of smile is screened, from a variety of micro- expressions to obtain the micro- expression sample of smile, comprising:
Micro- expression of all expressive features information with the predeterminable area is screened, from a variety of micro- expressions to obtain described laugh at
Hold micro- expression sample.
In a kind of exemplary embodiment of the disclosure, the micro- expression of smile obtained in the micro- expression sample of smile
Corresponding smile's sincerity degree, comprising: the micro- expression of smile obtained in the micro- expression sample of the smile is corresponding with multiple default
Micro- expressive features data of dimension；Obtain the weighted value of each default dimension；According to the weighted value of each default dimension with
And corresponding micro- expressive features data, obtain the corresponding smile's sincerity degree of the micro- expression of smile in the micro- expression sample of the smile.
It is described by the mapping model in a kind of exemplary embodiment of the disclosure, have using described in extraction
Micro- expressive features data of multiple default dimensions obtain smile's sincerity degree of the user, comprising: more by having described in extraction
Micro- expressive features data of a default dimension are input to the mapping model, corresponding with micro- expressive features data with determination
Smile's sincerity degree.
In a kind of exemplary embodiment of the disclosure, the default dimension includes ocular, cheek region and lip
Region.
According to one aspect of the disclosure, a kind of smile's sincerity degree detection device is provided, comprising: expression acquisition module is used
In micro- expression of acquisition user；Characteristic extracting module, for carrying out feature extraction to micro- expression, to obtain with multiple pre-
If micro- expressive features data of dimension；Mapping obtains module, and for obtaining mapping model, the mapping model is based on micro- expression
What characteristic sample and the training of corresponding smile's sincerity degree were formed；Smile's sincerity degree obtains module, for passing through the mapping
Model obtains smile's sincerity degree of the user using micro- expressive features data described in extraction with multiple default dimensions.
According to one aspect of the disclosure, a kind of storage medium is provided, computer program, the computer are stored thereon with
Smile's sincerity degree detection method described in above-mentioned any one is realized when program is executed by processor.
According to one aspect of the disclosure, a kind of electronic equipment is provided, comprising: processor；And memory, for storing
The executable instruction of the processor；Wherein, the processor is configured to above-mentioned to execute via the executable instruction is executed
Smile's sincerity degree detection method described in any one.
In smile's sincerity degree detection method of the disclosure, pass through reflecting between micro- expressive features data and smile's sincerity degree
Model is penetrated, using the micro- expressive features data extracted from micro- expression of user, obtains smile's sincerity degree of user.One side
Face is extracted micro- expressive features data with multiple default dimensions, realizes the comprehensive analysis to user's face expression, improves
The reliability of micro- Expression Recognition；Meanwhile the omission of micro- expressive features is avoided, and then improve the detection of user's smile's sincerity degree
Accuracy.On the other hand, sincere using the smile of the micro- expressive features data acquisition user extracted by mapping model
The micro- expression of various smiles is carried out level differentiation, improves the efficiency of smile's sincerity degree detection by degree.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The following detailed description is read with reference to the accompanying drawings, above-mentioned and other mesh of disclosure illustrative embodiments
, feature and advantage will become prone to understand.In the accompanying drawings, if showing the disclosure by way of example rather than limitation
Dry embodiment, in which:
Fig. 1 schematically shows the flow chart of smile's sincerity degree detection method according to disclosure embodiment；
Fig. 2 schematically shows the flow charts for generating mapping model according to disclosure embodiment；
Fig. 3 schematically shows the flow chart of a plurality of training data of acquisition according to disclosure embodiment；
Fig. 4 schematically shows according to disclosure embodiment based on mapping model, it is multiple using having for extraction
Micro- expressive features data of default dimension obtain the flow chart of user's smile's sincerity degree；
Fig. 5 schematically shows the schematic diagram of smile's sincerity degree detection device according to disclosure embodiment；
Fig. 6 schematically shows the schematic diagram of the storage medium according to disclosure embodiment；
Fig. 7 schematically shows the block diagram of the electronic equipment according to disclosure embodiment.
In the accompanying drawings, identical or corresponding label indicates identical or corresponding part.
Specific embodiment
Illustrative embodiments are described more fully with reference to the drawings.However, illustrative embodiments can be with more
Kind form is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Add fully and completely, and the design of illustrative embodiments is comprehensively communicated to those skilled in the art.It is identical in figure
Appended drawing reference indicates same or similar structure, thus the detailed description that will omit them.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can be with technical solution of the disclosure without one in the specific detail or more
It is more, or can be using other methods, constituent element, device, step etc..In other cases, known in being not shown in detail or describing
Structure, method, apparatus, realization or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or these are realized in the module of one or more softwares hardening
A part of functional entity or functional entity, or realized in heterogeneous networks and/or processor device and/or microcontroller device
These functional entitys.
This field in the related technology, the identification to the micro- expression (such as smile) of face is the base in human facial expression recognition
On plinth, intellectual analysis further is carried out to facial characteristics and detects micro- expression, usually by characteristic area (such as eyes, eyebrow and
Mouth etc.) model or topological structure are established, and required characteristic point or geometrical characteristic region are extracted in figure after imaging,
These characteristic points or characteristic area are compared with well-established model or topological structure finally, realize the base to micro- expression
This judgement.
Correspondingly, correlative technology field, which has following defects that the identification of the micro- expression of smile, only may determine that facial table
Whether feelings belong to the micro- expression of smile, have ignored the otherness between the micro- expression of all kinds of smiles, it is difficult to whether obtain the micro- expression of smile
It is sincere smile, i.e., can not detects the sincerity degree of smile.
Based on this, in an exemplary embodiment of the disclosure, a kind of smile's sincerity degree detection method is provided firstly.Fig. 1
Show smile's sincerity degree detection method flow diagram, refering to what is shown in Fig. 1, smile's sincerity degree detection method may include with
Lower step:
Step S110: micro- expression of user is acquired；
Step S120: carrying out feature extraction to micro- expression, to obtain micro- expressive features with multiple default dimensions
Data；
Step S130: obtaining mapping model, and the mapping model is based on micro- expressive features data sample and corresponding to laugh at
Hold what the training of sincerity degree was formed；
Step S140: by the mapping model, micro- expressive features described in extraction with multiple default dimensions are utilized
Data obtain smile's sincerity degree of the user.
According to smile's sincerity degree detection method in this example embodiment, on the one hand, be extracted with multiple default dimensions
Micro- expressive features data, realize the comprehensive analysis to user's face expression, improve the reliability of micro- Expression Recognition；Together
When, the omission of micro- expressive features is avoided, and then improve the accuracy of user's smile's sincerity degree detection.On the other hand, pass through
Mapping model is carried out the micro- expression of various smiles using smile's sincerity degree of the micro- expressive features data acquisition user extracted
Level is distinguished, and the efficiency of smile's sincerity degree detection is improved.
In an exemplary embodiment of the disclosure, a kind of smile's sincerity degree detection method is provided firstly, can use clothes
Device be engaged in realize smile's sincerity degree detection method of the disclosure, which can be the server of micro- Expression Recognition platform.
Refering to what is shown in Fig. 1, smile's sincerity degree detection method may comprise steps of:
In step s 110, micro- expression of user is acquired.
In this example embodiment, micro- expression of user can be acquired by image capture device, which sets
It is standby to can be all kinds of electronic equipments with camera, such as smart phone, PAD, camera or video camera, pass through those images
Equipment is acquired, real-time micro- expression of user can be obtained；The face stored in its terminal device can also be uploaded by receiving user
Image, and the face-image is identified to obtain the micro- expression of user.In addition, before micro- expression of acquisition user, Ke Yixian
Establishing micro- expression data library can be for storing micro- expression, micro- expression therein through a large amount of micro- of image capture device acquisition
A large amount of micro- expressions that expression or the user received upload；Further, in order to make the micro- expression of user in micro- expression data library
It is representative, the range of the acquisition micro- expression of user can also be increased, such as can be from all kinds of websites (such as Baidu, Google)
The image of a variety of micro- expressions is obtained, and is stored in micro- expression data library, as it will be apparent to a skilled person that this is micro-
Expression data library includes all kinds of micro- expressions, such as smile, sadness, sobbing, contempt or indignation.
In the step s 120, feature extraction is carried out to micro- expression, to obtain micro- expression with multiple default dimensions
Characteristic.
It is to extract with multiple default to the purpose that micro- expression carries out feature extraction in this example embodiment
The face characteristic of dimension, so as to subsequent micro- Expression Recognition.First by the way that face is divided into the area with multiple default dimensions
Domain, then respectively from each extracted region expressive features, to obtain micro- expressive features data, finally according to those with multiple default
Micro- expressive features data of dimension, judge the different true emotionals being hidden in micro- expression.Wherein, the spy of expressive features
Sign extracting method can be optical flow method, LBP-TOP (Local Binary Pattern from Three Orthogonal
Planes) feature extraction algorithm and filtering extraction method (Gabor).Also, each default dimension may include reflection user one
Or the expressive parts of multiple micro- expressive features data, for example, default dimension may include the ocular of user, cheek region,
Lip-region and chin area etc..Wherein, ocular may include palpebra inferior part, canthus part, can pass through those portions
Separately win take the micro- expressive features data in family (such as palpebra inferior whether protrusion, whether canthus is bent downwardly, whether eye tail fish tail occurs
Line)；By the cheek of the available user of cheek region whether Tu Qi micro- expressive features data；Lip-region includes mouth portion
Point, dental part and gum portion, can be obtained by those parts the micro- expressive features data of user (whether such as corners of the mouth raise up,
Whether the corners of the mouth occurs whether dimple, tooth expose, whether gum exposes)；Whether it is unfolded by the available chin of chin area
Micro- expressive features data, etc..
It should be noted that in the other exemplary embodiments of the disclosure, according to age, gender and locating bad border etc.
The difference of situation, default dimension can also include other expression regions, for example including Nasolabial Fold Region etc., the present exemplary embodiment
In particular determination is not done to this.
Step S130: obtaining mapping model, and the mapping model is based on micro- expressive features data sample and corresponding to laugh at
Hold what the training of sincerity degree was formed.
In this example embodiment, mapping model is used to indicate pair between micro- expressive features data and smile's sincerity degree
It should be related to.Mapping model determines the smile's sincerity degree obtained according to the micro- expressive features data extracted, can be default
Mathematical model, such as machine learning model.In the following, being described in detail for how to generate above-mentioned mapping model.
When the mapping model is data model, mapping model can be generated by machine learning, as shown in Fig. 2, this
In smile's sincerity degree detection method of example embodiment, generating mapping model be may include steps of:
Step S210: obtaining a plurality of training data, and the training data includes micro- expressive features data sample and described
The corresponding smile's sincerity degree of micro- expressive features data sample.
In this example embodiment, in order to be trained generation mapping model to machine learning model, it is necessary first to obtain
A plurality of training data is taken, which includes at least micro- expressive features data sample and micro- expressive features data sample
Corresponding smile's sincerity degree, by the way that training data is input to machine learning model to be trained generation mapping model to it.
Fig. 3 shows the flow chart for obtaining a plurality of training data, as shown in figure 3, can be obtained by following step S310 to step S330
Take a plurality of training data.
Step S310: according to the expressive features information of predeterminable area, screening the micro- expression of smile from a variety of micro- expressions, with
To the micro- expression sample of smile.
In this example embodiment, the expressive features information of predeterminable area includes that eyes have been narrowed, palpebra inferior is raised, eye wheel
One of orbiculares contraction, corners of the mouth tilting, cheek protrusion or chin expansion are a variety of；All tools are screened from micro- expression data library
There is micro- expression of above-mentioned predeterminable area expressive features information, to obtain the micro- expression sample of smile, in order to avoid obtained smile is micro-
Expression sample includes other non-micro- expressions of smile to the interference effect of model training, can be by repeatedly verifying the micro- table of non-smile
Feelings are rejected.
Step S320: being based on the micro- expression sample of the smile, and it is special to extract micro- expression according to the multiple default dimension
Data are levied, to obtain micro- expressive features data sample.
In this example embodiment, compared to the characteristic for not distinguishing dimension and directly extracting micro- expression, from multiple pre-
If extracting micro- expressive features data in dimension respectively more comprehensively, it is not easy missing feature point, obtained micro- expressive features data have more
Reliability.Further, micro- expression of face is often complicated, and only by human eye observation, a few micro- expressive features goes to sentence
The sincerity degree of disconnected smile, it is difficult to which comprehensive various micro- expressive features data, judging result is insecure；And using machine learning
When method, due to having the ability for handling a large amount of micro- expressive features data, the micro- expression for judging smile's sincerity degree can be will be unable to
A large amount of micro- expressive features data be input in machine learning model, as a part of training data, be conducive to smile's sincerity
The accurate detection of degree.
Step S330: the corresponding smile's sincerity degree of the micro- expression of smile in the micro- expression sample of the smile is obtained, according to institute
It states micro- expressive features data sample and smile's sincerity degree obtains the training data.
In this example embodiment, by scoring the micro- expression of smile in the micro- expression sample of smile, to obtain those
The corresponding smile's sincerity degree of the micro- expression of smile.Firstly, obtaining the corresponding micro- table with multiple default dimensions of the micro- expression of smile
Feelings characteristic；Then, the weighted value for obtaining each default dimension, since each default dimension is calculating micro- expression smile sincerity degree
Shi Suozhan weight has differences, such as compared to ocular, and mouth region better reflects the sincerity degree of smile, therefore eye
Region weight shared during detecting smile's sincerity degree is higher；Finally according to the weighted value of each default dimension and corresponding
Micro- expressive features data obtain the corresponding smile's sincerity degree of the micro- expression of smile in the micro- expression sample of smile.Specifically, smile is micro-
The corresponding smile's sincerity degree of expression can be obtained by following formula:
S=W1×a1+W2×a2+…+Wn×an
Wherein, S indicates the corresponding smile's sincerity degree of the micro- expression of smile, W1, W2... Wn indicates the expressive features of each default dimension
The corresponding score value of data, the score value are obtained by presetting the sum of the expressive features data score value in each expression region that dimension includes,
a1, a2…anIndicate the weighted value of each default dimension.
For example, table 1 shows a tranining database, and it comprises multiple default dimensions of the micro- expression of multiple users
Micro- expressive features data of (ocular, cheek region, lip-region and chin area etc.) and corresponding smile's sincerity degree.
As shown in table 1, the weight for obtaining ocular, cheek region, lip-region and chin area is respectively 1/4,1/8,1/2 and 1/
8；According to the weighted value of each default dimension and the corresponding score value of expressive features data, smile's sincerity degree of user A are as follows: 50 × 1/4+
60 × 1/8+50 × 1/2+40 × 1/8=50；Smile's sincerity degree of user B are as follows: 60 × 1/4+40 × 1/8+40 × 1/2+40 ×
1/8=45.Certainly, in actual conditions, the default dimension that micro- expressive features data are divided is higher than the complexity in table 1, but
According to the weighted value of the default dimension of the micro- expression of smile and corresponding micro- expressive features data, obtain that the micro- expression of smile is corresponding to be laughed at
The process for holding sincerity degree is consistent with this illustrative embodiment, therefore the disclosure repeats no more this.
Table 1
It should be noted that being first respectively pre- before the corresponding score value of expressive features data for obtaining each default dimension
If each expressive parts (such as eye portion, corners of the mouth part and cheek part) established standards value that dimension includes, for each expression
Bonus point processing is done, when the expressive features number of the part when the expressive features data of the part are greater than the standard value of setting in part
When according to the standard value for being less than setting, then deduction processing is done；Finally the sum of the score value that all expressive parts obtain, as with those tables
The corresponding score value of expressive features data of the corresponding default dimension in feelings part.Specifically, such as lip-region, if the setting corners of the mouth is curved
Bent 15 ° are standard value, when the corners of the mouth bending angle of user is 20 °, then do bonus point processing；When the corners of the mouth bending angle of user is
At 10 °, then corresponding deduction processing is done；It is standard value that tooth, which exposes 6, is done at bonus point when the tooth of user exposes greater than 6
Reason, user's tooth expose less than 6, then do deduction processing, etc., the plus-minus for all expressive parts that last lip-region includes
The sum of score value, the as corresponding score value of expressive features data of lip-region.It should be noted that specifically plus-minus score value can be with
It is set according to micro- expressive features of each default dimension and actual needs, the disclosure does not do particular determination to this.
Step S220: using micro- expressive features data sample as input vector, smile's sincerity degree is as output
Vector is input to a machine learning model, is trained to the machine learning model, to generate the mapping model.
In this example embodiment, mapping model can be convolutional neural networks or depth residual error network etc., this field
Technical staff can use corresponding machine learning model according to demand, and the disclosure is not specifically limited in this embodiment.Micro- expression is special
It levies data sample and is input to machine learning model with corresponding smile's sincerity degree, set learning rate, frequency of training, loss function
And after the training parameters such as optimization aim, it can train automatically and obtain mapping model.
In addition, above-mentioned mapping model is also possible to contain between a large amount of micro- expressive features data and smile's sincerity degree
The mapping table of corresponding relationship can also obtain corresponding smile's sincerity degree by way of searching in corresponding relationship mapping table.
Step S140: by the mapping model, micro- expressive features described in extraction with multiple default dimensions are utilized
Data obtain smile's sincerity degree of user.
In this example embodiment, Fig. 4 is shown based on mapping model, using extraction with multiple default dimensions
Micro- expressive features data obtain the flow chart of user's smile's sincerity degree.As shown in figure 4, being by convolutional neural networks of mapping model
Example is illustrated the smile's sincerity degree for obtaining user by mapping model.Specific step is as follows:
Step S410: carrying out feature extraction to the micro- expression of collected user, to obtain the table with multiple default dimensions
Feelings characteristic.In this example embodiment, after collecting micro- expression of user, feature extraction is carried out to it first to obtain
Take micro- expressive features number with multiple default dimensions (such as ocular, cheek region and lip-region) corresponding with micro- expression
According to.Wherein, feature extraction can be optical flow method, filtering extraction method etc..
Micro- expressive features data with multiple default dimensions of extraction are input to mapping model, with true by step S420
Fixed smile's sincerity degree corresponding with micro- expressive features data.It is micro- by being extracted according to step S410 in this example embodiment
Expressive features data are input to convolutional neural networks, convolutional neural networks according to micro- expressive features data and corresponding weight,
It scores micro- expression of user, to obtain smile's sincerity degree corresponding with the micro- expression of the user.
In this example embodiment, on the basis of acquired trained mapping model, by micro- expression of user
Characteristic is input to mapping model, can be obtained the score value of micro- expression corresponding with micro- expressive features data of input, that is, laughs at
Hold sincerity degree.Based on this, the efficiency of user's smile's sincerity degree detection is not only increased；Simultaneously as mapping model is based on more
Item includes the training data training of the micro- expressive features data sample and corresponding smile's sincerity degree of a large amount of micro- expressive features data
It obtains, the result of output has reliability, improves the accuracy of user's smile's sincerity degree detection, also avoids due to artificial feelings
The interference effect that the influence of thread generates the detection of user's smile's sincerity degree.
In addition, additionally providing a kind of smile's sincerity degree detection device in this example embodiment.Referring to Figure 5, should
Smile's sincerity degree detection device 500 may include: expression acquisition module 510, characteristic extracting module 520, mapping acquisition module 530
And smile's sincerity degree obtains module 540.Specifically,
Expression acquisition module 510, for acquiring micro- expression of user；
Characteristic extracting module 520 has multiple default dimensions for carrying out feature extraction to micro- expression to obtain
Micro- expressive features data；
Mapping obtains module 530, and for obtaining mapping model, the mapping model is based on micro- expressive features data sample
It is formed with the training of corresponding smile's sincerity degree；
Smile's sincerity degree obtains module 540, for being preset with multiple using described in extraction by the mapping model
Micro- expressive features data of dimension obtain smile's sincerity degree of the user.
It is collapsed due to each functional module of smile's sincerity degree detection device of disclosure embodiment and above-mentioned positioning
It is identical in the invention embodiment of method, therefore details are not described herein.
In addition, in an exemplary embodiment of the disclosure, additionally provides a kind of computer that can be realized the above method and deposit
Storage media.It is stored thereon with the program product that can be realized this specification above method.In some possible embodiments, this public affairs
The various aspects opened are also implemented as a kind of form of program product comprising program code, when described program product is at end
When running in end equipment, said program code is for making the terminal device execute above-mentioned " illustrative methods " part of this specification
Described in exemplary embodiments various according to the disclosure the step of.
Refering to what is shown in Fig. 6, the program product 600 according to an embodiment of the present disclosure for realizing the above method is described,
It can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device, such as
It is run on PC.However, the program product of the disclosure is without being limited thereto, in this document, readable storage medium storing program for executing, which can be, appoints
What include or the tangible medium of storage program that the program can be commanded execution system, device or device use or and its
It is used in combination.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with any combination of one or more programming languages come write for execute the disclosure operation program
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, in an exemplary embodiment of the disclosure, additionally providing a kind of electronic equipment that can be realized the above method.
Person of ordinary skill in the field is it is understood that various aspects of the disclosure can be implemented as system, method or program product.
Therefore, various aspects of the disclosure can be with specific implementation is as follows, it may be assumed that complete hardware embodiment, complete software are real
The embodiment combined in terms of applying example (including firmware, microcode etc.) or hardware and software, may be collectively referred to as " circuit ", " mould here
Block " or " system ".
The electronic equipment 700 of this embodiment according to the disclosure is described referring to Fig. 7.The electronics that Fig. 7 is shown is set
Standby 700 be only an example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in fig. 7, electronic equipment 700 is showed in the form of universal computing device.The component of electronic equipment 700 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 710, at least one above-mentioned storage unit 720, the different system components of connection
The bus 730 of (including storage unit 720 and processing unit 710), display unit 740.
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 710
Row, so that various according to the disclosure described in the execution of the processing unit 710 above-mentioned " illustrative methods " part of this specification
The step of exemplary embodiment.
Storage unit 720 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 7201 and/or cache memory unit 7202, it can further include read-only memory unit (ROM) 7203.
Storage unit 720 can also include program/utility with one group of (at least one) program module 7205
7204, such program module 7205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 730 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 700 can also be with one or more external equipments 800 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 700 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 700 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 750.Also, electronic equipment 700 can be with
By network adapter 760 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 760 is communicated by bus 730 with other modules of electronic equipment 700.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 700, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
By the description of above embodiment, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can also be realized in such a way that software is in conjunction with necessary hardware by software realization.Therefore, implemented according to the disclosure
The technical solution of example can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are so that a calculating equipment (can
To be personal computer, server, terminal installation or network equipment etc.) it executes according to the method for the embodiment of the present disclosure.
In addition, above-mentioned attached drawing is only the schematic theory of the processing according to included by the method for disclosure exemplary embodiment
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.The disclosure is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the attached claims.
Claims (10)
1. a kind of smile's sincerity degree detection method characterized by comprising
Acquire micro- expression of user；
Feature extraction is carried out to micro- expression, to obtain micro- expressive features data with multiple default dimensions；
Mapping model is obtained, the mapping model is based on micro- expressive features data sample and corresponding smile's sincerity degree training shape
At；
By the mapping model, the use is obtained using micro- expressive features data described in extraction with multiple default dimensions
Smile's sincerity degree at family.
2. smile's sincerity degree detection method according to claim 1, which is characterized in that the method also includes:
A plurality of training data is obtained, the training data includes micro- expressive features data sample and micro- expressive features data
The corresponding smile's sincerity degree of sample；
Using micro- expressive features data sample as input vector, smile's sincerity degree is input to one as output vector
Machine learning model is trained the machine learning model, to generate the mapping model.
3. smile's sincerity degree detection method according to claim 2, which is characterized in that described to obtain a plurality of training data packet
It includes:
According to the expressive features information of predeterminable area, the micro- expression of smile is screened, from a variety of micro- expressions to obtain the micro- expression of smile
Sample；
Based on the micro- expression sample of the smile, micro- expressive features data are extracted according to the multiple default dimension, to obtain
Micro- expressive features data sample；
The corresponding smile's sincerity degree of the micro- expression of smile in the micro- expression sample of the smile is obtained, according to micro- expressive features number
The training data is obtained according to sample and smile's sincerity degree.
4. smile's sincerity degree detection method according to claim 3, which is characterized in that the expressive features of the predeterminable area
Information includes one of eyes have been narrowed, palpebra inferior protrusion, orbicular muscle of eye are shunk, the corners of the mouth tilts, cheek is raised or chin is unfolded
Or it is a variety of；
The expressive features information according to predeterminable area screens the micro- expression of smile from a variety of micro- expressions, micro- to obtain smile
Expression sample, comprising:
Micro- expression of all expressive features information with the predeterminable area is screened, from a variety of micro- expressions to obtain
State the micro- expression sample of smile.
5. smile's sincerity degree detection method according to claim 3, which is characterized in that described to obtain the micro- expression of smile
The corresponding smile's sincerity degree of the micro- expression of smile in sample, comprising:
Obtain the corresponding micro- expressive features number with multiple default dimensions of the micro- expression of smile in the micro- expression sample of the smile
According to；
Obtain the weighted value of each default dimension；
According to the weighted value of each default dimension and corresponding micro- expressive features data, the micro- expression sample of the smile is obtained
In the corresponding smile's sincerity degree of the micro- expression of smile.
6. smile's sincerity degree detection method according to claim 1, which is characterized in that it is described by the mapping model,
Smile's sincerity degree of the user is obtained using micro- expressive features data described in extraction with multiple default dimensions, comprising:
Micro- expressive features data described in extraction with multiple default dimensions are input to the mapping model, with determining and institute
State the corresponding smile's sincerity degree of micro- expressive features data.
7. smile's sincerity degree detection method according to any one of claims 1 to 6, which is characterized in that the default dimension
Including ocular, cheek region and lip-region.
8. a kind of smile's sincerity degree detection device, which is characterized in that described device includes:
Expression acquisition module, for acquiring micro- expression of user；
Characteristic extracting module, for carrying out feature extraction to micro- expression, to obtain micro- expression with multiple default dimensions
Characteristic；
Mapping obtains module, and for obtaining mapping model, the mapping model is based on micro- expressive features data sample and correspondence
The training of smile sincerity degree formed；
Smile's sincerity degree obtains module, for by the mapping model, using described in extraction with multiple default dimensions
Micro- expressive features data obtain smile's sincerity degree of the user.
9. a kind of storage medium, is stored thereon with computer program, the computer program realizes basis when being executed by processor
Smile's sincerity degree detection method described in any one of claims 1 to 7.
10. a kind of electronic equipment characterized by comprising
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to come described in any one of perform claim requirement 1 to 7 via the execution executable instruction
Smile's sincerity degree detection method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910003267.9A CN109858379A (en) | 2019-01-03 | 2019-01-03 | Smile's sincerity degree detection method, device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910003267.9A CN109858379A (en) | 2019-01-03 | 2019-01-03 | Smile's sincerity degree detection method, device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109858379A true CN109858379A (en) | 2019-06-07 |
Family
ID=66893839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910003267.9A Pending CN109858379A (en) | 2019-01-03 | 2019-01-03 | Smile's sincerity degree detection method, device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858379A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110895685A (en) * | 2019-11-25 | 2020-03-20 | 创新奇智(上海)科技有限公司 | Smile service quality evaluation system and evaluation method based on deep learning |
| WO2021036664A1 (en) * | 2019-08-26 | 2021-03-04 | 深圳壹账通智能科技有限公司 | Method and apparatus for identifying customer satisfaction on basis of micro-expressions, terminal and medium |
| CN114170585A (en) * | 2021-11-16 | 2022-03-11 | 广西中科曙光云计算有限公司 | Dangerous driving behavior recognition method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886304A (en) * | 2014-04-03 | 2014-06-25 | 北京大学深圳研究生院 | True smile and fake smile identifying method based on space-time local descriptor |
| CN104766041A (en) * | 2014-01-07 | 2015-07-08 | 腾讯科技（深圳）有限公司 | Image recognition method, device and system |
| CN107480622A (en) * | 2017-08-07 | 2017-12-15 | 深圳市科迈爱康科技有限公司 | Micro- expression recognition method, device and storage medium |
| CN107798318A (en) * | 2017-12-05 | 2018-03-13 | 四川文理学院 | The method and its device of a kind of happy micro- expression of robot identification face |
| CN107977630A (en) * | 2017-12-04 | 2018-05-01 | 杨世鹏 | A kind of smile's kind judging method based on character face's Expression Recognition |
| CN109101956A (en) * | 2018-09-21 | 2018-12-28 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling image |
-
2019
- 2019-01-03 CN CN201910003267.9A patent/CN109858379A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766041A (en) * | 2014-01-07 | 2015-07-08 | 腾讯科技（深圳）有限公司 | Image recognition method, device and system |
| CN103886304A (en) * | 2014-04-03 | 2014-06-25 | 北京大学深圳研究生院 | True smile and fake smile identifying method based on space-time local descriptor |
| CN107480622A (en) * | 2017-08-07 | 2017-12-15 | 深圳市科迈爱康科技有限公司 | Micro- expression recognition method, device and storage medium |
| CN107977630A (en) * | 2017-12-04 | 2018-05-01 | 杨世鹏 | A kind of smile's kind judging method based on character face's Expression Recognition |
| CN107798318A (en) * | 2017-12-05 | 2018-03-13 | 四川文理学院 | The method and its device of a kind of happy micro- expression of robot identification face |
| CN109101956A (en) * | 2018-09-21 | 2018-12-28 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling image |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021036664A1 (en) * | 2019-08-26 | 2021-03-04 | 深圳壹账通智能科技有限公司 | Method and apparatus for identifying customer satisfaction on basis of micro-expressions, terminal and medium |
| CN110895685A (en) * | 2019-11-25 | 2020-03-20 | 创新奇智(上海)科技有限公司 | Smile service quality evaluation system and evaluation method based on deep learning |
| CN114170585A (en) * | 2021-11-16 | 2022-03-11 | 广西中科曙光云计算有限公司 | Dangerous driving behavior recognition method and device, electronic equipment and storage medium |
| CN114170585B (en) * | 2021-11-16 | 2023-03-24 | 广西中科曙光云计算有限公司 | Dangerous driving behavior recognition method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10303982B2 (en) | Systems and methods for machine learning enhanced by human measurements | |
| CN109359548B (en) | Multi-face recognition monitoring method and device, electronic equipment and storage medium | |
| EP3885965B1 (en) | Image recognition method based on micro facial expressions, apparatus and related device | |
| CN112990054B (en) | Compact linguistics-free facial expression embedding and novel triple training scheme | |
| US20180268458A1 (en) | Automated recommendation and virtualization systems and methods for e-commerce | |
| CN107545241A (en) | Neural network model is trained and biopsy method, device and storage medium | |
| JP6760318B2 (en) | Face image identification system, classifier generator, identification device, image identification system, and identification system | |
| US20230087657A1 (en) | Assessing face image quality for application of facial recognition | |
| CN111597884A (en) | Facial action unit identification method and device, electronic equipment and storage medium | |
| CN111310705A (en) | Image recognition method and device, computer equipment and storage medium | |
| CN111339990A (en) | Face recognition system and method based on dynamic update of face features | |
| CN109858379A (en) | Smile's sincerity degree detection method, device, storage medium and electronic equipment | |
| CN110728319B (en) | Image generation method and device and computer storage medium | |
| CN109034133A (en) | A kind of face identification method and device | |
| CN112818227B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| Boncolmo et al. | Gender Identification Using Keras Model Through Detection of Face | |
| CN112270747A (en) | Face recognition method and device and electronic equipment | |
| CN117095436A (en) | Intelligent management system and method for enterprise employee information | |
| CN110675312A (en) | Image data processing method, image data processing device, computer equipment and storage medium | |
| Czajka | Is that eye dead or alive? Detecting new iris biometrics attacks | |
| Emeršič et al. | The unconstrained ear recognition challenge 2019-arxiv version with appendix | |
| CN111428670B (en) | Face detection method, face detection device, storage medium and equipment | |
| CN114550249A (en) | Face image generation method and device, computer readable medium and electronic equipment | |
| CN114469139A (en) | Electroencephalogram signal recognition model training method, electroencephalogram signal recognition device and medium | |
| CN114005156A (en) | Face replacement method, face replacement system, terminal equipment and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information |
Address after: 201, room 518000, building A, No. 1, front Bay Road, Qianhai Shenzhen Guangdong Shenzhen Hong Kong cooperation zone (Qianhai business secretary) Applicant after: Shenzhen one ledger Intelligent Technology Co., Ltd. Address before: 518000 Guangdong city of Shenzhen province Qianhai Shenzhen Hong Kong cooperation zone before Bay Road No. 1 building 201 room A Applicant before: Shenzhen one ledger Intelligent Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |