CN109190495A - Gender identification method, device and electronic equipment - Google Patents
Gender identification method, device and electronic equipment Download PDFInfo
- Publication number
- CN109190495A CN109190495A CN201810900838.4A CN201810900838A CN109190495A CN 109190495 A CN109190495 A CN 109190495A CN 201810900838 A CN201810900838 A CN 201810900838A CN 109190495 A CN109190495 A CN 109190495A
- Authority
- CN
- China
- Prior art keywords
- identification
- gender
- identified
- ratio
- recognition
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
Abstract
This application involves a kind of gender identification method, device and electronic equipments.According to an exemplary embodiment, the property method for distinguishing of object is identified can include: the first identification is carried out by gender of the recognition of face to object;And it is unsuccessful in response to first identification, the second identification is carried out come the gender to object by thermal imaging, wherein first identification and second identification each include: obtaining the multiple image of the object;Identify the gender of the object, about the multiple image to obtain multiple recognition results;And if the ratio of one of the multiple recognition result sex determination is greater than or equal to first threshold, identify success, otherwise recognition failures.
Description
Technical field
Present invention relates generally to field of image recognition, more particularly, to a kind of gender identification method, device and electronics
Equipment.
Background technique
In recent years, artificial intelligence is gradually put into business application in many aspects, to promote the further of business
Development.For example, monitor the volume of the flow of passengers, identification client characteristics in the environment of market and determine customer priorities etc..Gender is client
One important feature, therefore in many situations, it is desirable to be able to the gender of client is identified, to carry out for example targeted business
Promote etc..In general, client gender can be readily determined by recognition of face, however in some market environment, by
Reasons, the cameras such as, movement speed big in flow of the people is fast and moving direction is random are often difficult to be accurately captured whole disengaging
The comprehensive facial information of object, therefore cannot accurately differentiate the gender of a large amount of clients.
A kind of existing technical solution is to collect the video for largely covering various scenes, then by manually come to disengaging pair
The gender of elephant is judged.Later, the data result that can be provided with face recognition algorithms compares, to find algorithm
Defect improves recognition success rate and accuracy to improve algorithm.However, this prior art relies basically on IPC (net
Network camera) algorithm promotion, be limited by the development of face recognition technology, rely solely on face recognition algorithms in a short time still
It is difficult to fundamentally improve gender recognition accuracy.
Summary of the invention
In view of above-mentioned prior art situation, the application proposes a kind of gender identifying schemes, passes through the technical method of auxiliary,
Further gender identification is carried out to the object of recognition of face failure, is identified by supplement, whole gender recognition accuracy is improved.
On the other hand, by carrying out judgement of stability to recognition result, it can be further improved the accuracy of recognition result.
According to an exemplary embodiment, a kind of property method for distinguishing for identifying object is provided, comprising: by recognition of face to right
The gender of elephant carries out the first identification;And in response to it is described first identification it is unsuccessful, by thermal imaging come the gender to object into
Row second identifies, wherein first identification and second identification each include: obtaining the multiple image of the object;
Identify the gender of the object, about the multiple image to obtain multiple recognition results;And if the multiple identification
One of as a result the ratio of sex determination is greater than or equal to first threshold, then identifies success, otherwise recognition failures.
In some instances, carrying out the second identification by thermal imaging come the gender to object includes: to be obtained by thermal imaging
The graphic images of the object;And face, body contour or features based on object described in the graphic images
Position identifies the gender of the object.
In some instances, the method also includes: in response to it is described second identification it is unsuccessful, by wearing clothes come to described
The gender of object carries out third identification.
It in some instances, include: by the object come the gender progress third identification to the object by wearing clothes
Color, style or the classification of clothing identify the gender of the object.
In some instances, if identifying that the gender of the object includes: by the color of the clothing of the object
The ratio that one predetermined clothing color accounts for the clothing gross area of the object in the picture is greater than or equal to second threshold, then is identified as
First gender, and if the ratio that the second predetermined clothing color accounts for the clothing gross area of the object in the picture is greater than or waits
In second threshold, then second sex is identified as.
In some instances, if identifying that the gender of the object includes: right by the color of the clothing of the object
The sum of the clothing color of elephant is greater than or equal to third threshold value, then is identified as women, otherwise, is identified as male.
In some instances, the method also includes: in response to the third identify it is unsuccessful, count unsuccessful identification
The quantity of object;And reach the 4th threshold value in response to the quantity of the object of the unsuccessful identification, introduce the first reference ratio
Men and women's quantity in object to determine the unsuccessful identification.
In some instances, first reference ratio is the sex ratio of the registered members in the place identified.
In some instances, the method also includes: count successfully identification and by introduce the first reference ratio know
The sex ratio of other object obtains whole sex ratio;And by the whole sex ratio compared with the second reference ratio
Compared with if difference less than the 5th threshold value, exports successfully identification and by introducing the object that identifies of the first reference ratio
Data abandon the data by introducing the object that the first reference ratio identifies if difference is equal to or more than the 5th threshold value,
And export the data of the successfully object of identification.
In some instances, the statistical data before second reference ratio is under similar scene.
According to another exemplary embodiment, a kind of device of gender identifying object is provided, comprising: face recognition module,
It is configured to carry out the first identification by recognition of face come the gender to object;And graphic images identification module, it is configured to ring
First identification described in Ying Yu is unsuccessful, carries out the second identification by graphic images come the gender to the object, wherein described
First identification and second identification each include: obtaining the multiple image of the object;Know about the multiple image
The gender of the not described object, to obtain multiple recognition results;And if one of the multiple recognition result sex determination
Ratio be greater than or equal to first threshold, then identify success, otherwise, then recognition failures.
In some instances, described device further include: clothing identification module, be configured in response to it is described second identification not at
Function carries out third identification by wearing clothes come the gender to the object.
In some instances, described device further include: unsuccessful object handles module is configured to identify not the third
The object that success identifies is handled, to export final recognition result.
According to another exemplary embodiment, a kind of electronic equipment is provided, comprising: camera, for obtaining the image of object;
Thermal imaging module, for obtaining the graphic images of the object;And processor, the computer being configured in run memory
Program instruction is to execute the above method.
According to another exemplary embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with
Instruction, the computer program instructions make the processor execute the above method when being run by processor.
By the gender identifying schemes of the application, with the technical method of auxiliary, to the object of recognition of face failure carry out into
The gender of one step identifies, is identified by supplement, improves the accuracy rate of whole gender identification.
The above and other feature and advantage of the application will become aobvious and easy from the following description to exemplary embodiment
See.
Detailed description of the invention
The exemplary embodiment of the application is described in more detail in conjunction with the accompanying drawings, the application above-mentioned and its
His purpose, feature and advantage will be apparent.Attached drawing is used to provide to further understand the embodiment of the present application, and structure
At part of specification, it is used to explain the application together with the embodiment of the present application, does not constitute the limitation to the application.Attached
In figure, identical reference label typically represents same parts or step.
Fig. 1 illustrates the flow charts according to the synthesis gender identification method of one exemplary embodiment of the application.
Fig. 2 illustrates the flow chart of the particular sex recognition methods according to one exemplary embodiment of the application.
Fig. 3 illustrates the functional block diagram of the gender identification device according to one exemplary embodiment of the application.
Fig. 4 illustrates the structural block diagram of the electronic equipment according to one exemplary embodiment of the application.
Specific embodiment
In the following, the exemplary embodiment that the application will be described in detail by referring to the drawings.Obviously, described embodiment is only
It is a part of the embodiment of the application, rather than the whole embodiments of the application, it should be appreciated that the application is not shown by described herein
The limitation of example embodiment.
As described above, there are the following problems for existing gender identifying schemes:
1. place one's entire reliance upon face recognition technology, but face recognition algorithms are difficult to the accurate of significant gender identification in a short time
Rate;
2. collecting the video for largely covering various scenes, is judged with the gender manually to disengaging object, automate journey
Spend low, person works' amount is big, can not get rid of the associated disadvantage of artificial treatment.
In view of the above-mentioned drawbacks in the prior art, the basic conception of the application is to increase auxiliary sex recognition methods, in people
Face recognizer identifies in the uncertain situation of gender, the use of sex character of the thermal imaging camera to object includes face, body
Body profile or characteristic portion carry out gender identification.Thermal imaging camera is main householder method, if this method cannot still identify
The gender of object, then use secondary householder method: the apparel characteristic to object includes that color, style, type etc. identify, from
And determine its gender.The object that can not all judge the above method gender, when the quantity of this class object is accumulated to a certain extent,
Registered members' data in place is applied where gender is identified estimates in these numbers.In this way in layers
It filters out and determines unsuccessful object, these information are determined again with the method for directly carrying out recognition of face is different from, with
Recognition result is improved, the accuracy rate of whole gender identification is thus improved.
It, can be with it should be noted that the above-mentioned basic conception of the application can be applied not only in commercial environment scene
Applied in other systems application.For example, the application is equally applicable to the identification of the gender in community environment.
After describing the basic principle of the application, carry out the various non-limits for specifically introducing the application below with reference to the accompanying drawings
Property embodiment processed.
Fig. 1 illustrates the flow charts according to the synthesis gender identification method of one exemplary embodiment of the application.Such as Fig. 1 institute
Show, identify that the property method for distinguishing 100 of object may begin at step S101, recognition of face (first is carried out to the video of object to be identified
Identification), this can capture facial image by camera, and be carried out using existing face recognition algorithms.In general,
It is correct to identify that the other success rate of objectivity is higher if facial image can be captured completely.If can succeed in step S101
The gender of identification object exports the gender identified then in step S102.Here, the data of step S102 output may include working as
The gender information of preceding identification object can also include the sex ratio information etc. of identified object.If step S101 can not
It identifies the gender of object, such as fails to obtain the full facial information of object, although or having obtained facial information recognition of face
Algorithm can not determine gender, then can carry out gender identification by the graphic images of object to be identified to step S111
(the second identification).The graphic images of object to be identified can be obtained by thermal imaging camera, and can based on heat at
Face, body contour or characteristic portion as the object in image etc. identify the gender of object.For example, due to light,
Common camera may not be able to obtain the full facial image of object in some cases, and thermal imaging camera can not be by can
Light-exposed influence obtains the graphic images of subjects face.Alternatively, thermal imaging camera can directly obtain the body wheel of object
Wide or characteristic portion information, these information can be used for being readily determined the gender of object.It, can be in a particular example
Object-based secondary sex characters such as breast, Adam's apple etc. determines its gender.If successfully identifying the property of object in step S111
Not, then recognition result is exported in step S112.If can not identify the gender of object in step S111, step can be proceeded to
Rapid S121.
It should be understood that when carrying out above-mentioned gender identification step, it may be even during same target is tracked and identified
It is continuous to have taken its multiple image, multiple identification has been carried out, and the result repeatedly identified may be not necessarily identical.At this point, knowing
The stability of other result is to identify the important indicator of accuracy, and stability is higher, then accuracy is higher.Therefore, in the present invention one
In embodiment, using the stability of recognition result as judging whether it identifies successful major criterion.Fig. 2 is illustrated according to this Shen
Please an exemplary embodiment by recognition of face or thermal imaging identification carry out gender identification process flow chart.With reference to figure
2, above-mentioned recognition of face or thermal imaging identification may include following procedure: in step S210, obtain several of object to be identified
Image, such as video carry out gender identification to object to be identified based on the multiple image in video then in step S220, with
Obtain multiple recognition results.In step S230, sex determination's ratio in these recognition results is compared with first threshold, such as
A possibility that fruit sex determination's ratio is greater than or equal to the first threshold, illustrates that recognition result is very stable, successfully identifies is high;Phase
Instead, a possibility that if sex determination's ratio is less than the first threshold, illustrating that recognition result is very unstable, successfully identifying is low.Cause
This proceeds to step S240, it is believed that identify successfully when high a possibility that successfully identifying;Otherwise, then step S250 is proceeded to,
Think recognition failures.Here first threshold can be arranged based on experience value, such as 66.7%, 75%.
It, can be according to the clothing of object in video image come the property to the object in step S121 with continued reference to Fig. 1
(third identification) is not identified.Here, clothing not only includes jacket, the trousers etc. of dress, can also include the ornaments worn
And necktie etc..The gender of object can be easily and directly determined by some ornaments.
In one example, the gender of object can be identified by the color and/or style of the clothing of object.For example,
If identifying that object gender may include: that (such as women is often worn bright-coloured the first predetermined clothing color by the color of clothing
Color) account for the ratio for wearing the gross area clothes of object in the picture more than or equal to second threshold, then it is identified as the first gender (such as female
Property);If the second predetermined clothing color (the dark-coloured system that such as male often wears) accounts for the ratio of the clothing gross area of object in the picture
Rate is greater than or equal to second threshold, then is identified as second sex (such as male).Equally, second threshold can also be set based on experience value
It sets.
It in one example, can also be according to clothing color sum, clothing if can not identify gender by wearing color clothes
Style etc. identify gender.For example, if clothing color sum is more (be greater than or equal to third threshold values, such as 3), then prejudgementing character
Not Wei female, otherwise Sex estimation be male.
It is appreciated that (clothing is known for above-mentioned first identification (recognition of face), the second identification (thermal imaging identification) and third identification
It not may be by machine learning model) to realize.For example, being trained first with training data to neural network, then
Identification is executed using trained model.
In step S121, if third identifies successfully, in step S122, recognition result is exported.If step
S121 can not identify the gender of object, then turn to step S131, count to the quantity for the object identified that can not succeed above
It is cumulative;Then in step S132, judge whether cumulative quantity reaches the 4th threshold value.If reaching the 4th threshold value, in step
Rapid S133, men and women's quantity in object that the first reference ratio can be introduced into determine the unsuccessful identification.Here it introduces
First reference ratio can be the sex ratio for for example carrying out the registered members in place of gender identification.That is, to above
It, can be using the place identified when the quantity for the object that can not successfully identify is accumulated to the 4th threshold value (such as 100 etc.)
The sex ratio information (such as male to female ratio is a:b) of registered members, then estimating has 100* (a/ (a+b)) position man in this 100 people,
There is 100* (b/ (a+b)) Mrs position.
Then, in step s 141, statistics before by first to third identify successfully identify gender data and
The gender data estimated in step S131 obtains total whole sex ratio.In step S142, by resulting whole sex ratio
Rate is compared with the second reference ratio.Here, the second reference ratio can for before for example under similar scene (such as the last week
Same time) obtain statistical data.If the difference between whole sex ratio and the second reference ratio is less than the 5th threshold
Be worth (such as 20% or other values), then in step S150, export whole sex ratio, i.e., it is successful identifying and pass through introducing
First reference ratio and the conceptual data of object identified.If difference is equal to or more than the 5th threshold value in step S142,
Think to differ greatly caused by introducing the result that the first reference ratio obtains, then can abandon in step S160 and pass through introducing
First reference ratio and the data of object identified, and only export the data of the object successfully identified.
In each step described above, some threshold values, such as the first to the 5th threshold value have been used.It is appreciated that
The numerical value of above-mentioned each threshold value can be determined rule of thumb, such as can be adjusted in the training process of neural network
It is whole.
By the above-mentioned gender identification method according to one exemplary embodiment of the application, gender is identified into unsuccessful object
It filters out, carries out further gender identification using the other supplementary means for directly carrying out recognition of face are different from, it can be perfect
Recognition result improves gender recognition accuracy, so as to be supplied to the more perfect and accurate customer's gender data of trade company.
Fig. 3 illustrates the functional block diagram of the gender identification device 200 according to one exemplary embodiment of the application.Such as Fig. 3 institute
Show, gender identification device 200 may include face recognition module 210, thermal imaging identification module 220 and clothing identification module 230.Know
Other module 210-230 can be identified respectively according to face identification method described above, graphic images recognition methods and clothing
Method identifies the gender of object, no longer repeats one by one here.In addition, gender identification device 200 can also include unidentified right
As processing module 240, the quantity of the object identified not successfully can be counted, and when the quantity reaches four threshold values, then
Aforementioned first reference ratio is introduced to carry out Sex Discrimination to the object identified not successfully, to export final recognition result.It introduces
Detailed description has been carried out above for the discriminating step that first reference ratio is carried out, and description is not repeated herein.
The concrete function of each unit and module in above-mentioned gender identification device 200 and operation have been described above with reference to figure
It is discussed in detail in the gender identification method of 1 to Fig. 2 description, therefore is only briefly explained here, and it is detailed that its repetition is omitted
Thin description.It may be implemented in image processing electronics according to the gender identification device 200 of the embodiment of the present application, such as can be with
It is integrated into image processing electronics as a software module and/or hardware module.
Fig. 4 shows the structural block diagram of the example electronic device 300 of achievable gender identification device 200.As shown in figure 4,
Electronic equipment 300 may include processor 310, camera 320, memory 330 and thermal imaging module 340, they pass through bus
370 are connected to each other.
Processor 310 can be central processing unit (CPU) or have data-handling capacity and/or instruction execution capability
Other forms processing unit, and can control the other assemblies in electronic equipment to execute desired function.
The normal image of the available object to be identified of camera 320, i.e. visible images.Thermal imaging module 340 then may be used
To obtain the graphic images of object to be identified, such as infrared image.
Memory 330 may include various forms of computer readable storage mediums, such as volatile memory and/or non-
Volatile memory.Volatile memory for example may include random access memory (RAM) and/or cache memory
(cache) etc..Nonvolatile memory for example may include read-only memory (ROM), hard disk, flash memory etc..It can in memory 330
To be stored with computer program instructions, processor 310 can run these computer program instructions, to realize the application above
Each embodiment gender identification method and/or other desired functions.
In some instances, electronic equipment 300 may also include input unit 350 and output unit 360.Input unit 350
With output unit 360 can be performed it is various output and input function, such as input unit 350 is subjected to the registered members of business place
Data, output unit 350 can export gender recognition result etc..In one embodiment, input unit 350 and output are single
Member 360 can integrate in individual devices, such as touch-screen display.Processor 310 passes through bus 370 and modules or unit
Connection, to control their operation.
Other than the above method and equipment, embodiments herein can also be computer program product comprising meter
Calculation machine program instruction, it is above-described according to this that the computer program instructions execute processor
Apply for the step in the gender identification method of embodiment.
The computer program product can be write with any combination of one or more programming languages for holding
The program code of row the embodiment of the present application operation, programming language includes object oriented program language, such as Java,
C++ etc. further includes conventional procedural programming language, such as " C " language or similar programming language.Program code
It can fully execute on the user computing device, partly execute, held as an independent software package on a user device
Part executes on a remote computing or completely in remote computing device or service on the user computing device for row, part
It is executed on device.
In addition, embodiments herein can also be computer readable storage medium, it is stored thereon with computer program and refers to
It enables, it is above-described according to the embodiment of the present application that the computer program instructions execute processor
Gender identification method in step.
The computer readable storage medium can be using any combination of one or more readable mediums.Readable medium can
To be readable signal medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can include but is not limited to electricity, magnetic, light, electricity
Magnetic, the system of infrared ray or semiconductor, device or device, or any above combination.Readable storage medium storing program for executing it is more specific
Example (non exhaustive list) includes: the electrical connection with one or more conducting wires, portable disc, hard disk, random access memory
Device (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.
The basic principle of the application is described in conjunction with specific embodiments above, however, it is desirable to, it is noted that in this application
The advantages of referring to, advantage, effect etc. are only exemplary rather than limitation, must not believe that these advantages, advantage, effect etc. are the application
Each embodiment is prerequisite.In addition, detail disclosed above is merely to exemplary effect and the work being easy to understand
With, rather than limit, it is that must be realized using above-mentioned concrete details that above-mentioned details, which is not intended to limit the application,.
Device involved in the application, device, equipment, system block diagram only as illustrative example and be not intended to
It is required that or hint must be attached in such a way that box illustrates, arrange, configure.As those skilled in the art will appreciate that
, it can be connected by any way, arrange, configure these devices, device, equipment, system.Such as "include", "comprise", " tool
" etc. word be open vocabulary, refer to " including but not limited to ", and can be used interchangeably with it.Vocabulary used herein above
"or" and "and" refer to vocabulary "and/or", and can be used interchangeably with it, unless it is not such that context, which is explicitly indicated,.Here made
Vocabulary " such as " refers to phrase " such as, but not limited to ", and can be used interchangeably with it.
It may also be noted that each component or each step are can to decompose in the device of the application, device and method
And/or reconfigure.These decompose and/or reconfigure the equivalent scheme that should be regarded as the application.
The above description of disclosed aspect is provided so that any person skilled in the art can make or use this
Application.Various modifications in terms of these are readily apparent to those skilled in the art, and are defined herein
General Principle can be applied to other aspect without departing from scope of the present application.Therefore, the application is not intended to be limited to
Aspect shown in this, but according to principle disclosed herein and the consistent widest range of novel feature.
In order to which purpose of illustration and description has been presented for above description.In addition, this description is not intended to the reality of the application
It applies example and is restricted to form disclosed herein.Although already discussed above multiple exemplary aspects and embodiment, this field skill
Its certain modifications, modification, change, addition and sub-portfolio will be recognized in art personnel.
Claims (15)
1. a kind of property method for distinguishing for identifying object, comprising:
The first identification is carried out by gender of the recognition of face to object;And
It is unsuccessful in response to first identification, the second identification is carried out come the gender to object by thermal imaging,
Wherein, first identification and second identification each include:
Obtain the multiple image of the object;
Identify the gender of the object, about the multiple image to obtain multiple recognition results;
And
If the ratio of one of the multiple recognition result sex determination is greater than or equal to first threshold, success is identified,
Otherwise recognition failures.
2. the method for claim 1, wherein carrying out the second identification by thermal imaging come the gender to object includes:
The graphic images of the object are obtained by thermal imaging;And
The property of the object is identified based on the face of object described in the graphic images, body contour or characteristic portion
Not.
3. the method as described in claim 1, further includes:
It is unsuccessful in response to second identification, third identification is carried out by wearing clothes come the gender to the object.
4. method as claimed in claim 3, wherein include: come the gender progress third identification to the object by wearing clothes
The gender of the object is identified by the color of the clothing of the object, style or classification.
5. method as claimed in claim 4, wherein identify the gender of the object by the color of the clothing of the object
Include:
If the ratio that the first predetermined clothing color accounts for the clothing gross area of the object in the picture is greater than or equal to the second threshold
Value, then be identified as the first gender, and
If the ratio that the second predetermined clothing color accounts for the clothing gross area of the object in the picture is greater than or equal to the second threshold
Value, then be identified as second sex.
6. method as claimed in claim 4, wherein identify the gender of the object by the color of the clothing of the object
Include:
If the sum of the clothing color of object is greater than or equal to third threshold value, it is identified as women, otherwise, is identified as male.
7. method as claimed in claim 3, further includes:
It is unsuccessful in response to third identification, count the quantity of the object of unsuccessful identification;And
Reach the 4th threshold value in response to the quantity of the object of the unsuccessful identification, introduce the first reference ratio determine it is described not
Men and women's quantity in object that success identifies.
8. the method for claim 7, wherein first reference ratio is the registered members in the place identified
Sex ratio.
9. the method for claim 7, further includes:
Successfully identification and the sex ratio by introducing the object that the first reference ratio identifies are counted, whole sex ratio is obtained
Rate;And
The whole sex ratio is compared with the second reference ratio, if difference exports and successfully knows less than the 5th threshold value
Not and the data by introducing the object that the first reference ratio identifies are lost if difference is equal to or more than the 5th threshold value
The data by introducing the object that the first reference ratio identifies are abandoned, and export the data of the successfully object of identification.
10. method as claimed in claim 9, wherein second reference ratio be under similar scene before statistical number
According to.
11. a kind of device for the gender for identifying object, comprising:
Face recognition module is configured to carry out the first identification by recognition of face come the gender to object;And
Graphic images identification module, be configured in response to it is described first identification it is unsuccessful, by graphic images come to described
The gender of object carries out the second identification,
Wherein, first identification and second identification each include:
Obtain the multiple image of the object;
Identify the gender of the object, about the multiple image to obtain multiple recognition results;
And
If the ratio of one of the multiple recognition result sex determination is greater than or equal to first threshold, success is identified,
Otherwise, then recognition failures.
12. device as claimed in claim 11, further includes:
Wear clothes identification module, be configured in response to it is described second identification it is unsuccessful, by wear clothes come the gender to the object into
The identification of row third.
13. device as claimed in claim 12, further includes:
Unsuccessful object handles module is configured to identify that the object identified not successfully is handled to the third, to export most
Whole recognition result.
14. a kind of electronic equipment, comprising:
Camera, for obtaining the image of object;
Thermal imaging module, for obtaining the graphic images of the object;And
Processor is configured to the computer program instructions in run memory and is required described in any one of 1-10 with perform claim
Method.
15. a kind of computer readable storage medium is stored thereon with computer program instructions, the computer program instructions are in quilt
Processor makes the processor execute such as method of any of claims 1-10 when running.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810900838.4A CN109190495B (en) | 2018-08-09 | 2018-08-09 | Gender identification method and device and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810900838.4A CN109190495B (en) | 2018-08-09 | 2018-08-09 | Gender identification method and device and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109190495A true CN109190495A (en) | 2019-01-11 |
CN109190495B CN109190495B (en) | 2020-10-30 |
Family
ID=64921152
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810900838.4A Active CN109190495B (en) | 2018-08-09 | 2018-08-09 | Gender identification method and device and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109190495B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110264566A (en) * | 2019-06-03 | 2019-09-20 | 杭州小伊智能科技有限公司 | A kind of device and method of the multihead display based on the replacement of face AI color make-up |
CN112711233A (en) * | 2020-12-25 | 2021-04-27 | 珠海格力电器股份有限公司 | Intelligent household control method and device, processor, storage medium and electronic equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103226774A (en) * | 2013-04-25 | 2013-07-31 | 中国科学技术大学 | Information exchange system |
CN103824053A (en) * | 2014-02-17 | 2014-05-28 | 北京旷视科技有限公司 | Face image gender marking method and face gender detection method |
CN104598888A (en) * | 2015-01-28 | 2015-05-06 | 广州远信网络科技发展有限公司 | Human face gender recognition method |
CN106295591A (en) * | 2016-08-17 | 2017-01-04 | 乐视控股(北京)有限公司 | Gender identification method based on facial image and device |
CN107301389A (en) * | 2017-06-16 | 2017-10-27 | 广东欧珀移动通信有限公司 | Based on face characteristic identification user's property method for distinguishing, device and terminal |
CN108351963A (en) * | 2015-12-08 | 2018-07-31 | 英特尔公司 | Face analysis based on infrared image |
-
2018
- 2018-08-09 CN CN201810900838.4A patent/CN109190495B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103226774A (en) * | 2013-04-25 | 2013-07-31 | 中国科学技术大学 | Information exchange system |
CN103824053A (en) * | 2014-02-17 | 2014-05-28 | 北京旷视科技有限公司 | Face image gender marking method and face gender detection method |
CN104598888A (en) * | 2015-01-28 | 2015-05-06 | 广州远信网络科技发展有限公司 | Human face gender recognition method |
CN108351963A (en) * | 2015-12-08 | 2018-07-31 | 英特尔公司 | Face analysis based on infrared image |
CN106295591A (en) * | 2016-08-17 | 2017-01-04 | 乐视控股(北京)有限公司 | Gender identification method based on facial image and device |
CN107301389A (en) * | 2017-06-16 | 2017-10-27 | 广东欧珀移动通信有限公司 | Based on face characteristic identification user's property method for distinguishing, device and terminal |
Non-Patent Citations (2)
Title |
---|
SATOSHI NISHINO ETC: "Gender Determining Method using Thermography", 《2004 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)》 * |
李昆仑: "基于人脸图像的性别识别", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110264566A (en) * | 2019-06-03 | 2019-09-20 | 杭州小伊智能科技有限公司 | A kind of device and method of the multihead display based on the replacement of face AI color make-up |
CN112711233A (en) * | 2020-12-25 | 2021-04-27 | 珠海格力电器股份有限公司 | Intelligent household control method and device, processor, storage medium and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN109190495B (en) | 2020-10-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10445563B2 (en) | Time-in-store estimation using facial recognition | |
JP4241763B2 (en) | Person recognition apparatus and method | |
US20190332855A1 (en) | Person trend recording device, person trend recording method, and program | |
US20150339516A1 (en) | Collation apparatus and method for the same, and image searching apparatus and method for the same | |
CN108197592B (en) | Information acquisition method and device | |
CN109858552B (en) | Target detection method and device for fine-grained classification | |
CN110569731A (en) | face recognition method and device and electronic equipment | |
CN108491823B (en) | Method and device for generating human eye recognition model | |
CN111563396A (en) | Method and device for online identifying abnormal behavior, electronic equipment and readable storage medium | |
CN111563480A (en) | Conflict behavior detection method and device, computer equipment and storage medium | |
JP6969878B2 (en) | Discriminator learning device and discriminator learning method | |
CN112330383A (en) | Apparatus and method for visual element-based item recommendation | |
US9779285B2 (en) | Face template balancing | |
CN114937232A (en) | Wearing detection method, system and equipment for medical waste treatment personnel protective appliance | |
CN111401343B (en) | Method for identifying attributes of people in image and training method and device for identification model | |
CN108171208A (en) | Information acquisition method and device | |
Benhabiles et al. | Deep learning based detection of hair loss levels from facial images | |
CN108875549A (en) | Image-recognizing method, device, system and computer storage medium | |
CN109190495A (en) | Gender identification method, device and electronic equipment | |
CN112115790A (en) | Face recognition method and device, readable storage medium and electronic equipment | |
CN115565097A (en) | Method and device for detecting compliance of personnel behaviors in transaction scene | |
CN111461104B (en) | Visual recognition method, device, equipment and storage medium | |
CN112906680A (en) | Pedestrian attribute identification method and device and electronic equipment | |
CN109934149B (en) | Method and apparatus for outputting information | |
JP7301432B1 (en) | Causal inference program and causal inference device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |