CN103886284A - Character attribute information identification method and device and electronic device - Google Patents

Character attribute information identification method and device and electronic device Download PDF

Info

Publication number
CN103886284A
CN103886284A CN201410074645.XA CN201410074645A CN103886284A CN 103886284 A CN103886284 A CN 103886284A CN 201410074645 A CN201410074645 A CN 201410074645A CN 103886284 A CN103886284 A CN 103886284A
Authority
CN
China
Prior art keywords
information
personage
attribute information
initial
age
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
Application number
CN201410074645.XA
Other languages
Chinese (zh)
Other versions
CN103886284B (en
Inventor
秦秋平
王琳
陈志军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Xiaomi Technology Co Ltd
Xiaomi Inc
Original Assignee
Xiaomi Inc
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xiaomi Inc filed Critical Xiaomi Inc
Priority to CN201410074645.XA priority Critical patent/CN103886284B/en
Publication of CN103886284A publication Critical patent/CN103886284A/en
Application granted granted Critical
Publication of CN103886284B publication Critical patent/CN103886284B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention discloses a character attribute information identification method and device and an electronic device and belongs to the field of image processing. The method comprises the steps of obtaining an image containing a face, identifying the face, obtaining character identity information and initial character attribute information, searching for historical character attribute information corresponding to the character identity information, and determining the character attribute information which is identified this time according to the initial character attribute information and the historical character attribute information. According to the character attribute information identification method, through identification of the face on the image, the character identity information and the initial character attribute information are obtained; the character attribute information which is identified this time is determined according to the initial character attribute information and the historical character attribute information corresponding to the character identity information; the problem that according to a relevant technology, geometrical features extracted from the face image are influenced greatly by the brightness and the illumination angle in a face area is solved, and the accuracy of character attribute information identification is improved.

Description

The recognition methods of personage's attribute information, device and electronic equipment
Technical field
The disclosure relates to image processing field, relates in particular to the recognition methods of a kind of personage's attribute information, device and electronic equipment.
Background technology
Personage's attribute information is identified in a lot of fields such as image processing, authentication and robot vision and all exists potential application.Such as, in image processing field, can the personage in image be done targetedly and be processed according to the personage's attribute information identifying.
In correlation technique, conventionally from facial image, extract personage's attribute information and identify needed geometric properties, and use various machine learning algorithms to train the geometric properties extracting.Such as, in the time that personage's attribute information comprises age information and sex information, can use NMF(Non-negative Matrix Factorization, Non-negative Matrix Factorization) improvement algorithm carries out age identification, and use is carried out sex identification based on AdaBoost sorting technique.
Realizing in process of the present disclosure, find that correlation technique at least exists following problem:
In the personage's attribute information recognition methods shown in correlation technique; the geometric properties extracting from facial image be subject to the brightness of human face region and the impact of lighting angle larger; the geometric properties extracting under dark or backlight environment at light has bigger difference with respect under home; identify the result obtaining along with the conversion of environment can produce larger fluctuation, thereby cause recognition result inaccurate.
Summary of the invention
For solve the geometric properties extracting from facial image in correlation technique be subject to the brightness of human face region and the impact of lighting angle larger, thereby cause the inaccurate problem of recognition result, disclosure embodiment provides the recognition methods of a kind of personage's attribute information, device and electronic equipment.Described technical scheme is as follows:
According to the first aspect of disclosure embodiment, the recognition methods of a kind of personage's attribute information is provided, comprising:
Obtain the image that includes face;
Described face is identified, obtained personage's identity information and initial personage's attribute information;
Inquire about the historical personage attribute information corresponding with described personage's identity information;
Determine personage's attribute information of this identification according to personage's attribute information of described initial personage's attribute information and described history.
Preferably, described personage's attribute information according to described initial personage's attribute information and described history is determined personage's attribute information of this identification, comprising:
In the time that described personage's attribute information comprises age information, the mean value of initial age information and historical age information is defined as to the age information of this identification.
Preferably, described personage's attribute information according to described initial personage's attribute information and described history is determined personage's attribute information of this identification, comprising:
In the time that described personage's attribute information comprises age information, obtain temporal information corresponding to initial age information and historical temporal information corresponding to age information;
Determine the weight of the weight of described initial age information and the age information of described history according to the temporal information corresponding to age information of temporal information corresponding to described initial age information and described history;
Determine the age information of this identification according to the weight of described initial age information, the weight of described initial age information, the age information of described history and the age information of described history.
Preferably, described personage's attribute information according to described initial personage's attribute information and described history is determined personage's attribute information of this identification, comprising:
In the time that described personage's attribute information comprises sex information, calculate two kinds of sexes each self-corresponding accounting numerical value in the set of initial sex information and historical sex information composition;
Judge in the each self-corresponding accounting numerical value of described two kinds of sexes whether have the accounting numerical value that is greater than predetermined ratio threshold value t, 50% < t < 100%;
If judged result is to have the accounting numerical value that is greater than described predetermined ratio threshold value t, the sex information that is this identification by described sex determination corresponding to accounting numerical value that is greater than predetermined ratio threshold value t.
Preferably, also comprise:
If judged result is not have the accounting numerical value that is greater than described predetermined ratio threshold value t, described initial sex information is defined as to the sex information of this identification.
Preferably, described method also comprises:
Upgrade personage's attribute information of described history according to personage's attribute information of described initial personage's attribute information and/or described this identification.
According to the second aspect of disclosure embodiment, a kind of personage's attribute information recognition device is provided, comprising:
Image collection module, for obtaining the image that includes face;
Identification module, for described face is identified, obtains personage's identity information and initial personage's attribute information;
Enquiry module, for inquiring about the historical personage attribute information corresponding with described personage's identity information;
Attribute information determination module, for determining personage's attribute information of this identification according to personage's attribute information of described initial personage's attribute information and described history.
Preferably, described attribute information determination module, comprising:
The first age information determining unit, in the time that described personage's attribute information comprises age information, is defined as the mean value of initial age information and historical age information the age information of this identification.
Preferably, described attribute information determination module, comprising:
Temporal information acquiring unit, in the time that described personage's attribute information comprises age information, obtains temporal information corresponding to initial age information and historical temporal information corresponding to age information;
Weight determining unit, for determining the weight of the weight of described initial age information and the age information of described history according to the temporal information corresponding to age information of temporal information corresponding to described initial age information and described history;
The second age information determining unit, for determining the age information of this identification according to the weight of described initial age information, the weight of described initial age information, the age information of described history and the age information of described history.
Preferably, described attribute information determination module, comprising:
Computing unit, in the time that described personage's attribute information comprises sex information, calculates two kinds of sexes each self-corresponding accounting numerical value in the set of initial sex information and historical sex information composition;
Judging unit, for judging whether the each self-corresponding accounting numerical value of described two kinds of sexes exists the accounting numerical value that is greater than predetermined ratio threshold value t, 50% < t < 100%;
The first sex information determining unit, if be to have the accounting numerical value that is greater than described predetermined ratio threshold value t, the sex information that is this identification by described sex determination corresponding to accounting numerical value that is greater than predetermined ratio threshold value t for described judging unit judged result.
Preferably, described attribute information determination module, also comprises:
Second sex information determining unit, if be not have the accounting numerical value that is greater than described predetermined ratio threshold value t for the judged result of described judging unit, is defined as described initial sex information the sex information of this identification.
Preferably, described device also comprises:
Update module, for upgrading personage's attribute information of described history according to personage's attribute information of described initial personage's attribute information and/or described this identification.
According to the third aspect of disclosure embodiment, a kind of electronic equipment is provided, comprising:
Processor;
For storing the storer of described processor executable;
Wherein, described processor is configured to:
Obtain the image that includes face;
Described face is identified, obtained personage's identity information and initial personage's attribute information;
Inquire about the historical personage attribute information corresponding with described personage's identity information;
Determine personage's attribute information of this identification according to personage's attribute information of described initial personage's attribute information and described history.
The technical scheme that disclosure embodiment provides can be brought following beneficial effect:
By the face in image is identified, obtain personage's identity information and initial personage's attribute information; Obtain personage's attribute information of this identification according to this initial personage's attribute information and historical personage's attribute information corresponding with this personage's identity information; Initial recognition result and historical recognition result are combined, to determine final recognition result, solved the geometric properties extracting from facial image in correlation technique be subject to the brightness of human face region and the impact of lighting angle larger, thereby cause the inaccurate problem of recognition result, reach the effect that improves personage's attribute information identification accuracy.
Should be understood that, it is only exemplary and explanatory that above general description and details are hereinafter described, and can not limit the disclosure.
Brief description of the drawings
Accompanying drawing is herein merged in instructions and forms the part of this instructions, shows and meets embodiment of the present disclosure, and be used from and explain principle of the present disclosure with instructions one.
Fig. 1 is according to the process flow diagram of a kind of personage's attribute information recognition methods shown in an exemplary embodiment;
Fig. 2 is according to the process flow diagram of a kind of personage's attribute information recognition methods shown in another exemplary embodiment;
Fig. 3 is according to the process flow diagram of a kind of personage's attribute information recognition methods shown in another exemplary embodiment;
Fig. 4 is according to the schematic diagram of a kind of personage's attribute information recognition device shown in an exemplary embodiment;
Fig. 5 is according to the schematic diagram of a kind of personage's attribute information recognition device shown in another exemplary embodiment;
Fig. 6 is according to the schematic diagram of a kind of electronic equipment shown in an exemplary embodiment;
Fig. 7 is according to the block diagram of a kind of electronic equipment shown in an exemplary embodiment.
Embodiment
Here will at length describe exemplary embodiment, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless separately there is expression, the same numbers in different accompanying drawings represents same or analogous key element.Embodiment described in following exemplary embodiment does not represent all embodiments consistent with the disclosure.On the contrary, they are only and equipment as consistent in some aspects that described in detail in appended claims, of the present disclosure and the example of method.
Fig. 1 is according to the process flow diagram of a kind of personage's attribute information recognition methods shown in an exemplary embodiment, as shown in Figure 1, this personage's attribute information recognition methods is for electronic equipment, and this electronic equipment can be smart mobile phone, panel computer or E-book reader etc.This personage's attribute information recognition methods can comprise the following steps:
In step 102, obtain the image that includes face;
In step 104, this face is identified, obtain personage's identity information and initial personage's attribute information;
In step 106, inquire about the historical personage attribute information corresponding with this personage's identity information;
In step 108, determine personage's attribute information of this identification according to this initial personage's attribute information and this historical personage's attribute information.
In sum, the personage's attribute information recognition methods shown in this exemplary embodiment, by the face in image is identified, obtains personage's identity information and initial personage's attribute information; Obtain personage's attribute information of this identification according to this initial personage's attribute information and historical personage's attribute information corresponding with this personage's identity information; Initial recognition result and historical recognition result are combined, to determine final recognition result, solved the geometric properties extracting from facial image in correlation technique be subject to the brightness of human face region and the impact of lighting angle larger, thereby cause the inaccurate problem of recognition result, reach the effect that improves personage's attribute information identification accuracy.
Fig. 2 is according to the process flow diagram of a kind of personage's attribute information recognition methods shown in another exemplary embodiment, as shown in Figure 2, this personage's attribute information recognition methods is for electronic equipment, and this electronic equipment can be smart mobile phone, panel computer or E-book reader etc.This personage's attribute information recognition methods can comprise the following steps:
In step 202, obtain the image that includes face;
Wherein, this image that includes face can be the image of the image acquisition units Real-time Collection in electronic equipment, also can time electronic equipment in pre-stored image.Such as, take electronic equipment as example as smart mobile phone, this image that includes face can be the photo that the camera in smart mobile phone is taken in real time, can be also the local pre-stored photo of smart mobile phone.
In step 204, this face is identified, obtain personage's identity information and initial personage's attribute information;
Recognition of face is a kind ofly to compare by analysis the technology that face visual signature information is carried out identity discriminating, belongs to biometrics identification technology, is generally used for the biological characteristic of biosome (generally refering in particular to people) itself to distinguish biosome individuality.Along with the development of technology, recognition of face not only can, for the identification to personage's identity information, can also be used for the identification to personage's attribute information, such as personage's age and sex etc.
In step 206, detect the local historical personage attribute information corresponding with this personage's identity information that whether store;
Whether electronic equipment can store corresponding historical personage's attribute information according to this personage's identity information inquiry this locality.
In step 208, store the historical personage attribute information corresponding with this personage's identity information if local, determine personage's attribute information of this identification according to this initial personage's attribute information and this historical personage's attribute information;
Wherein, personage's attribute information can comprise personage's age information and sex information.
In the time that personage's attribute information comprises age information, the mean value of initial age information and historical age information can be defined as to the age information of this identification.Such as, suppose that the initial age information that this identification obtains is 25 years old, obtain historical age information according to personage's identity information from local search and have 2, be respectively: 22 years old and 26 years old, the age information of this identification was (25+22+26)/3 ≈ 24 years old.
In addition,, when age information that the mean value that uses initial age information and historical age information is this identification, can also only store historical mean value and historical identification number of times.Such as, suppose that the initial age information that this identification obtains is 25 years old, the mean value of historical age information is 27 years old, and historical detection number of times is 2 times, and the age information of this identification is (25+27*2)/3 ≈ 26 years old.
In the time that personage's attribute information comprises sex information, can calculate two kinds of sexes each self-corresponding accounting numerical value in the set of initial sex information and historical sex information composition, and judge in the each self-corresponding accounting numerical value of these two kinds of sexes whether have the accounting numerical value that is greater than predetermined ratio threshold value t, 50% < t < 100%; If judged result is to have the accounting numerical value that is greater than t, the sex information that is this identification by sex determination corresponding the accounting numerical value of this t; If judged result is not have the accounting numerical value that is greater than t, initial sex information is defined as to the sex information of this identification.
Such as, suppose that t is 70%, the initial sex information that this identification obtains is the male sex, obtains 4 of historical sex Information commons according to personage's identity information from local search, is respectively the male sex, the male sex, masculinity and femininity., in the set of initial sex information and historical sex information composition, accounting numerical value corresponding to the male sex is 80%, and accounting numerical value corresponding to women is 20%, and wherein, accounting numerical value corresponding to the male sex is greater than 70%, determines that the sex information of this identification is the male sex.Be respectively the male sex, the male sex, women and women if obtain historical sex information from local search, in the set of initial sex information and historical sex information composition, accounting numerical value corresponding to the male sex is 60%, accounting numerical value corresponding to women is 40%, the accounting numerical value that masculinity and femininity is corresponding is all not more than 70%, the sex information of determining this identification is that this identification obtains initial sex information, the i.e. male sex.
In step 210, upgrade this historical personage's attribute information according to personage's attribute information of initial personage's attribute information and/or this identification.
Electronic equipment can be stored as historical personage's attribute information by initial personage's attribute information; Or electronic equipment can be stored as historical personage's attribute information by personage's attribute information of this identification; Or electronic equipment can all be stored as historical personage's attribute information by personage's attribute information of initial personage's attribute information and this identification; Or electronic equipment can be stored as historical age information by initial age information, and the sex information of this identification is stored as to historical sex information; Or electronic equipment can be stored as historical sex information by initial sex information, and the age information of this identification is stored as to historical age information.
In sum, the personage's attribute information recognition methods shown in this exemplary embodiment, by the face in image is identified, obtains personage's identity information and initial personage's attribute information; Obtain personage's attribute information of this identification according to this initial personage's attribute information and historical personage's attribute information corresponding with this personage's identity information; Initial recognition result and historical recognition result are combined, to determine final recognition result, solved the geometric properties extracting from facial image in correlation technique be subject to the brightness of human face region and the impact of lighting angle larger, thereby cause the inaccurate problem of recognition result, reach the effect that improves personage's attribute information identification accuracy.
Fig. 3 is according to the process flow diagram of a kind of personage's attribute information recognition methods shown in another exemplary embodiment, as shown in Figure 3, this personage's attribute information recognition methods is for electronic equipment, and this electronic equipment can be smart mobile phone, panel computer or E-book reader etc.This personage's attribute information recognition methods can comprise the following steps:
In step 302, obtain the image that includes face;
Wherein, this image that includes face can be the image of the image acquisition units Real-time Collection in electronic equipment, also can time electronic equipment in pre-stored image.Such as, take electronic equipment as example as smart mobile phone, this image that includes face can be the photo that the camera in smart mobile phone is taken in real time, can be also the local pre-stored photo of smart mobile phone.
In step 304, this face is identified, obtain personage's identity information and initial personage's attribute information;
Recognition of face is a kind ofly to compare by analysis the technology that face visual signature information is carried out identity discriminating, belongs to biometrics identification technology, is generally used for the biological characteristic of biosome (generally refering in particular to people) itself to distinguish biosome individuality.Along with the development of technology, recognition of face not only can, for the identification to personage's identity information, can also be used for the identification to personage's attribute information, such as personage's age and sex etc.
In step 306, judge the local historical personage attribute information corresponding with this personage's identity information that whether store; If so, enter step 308, otherwise, step 310 entered;
Electronic equipment can be stored as historical personage's attribute information by corresponding all previous personage's attribute information identifying personage's identity information.In the time of follow-up each identification, can whether there is corresponding historical personage's attribute information according to the personage's identity information inquiry identifying.
In step 308, determine to obtain personage's attribute information of this identification according to this initial personage's attribute information and this historical personage's attribute information;
Wherein, personage's attribute information can comprise personage's age information and sex information.
In the time that personage's attribute information comprises age information, the mean value of initial age information and historical age information can be defined as to the age information of this identification.Such as, suppose that the initial age information that this identification obtains is 25 years old, obtain historical age information according to personage's identity information from local search and have 2, be respectively: 22 years old and 26 years old, the age information of this identification was (25+22+26)/3 ≈ 24 years old.
In addition,, when age information that the mean value that uses initial age information and historical age information is this identification, can also only store historical mean value and historical identification number of times.Such as, suppose that the initial age information that this identification obtains is 25 years old, the mean value of historical age information is 27 years old, and historical detection number of times is 2 times, and the age information of this identification is (25+27*2)/3 ≈ 26 years old.
In addition, consider As time goes on, same personage's age can change, and in order further to improve the accuracy of age identification, can identify at the age time, the historical age information obtaining in different time identification is arranged to different weights.Such as, electronic equipment can obtain temporal information corresponding to initial age information and historical temporal information corresponding to age information, determine the weight of this initial age information and the weight of this historical age information according to temporal information corresponding to this initial age information and temporal information corresponding to this historical age information, and determine the age information of this identification according to the weight of the weight of this initial age information, this initial age information, this historical age information and this historical age information.Wherein, temporal information corresponding to initial age information is current time, and historical temporal information corresponding to age information is the time that historical age information is identified storage.The length that electronic equipment can be identified the time gap current time of storage according to historical age information arranges the weight of each age information.
In actual applications, can consider to initial age information and apart from obtaining the historical larger weight of age information setting in nearer time period of current time, the interior historical less weight of age information setting obtaining of time period that the current time of adjusting the distance is far away, such as, suppose that the initial age information that this identification obtains is 25 years old, obtain historical age information according to personage's identity information from local search and have 2, be respectively: 22 years old and 26 years old, wherein, it within 22 years old, is the historical age information of storage within month, it within 26 years old, is the half a year of the historical age information of storage before, electronic equipment can be according to pre-configured weight Provisioning Policy, the weight of initial age information is set to 4, within one month, the weight of the historical age information of storage is set to 2, before half a year, the weight of the historical age information of storage is set to 1, determine that the age information of this identification is (25*4+22*2+26*1)/(4+2+1) ≈ 24 years old.
In the time that personage's attribute information comprises sex information, can calculate two kinds of sexes each self-corresponding accounting numerical value in the set of initial sex information and historical sex information composition, and judge in the each self-corresponding accounting numerical value of these two kinds of sexes whether have the accounting numerical value that is greater than predetermined ratio threshold value t, 50% < t < 100%; If judged result is to have the accounting numerical value that is greater than t, the sex information that is this identification by sex determination corresponding the accounting numerical value of this t; If judged result is not have the accounting numerical value that is greater than t, initial sex information is defined as to the sex information of this identification.
Such as, suppose that t is 70%, the initial sex information that this identification obtains is the male sex, 4 of the historical sex Information commons obtaining from local search according to personage's identity information, are respectively the male sex, the male sex, masculinity and femininity., in the set of initial sex information and historical sex information composition, accounting numerical value corresponding to the male sex is 80%, and accounting numerical value corresponding to women is 20%, and wherein, accounting numerical value corresponding to the male sex is greater than 70%, determines that the sex information of this identification is the male sex.Be respectively the male sex, the male sex, women and women if obtain historical sex information from local search, in the set of initial sex information and historical sex information composition, accounting numerical value corresponding to the male sex is 60%, accounting numerical value corresponding to women is 40%, the accounting numerical value that masculinity and femininity is corresponding is all not more than 70%, the sex information of determining this identification is that this identification obtains initial sex information, the i.e. male sex.
Like age recognition category, in the time that sex is identified, also can different weights be set to the historical sex information obtaining in different time identification.Such as, electronic equipment can obtain temporal information corresponding to initial sex information and historical temporal information corresponding to sex information, determine the weight of this initial sex information and the weight of this historical sex information according to temporal information corresponding to this initial sex information and this historical temporal information corresponding to sex information, and according to the each self-corresponding accounting numerical value of two kinds of sexes of weight calculation of the weight of this initial sex information, this initial sex information, this historical sex information and this historical sex information.Wherein, temporal information corresponding to initial sex information is current time, and historical temporal information corresponding to sex information is the time that historical sex information is identified storage.The length that electronic equipment can be identified the time gap current time of storage according to historical sex information arranges the weight of each sex information.
In actual applications, can consider to initial sex information and apart from obtaining the historical larger weight of sex information setting in nearer time period of current time, the interior historical less weight of sex information setting obtaining of time period that the current time of adjusting the distance is far away, such as, suppose that the initial sex information that this identification obtains is the male sex, 4 of the historical sex Information commons obtaining from local search according to personage's identity information, be respectively the male sex, the male sex, masculinity and femininity, be respectively 1 month the storage time of these 4 historical sex information apart from current time, 1 month, 3 months and 6 months, electronic equipment can be according to pre-configured weight Provisioning Policy, the weight of initial sex information is set to 5, within 1 month, the weight of the historical sex information of storage is set to 4, in 1 to 3 months, the weight of the historical sex information of storage is set to 2, in 3 to 6 months, the weight of the historical sex information of storage is set to 1, accounting numerical value corresponding to the male sex is (1*5+1*4+1*4+1*2)/(1*5+1*4+1*4+1*2+1*1) ≈ 93%, accounting numerical value corresponding to women is (1*5+1*4+1*4+1*2)/(1*5+1*4+1*4+1*2+1*1) ≈ 7%.
In step 310, this initial personage's attribute information is defined as to personage's attribute information of this identification;
Do not store the historical personage attribute information corresponding with this personage's identity information if local, initial personage's attribute information is defined as to personage's attribute information of this identification.
In step 312, more personage's attribute information of new historical.
In the time that this locality stores corresponding with this personage's identity information historical personage's attribute information, electronic equipment can be stored as historical personage's attribute information by initial personage's attribute information; Or electronic equipment can be stored as historical personage's attribute information by personage's attribute information of this identification; Or electronic equipment can all be stored as historical personage's attribute information by personage's attribute information of initial personage's attribute information and this identification; Or electronic equipment can be stored as historical age information by initial age information, and the sex information of this identification is stored as to historical sex information; Or electronic equipment can be stored as historical sex information by initial sex information, and the age information of this identification is stored as to historical age information.
It should be noted that, when the mean value of initial age information and historical age information being retrieved as to the age information of this identification, and historical age information is during with the form storage of mean value, the age information of this identification can be updated to historical age mean value, and history is identified to number of times+1.
In the time that this locality does not store corresponding with this personage's identity information historical personage's attribute information, electronic equipment is set up the corresponding relation of this personage's identity information and personage's attribute information, and initial personage's attribute information is stored as to historical personage's attribute information.
In sum, the personage's attribute information recognition methods shown in this exemplary embodiment, by the face in image is identified, obtains personage's identity information and initial personage's attribute information; Obtain personage's attribute information of this identification according to this initial personage's attribute information and historical personage's attribute information corresponding with this personage's identity information; Initial recognition result and historical recognition result are combined, to determine final recognition result, solved the geometric properties extracting from facial image in correlation technique be subject to the brightness of human face region and the impact of lighting angle larger, thereby cause the inaccurate problem of recognition result, reach the effect that improves personage's attribute information identification accuracy.
In addition, personage's attribute information recognition methods shown in this exemplary embodiment, in the time carrying out the identification of personage's attribute information, the historical personage's attribute information obtaining is arranged to different weights, thereby further improve the accuracy of personage's attribute information identification in different time identification.
Fig. 4 is according to the schematic diagram of a kind of personage's attribute information recognition device shown in an exemplary embodiment.This personage's attribute information recognition device is for electronic equipment, and this electronic equipment can be smart mobile phone, panel computer or E-book reader etc.With reference to Fig. 4, this device comprises image collection module 401, identification module 402, enquiry module 403 and attribute information determination module 404;
This image collection module 401 is configured to the image that includes face for obtaining;
This identification module 402 is configured to for this face is identified, and obtains personage's identity information and initial personage's attribute information;
This enquiry module 403 is configured to for inquiring about the historical personage attribute information corresponding with this personage's identity information;
This attribute information determination module 404 is configured to the personage's attribute information for determine this identification according to this initial personage's attribute information and this historical personage's attribute information.
In sum, the personage's attribute information recognition device shown in this exemplary embodiment, by the face in image is identified, obtains personage's identity information and initial personage's attribute information; Obtain personage's attribute information of this identification according to this initial personage's attribute information and historical personage's attribute information corresponding with this personage's identity information; Initial recognition result and historical recognition result are combined, to determine final recognition result, solved the geometric properties extracting from facial image in correlation technique be subject to the brightness of human face region and the impact of lighting angle larger, thereby cause the inaccurate problem of recognition result, reach the effect that improves personage's attribute information identification accuracy.
Fig. 5 is according to the schematic diagram of a kind of personage's attribute information recognition device shown in another exemplary embodiment.This personage's attribute information recognition device is for electronic equipment, and this electronic equipment can be smart mobile phone, panel computer or E-book reader etc.With reference to Fig. 5, this device comprises image collection module 501, identification module 502, enquiry module 503 and attribute information determination module 504;
Image collection module 501 is configured to the image that includes face for obtaining;
This identification module 502 is configured to for this face is identified, and obtains personage's identity information and initial personage's attribute information;
This enquiry module 503 is configured to for inquiring about the historical personage attribute information corresponding with this personage's identity information;
This attribute information determination module 504 is configured to the personage's attribute information for determine this identification according to this initial personage's attribute information and this historical personage's attribute information.
Described attribute information determination module 504, comprising: the first age information determining unit 504a;
Described the first age information determining unit 504a is configured to in the time that described personage's attribute information comprises age information, the mean value of initial age information and historical age information is defined as to the age information of this identification.
Described attribute information determination module 504, comprising: temporal information acquiring unit 504b, weight determining unit 504c and the second age information determining unit 504d;
Described temporal information acquiring unit 504b is configured to in the time that described personage's attribute information comprises age information, obtains temporal information corresponding to initial age information and historical temporal information corresponding to age information;
Described weight determining unit 504c is configured to the weight for determine the weight of described initial age information and the age information of described history according to the temporal information corresponding to age information of temporal information corresponding to described initial age information and described history;
Described the second age information determining unit 504d is configured to the age information for determine this identification according to the weight of described initial age information, the weight of described initial age information, the age information of described history and the age information of described history.
Described attribute information determination module 504, comprising: computing unit 504e, judging unit 504f and the first sex information determining unit 504g;
Described computing unit 504e is configured to in the time that described personage's attribute information comprises sex information, calculates two kinds of sexes each self-corresponding accounting numerical value in the set of initial sex information and historical sex information composition;
Wherein, described computing unit 504e is specifically configured to in the time that described personage's attribute information comprises sex information, obtain temporal information corresponding to initial sex information and historical temporal information corresponding to sex information, determine the weight of the weight of described initial sex information and the sex information of described history according to the temporal information corresponding to sex information of temporal information corresponding to described initial sex information and described history, according to described initial sex information, the weight of described initial sex information, two kinds of sexes of weight calculation of the sex information of described history and the sex information of described history are each self-corresponding accounting numerical value in the set of initial sex information and historical sex information composition.
Described judging unit 504f is configured to for judging whether the each self-corresponding accounting numerical value of described two kinds of sexes exists the accounting numerical value that is greater than predetermined ratio threshold value t, 50% < t < 100%;
If it is to have the accounting numerical value that is greater than described predetermined ratio threshold value t, the sex information that is this identification by described sex determination corresponding to accounting numerical value that is greater than predetermined ratio threshold value t that described the first sex information determining unit 504g is configured to for described judging unit 504f judged result.
Described attribute information determination module, also comprises: second sex information determining unit 504h;
If it is not have the accounting numerical value that is greater than described predetermined ratio threshold value t that described second sex information determining unit 504h is configured to for the judged result of described judging unit 504f, described initial sex information is defined as to the sex information of this identification.
Described device also comprises: update module 504;
Described update module 504 is configured to the personage's attribute information for upgrade described history according to personage's attribute information of described initial personage's attribute information and/or described this identification.
In sum, the personage's attribute information recognition methods shown in this exemplary embodiment, by the face in image is identified, obtains personage's identity information and initial personage's attribute information; Obtain personage's attribute information of this identification according to this initial personage's attribute information and historical personage's attribute information corresponding with this personage's identity information; Initial recognition result and historical recognition result are combined, to obtain final recognition result, solved the geometric properties extracting from facial image in correlation technique be subject to the brightness of human face region and the impact of lighting angle larger, thereby cause the inaccurate problem of recognition result, reach the effect that improves personage's attribute information identification accuracy.
In addition, personage's attribute information recognition methods shown in this exemplary embodiment, in the time carrying out the identification of personage's attribute information, the historical personage's attribute information obtaining is arranged to different weights, thereby further improve the accuracy of personage's attribute information identification in different time identification.
Fig. 6 is according to the schematic diagram of a kind of electronic equipment shown in an exemplary embodiment.This electronic equipment can be smart mobile phone, panel computer or E-book reader etc.With reference to Fig. 6, this electronic equipment comprises the personage's attribute information recognition device 001 as shown in Fig. 4 or Fig. 5.
Fig. 7 is according to the block diagram of a kind of electronic equipment 700 shown in an exemplary embodiment.For example, electronic equipment 700 can be mobile phone, computing machine, digital broadcast terminal, information receiving and transmitting equipment, game console, flat-panel devices, Medical Devices, body-building equipment, personal digital assistant etc.
With reference to Fig. 7, electronic equipment 700 can comprise following one or more assembly: processing components 702, storer 704, power supply module 706, multimedia groupware 708, audio-frequency assembly 710, the interface 712 of I/O (I/O), sensor module 714, and communications component 716.
Processing components 702 is controlled the integrated operation of electronic equipment 700 conventionally, such as with demonstration, call, data communication, the operation that camera operation and record operation are associated.Processing components 702 can comprise that one or more processors 720 carry out instruction, to complete all or part of step of above-mentioned method.In addition, processing components 702 can comprise one or more modules, is convenient to mutual between processing components 702 and other assemblies.For example, processing components 702 can comprise multi-media module, to facilitate mutual between multimedia groupware 708 and processing components 702.
Storer 704 is configured to store various types of data to be supported in the operation of electronic equipment 700.The example of these data comprises for any application program of operation on electronic equipment 700 or the instruction of method, contact data, telephone book data, message, picture, video etc.Storer 704 can be realized by the volatibility of any type or non-volatile memory device or their combination, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read-only memory (prom), ROM (read-only memory) (ROM), magnetic store, flash memory, disk or CD.In storer 704, also store one or more modules, these one or more modules are configured to be carried out by these one or more processors 720, to complete all or part of step of above-mentioned method.
The various assemblies that power supply module 706 is electronic equipment 700 provide electric power.Power supply module 706 can comprise power-supply management system, one or more power supplys, and other and the assembly that generates, manages and distribute electric power to be associated for electronic equipment 700.
Multimedia groupware 708 is included in the screen that an output interface is provided between described electronic equipment 700 and user.In certain embodiments, screen can comprise liquid crystal display (LCD) and touch panel (TP).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises that one or more touch sensors are with the gesture on sensing touch, slip and touch panel.Described touch sensor is the border of sensing touch or sliding action not only, but also detects duration and the pressure relevant to described touch or slide.In certain embodiments, multimedia groupware 708 comprises a front-facing camera and/or post-positioned pick-up head.When electronic equipment 700 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.
Audio-frequency assembly 710 is configured to output and/or input audio signal.For example, audio-frequency assembly 710 comprises a microphone (MIC), and when electronic equipment 700 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The sound signal receiving can be further stored in storer 704 or be sent via communications component 716.In certain embodiments, audio-frequency assembly 710 also comprises a loudspeaker, for output audio signal.
I/O interface 712 is for providing interface between processing components 702 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.
Sensor module 714 comprises one or more sensors, is used to electronic equipment 700 that the state estimation of various aspects is provided.For example, sensor module 714 can detect the opening/closing state of electronic equipment 700, the relative positioning of assembly, for example described assembly is display and the keypad of electronic equipment 700, the position of an assembly of all right detected electrons equipment 700 of sensor module 714 or electronic equipment 700 changes, the existence that user contacts with electronic equipment 700 or do not have the temperature variation of electronic equipment 700 orientation or acceleration/deceleration and electronic equipment 700.Sensor module 714 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor module 714 can also comprise optical sensor, as CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, this sensor module 714 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure transducer or temperature sensor.
Communications component 716 is configured to be convenient to the communication of wired or wireless mode between electronic equipment 700 and other equipment.Electronic equipment 700 can access the wireless network based on communication standard, as WiFi, and 2G or 3G, or their combination.In one exemplary embodiment, communications component 716 receives broadcast singal or the broadcast related information from external broadcasting management system via broadcast channel.In one exemplary embodiment, described communications component 716 also comprises near-field communication (NFC) module, to promote junction service.For example, can be based on radio-frequency (RF) identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology, ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.
In the exemplary embodiment, electronic equipment 700 can be realized by one or more application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD) (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components, for carrying out said method.
In the exemplary embodiment, also provide a kind of non-provisional computer-readable recording medium that comprises instruction, for example, comprised the storer 704 of instruction, above-mentioned instruction can have been carried out said method by the processor of electronic equipment 700 720.For example, this non-provisional computer-readable recording medium can be ROM, random-access memory (ram), CD-ROM, tape, floppy disk and optical data storage equipment etc.
Those skilled in the art, considering instructions and putting into practice after disclosure herein, will easily expect other embodiment of the present disclosure.The application is intended to contain any modification of the present disclosure, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present disclosure and comprised undocumented common practise or the conventional techniques means in the art of the disclosure.Instructions and embodiment are only regarded as exemplary, and true scope of the present disclosure and spirit are pointed out by claim.
Should be understood that, the disclosure is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendments and change not departing from its scope.The scope of the present disclosure is only limited by appended claim.

Claims (13)

1. the recognition methods of personage's attribute information, is characterized in that, described method comprises:
Obtain the image that includes face;
Described face is identified, obtained personage's identity information and initial personage's attribute information;
Inquire about the historical personage attribute information corresponding with described personage's identity information;
Determine personage's attribute information of this identification according to personage's attribute information of described initial personage's attribute information and described history.
2. method according to claim 1, is characterized in that, described personage's attribute information according to described initial personage's attribute information and described history is determined personage's attribute information of this identification, comprising:
In the time that described personage's attribute information comprises age information, the mean value of initial age information and historical age information is defined as to the age information of this identification.
3. method according to claim 1, is characterized in that, described personage's attribute information according to described initial personage's attribute information and described history is determined personage's attribute information of this identification, comprising:
In the time that described personage's attribute information comprises age information, obtain temporal information corresponding to initial age information and historical temporal information corresponding to age information;
Determine the weight of the weight of described initial age information and the age information of described history according to the temporal information corresponding to age information of temporal information corresponding to described initial age information and described history;
Determine the age information of this identification according to the weight of described initial age information, the weight of described initial age information, the age information of described history and the age information of described history.
4. method according to claim 1, is characterized in that, described personage's attribute information according to described initial personage's attribute information and described history is determined personage's attribute information of this identification, comprising:
In the time that described personage's attribute information comprises sex information, calculate two kinds of sexes each self-corresponding accounting numerical value in the set of initial sex information and historical sex information composition;
Judge in the each self-corresponding accounting numerical value of described two kinds of sexes whether have the accounting numerical value that is greater than predetermined ratio threshold value t, 50% < t < 100%;
If judged result is to have the accounting numerical value that is greater than described predetermined ratio threshold value t, the sex information that is this identification by sex determination corresponding the accounting numerical value that is greater than described predetermined ratio threshold value t.
5. method according to claim 4, is characterized in that, also comprises:
If judged result is not have the accounting numerical value that is greater than described predetermined ratio threshold value t, described initial sex information is defined as to the sex information of this identification.
6. method according to claim 1, is characterized in that, described method also comprises:
Upgrade personage's attribute information of described history according to personage's attribute information of described initial personage's attribute information and/or described this identification.
7. personage's attribute information recognition device, is characterized in that, described device comprises:
Image collection module, for obtaining the image that includes face;
Identification module, for described face is identified, obtains personage's identity information and initial personage's attribute information;
Enquiry module, for inquiring about the historical personage attribute information corresponding with described personage's identity information;
Attribute information determination module, for determining personage's attribute information of this identification according to personage's attribute information of described initial personage's attribute information and described history.
8. device according to claim 7, is characterized in that, described attribute information determination module, comprising:
The first age information determining unit, in the time that described personage's attribute information comprises age information, is defined as the mean value of initial age information and historical age information the age information of this identification.
9. device according to claim 7, is characterized in that, described attribute information determination module, comprising:
Temporal information acquiring unit, in the time that described personage's attribute information comprises age information, obtains temporal information corresponding to initial age information and historical temporal information corresponding to age information;
Weight determining unit, for determining the weight of the weight of described initial age information and the age information of described history according to the temporal information corresponding to age information of temporal information corresponding to described initial age information and described history;
The second age information determining unit, for determining the age information of this identification according to the weight of described initial age information, the weight of described initial age information, the age information of described history and the age information of described history.
10. device according to claim 7, is characterized in that, described attribute information determination module, comprising:
Computing unit, in the time that described personage's attribute information comprises sex information, calculates two kinds of sexes each self-corresponding accounting numerical value in the set of initial sex information and historical sex information composition;
Judging unit, for judging whether the each self-corresponding accounting numerical value of described two kinds of sexes exists the accounting numerical value that is greater than predetermined ratio threshold value t, 50% < t < 100%;
The first sex information determining unit, if be to have the accounting numerical value that is greater than described predetermined ratio threshold value t, the sex information that is this identification by sex determination corresponding the accounting numerical value that is greater than described predetermined ratio threshold value t for described judging unit judged result.
11. devices according to claim 10, is characterized in that, described attribute information determination module, also comprises:
Second sex information determining unit, if be not have the accounting numerical value that is greater than described predetermined ratio threshold value t for the judged result of described judging unit, is defined as described initial sex information the sex information of this identification.
12. devices according to claim 7, is characterized in that, described device also comprises:
Update module, for upgrading personage's attribute information of described history according to personage's attribute information of described initial personage's attribute information and/or described this identification.
13. 1 kinds of electronic equipments, is characterized in that, described electronic equipment comprises:
Processor;
For storing the storer of described processor executable;
Wherein, described processor is configured to:
Obtain the image that includes face;
Described face is identified, obtained personage's identity information and initial personage's attribute information;
Inquire about the historical personage attribute information corresponding with described personage's identity information;
Determine personage's attribute information of this identification according to personage's attribute information of described initial personage's attribute information and described history.
CN201410074645.XA 2014-03-03 2014-03-03 Character attribute information identifying method, device and electronic equipment Active CN103886284B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410074645.XA CN103886284B (en) 2014-03-03 2014-03-03 Character attribute information identifying method, device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410074645.XA CN103886284B (en) 2014-03-03 2014-03-03 Character attribute information identifying method, device and electronic equipment

Publications (2)

Publication Number Publication Date
CN103886284A true CN103886284A (en) 2014-06-25
CN103886284B CN103886284B (en) 2017-03-01

Family

ID=50955167

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410074645.XA Active CN103886284B (en) 2014-03-03 2014-03-03 Character attribute information identifying method, device and electronic equipment

Country Status (1)

Country Link
CN (1) CN103886284B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105335709A (en) * 2015-10-21 2016-02-17 奇酷互联网络科技（深圳）有限公司 Face identification display method, face identification display device and terminal
CN105488470A (en) * 2015-11-30 2016-04-13 小米科技有限责任公司 Method and apparatus for determining character attribute information
EP3067829A1 (en) * 2015-03-13 2016-09-14 Kabushiki Kaisha Toshiba Person authentication method
CN108108668A (en) * 2017-12-01 2018-06-01 北京小米移动软件有限公司 Age Forecasting Methodology and device based on image
CN108540755A (en) * 2017-03-01 2018-09-14 中国电信股份有限公司 Personal identification method and device
CN108831479A (en) * 2018-06-27 2018-11-16 努比亚技术有限公司 A kind of audio recognition method, terminal and computer readable storage medium
CN111368101A (en) * 2020-03-05 2020-07-03 腾讯科技（深圳）有限公司 Multimedia resource information display method, device, equipment and storage medium
CN114550088A (en) * 2022-02-22 2022-05-27 北京城建设计发展集团股份有限公司 Multi-camera fused passenger identification method and system and electronic equipment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101584575A (en) * 2009-06-19 2009-11-25 无锡骏聿科技有限公司 Age assessment method based on face recognition technology
CN102682294A (en) * 2012-05-17 2012-09-19 南京理工大学常熟研究院有限公司 Gender identification method based on face shape and generalized self-organizing mapping
US8520906B1 (en) * 2007-09-24 2013-08-27 Videomining Corporation Method and system for age estimation based on relative ages of pairwise facial images of people

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8520906B1 (en) * 2007-09-24 2013-08-27 Videomining Corporation Method and system for age estimation based on relative ages of pairwise facial images of people
CN101584575A (en) * 2009-06-19 2009-11-25 无锡骏聿科技有限公司 Age assessment method based on face recognition technology
CN102682294A (en) * 2012-05-17 2012-09-19 南京理工大学常熟研究院有限公司 Gender identification method based on face shape and generalized self-organizing mapping

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张天刚等: "基于人脸图像的性别识别与年龄估计", 《计算机工程与设计》 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3067829A1 (en) * 2015-03-13 2016-09-14 Kabushiki Kaisha Toshiba Person authentication method
US9807090B2 (en) 2015-03-13 2017-10-31 Kabushiki Kaisha Toshiba Person authentication method
CN105335709A (en) * 2015-10-21 2016-02-17 奇酷互联网络科技（深圳）有限公司 Face identification display method, face identification display device and terminal
CN105488470A (en) * 2015-11-30 2016-04-13 小米科技有限责任公司 Method and apparatus for determining character attribute information
CN108540755A (en) * 2017-03-01 2018-09-14 中国电信股份有限公司 Personal identification method and device
CN108108668A (en) * 2017-12-01 2018-06-01 北京小米移动软件有限公司 Age Forecasting Methodology and device based on image
CN108108668B (en) * 2017-12-01 2021-04-27 北京小米移动软件有限公司 Age prediction method and device based on image
CN108831479A (en) * 2018-06-27 2018-11-16 努比亚技术有限公司 A kind of audio recognition method, terminal and computer readable storage medium
CN111368101A (en) * 2020-03-05 2020-07-03 腾讯科技（深圳）有限公司 Multimedia resource information display method, device, equipment and storage medium
CN111368101B (en) * 2020-03-05 2021-06-18 腾讯科技（深圳）有限公司 Multimedia resource information display method, device, equipment and storage medium
CN114550088A (en) * 2022-02-22 2022-05-27 北京城建设计发展集团股份有限公司 Multi-camera fused passenger identification method and system and electronic equipment
CN114550088B (en) * 2022-02-22 2022-12-13 北京城建设计发展集团股份有限公司 Multi-camera fused passenger identification method and system and electronic equipment

Also Published As

Publication number Publication date
CN103886284B (en) 2017-03-01

Similar Documents

Publication Publication Date Title
CN104850828B (en) Character recognition method and device
CN103886284B (en) Character attribute information identifying method, device and electronic equipment
CN106503617A (en) Model training method and device
CN104408402B (en) Face identification method and device
CN107454465A (en) Video playback progress display method and device, electronic equipment
CN105654420A (en) Face image processing method and device
CN104852966A (en) Numerical value transfer method, terminal and cloud server
CN107133576A (en) Age of user recognition methods and device
CN105095881A (en) Method, apparatus and terminal for face identification
CN105335712A (en) Image recognition method, device and terminal
CN103944804A (en) Contact recommending method and device
CN104077563A (en) Human face recognition method and device
CN105279499A (en) Age recognition method and device
CN103885588A (en) Automatic switchover method and device
CN104408404A (en) Face identification method and apparatus
CN106250921A (en) Image processing method and device
CN104063865A (en) Classification model creation method, image segmentation method and related device
CN104301528A (en) Information displaying method and device
CN109360197A (en) Processing method, device, electronic equipment and the storage medium of image
CN105354560A (en) Fingerprint identification method and device
CN105357425A (en) Image shooting method and image shooting device
CN105574512A (en) Method and device for processing image
CN107463903A (en) Face key independent positioning method and device
CN105335684A (en) Face detection method and device
CN105139378A (en) Card boundary detection method and apparatus

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant