CN110019890A - A kind of photo matching process of mobile terminal - Google Patents
A kind of photo matching process of mobile terminal Download PDFInfo
- Publication number
- CN110019890A CN110019890A CN201711330944.5A CN201711330944A CN110019890A CN 110019890 A CN110019890 A CN 110019890A CN 201711330944 A CN201711330944 A CN 201711330944A CN 110019890 A CN110019890 A CN 110019890A
- Authority
- CN
- China
- Prior art keywords
- information
- user images
- module
- user
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of photo matching process of mobile terminal, solve the problems, such as only to find photo similar with user by the single comparison factor of five features in the prior art.This method comprises the following steps: obtaining user images, the user images include at least the face of user;Identify that the information of the user images, the information include, the face information of the user images and the user's face angle information by the face information acquisition;The information of the user images is compared with the information of image in photo library;Push photo library in the highest image of user images matching degree.
Description
Technical field
The photo match party for comparing application field more particularly to a kind of mobile terminal is inquired the present invention relates to a kind of photo
Method.
Background technique
With the promotion of the mobile devices performance such as mobile phone, tablet computer, the intelligence of mobile device has been melted into academia and work
The research hotspot of industry.The performance boost of imaging sensor is also provided to the vision application on mobile platform on mobile intelligent terminal
Better hardware condition support.Meanwhile with the progress of human face analysis technology, the recognition of face of mobile terminal, Expression Recognition,
The mobile applications such as attributive analysis are shown up prominently in people's lives.In addition, the information retrieval technique based on image also gradually at
Ripe, major search engine also joined the function " scheme to search figure ".Face recognition technology and information retrieval technique based on image
Progress, make it possible automation similar face retrieval.Similar face retrieval has in terms of amusement search, crime
Very high application value.
Existing some methods for finding most like photo, derived from the application of face's five features comparison, matching way
It is single, i.e., similar face only is matched by comparing face's five features, not can be carried out accurate matching, accurately compared based on user
The photo psychology most like with oneself is found out, how one kind is provided and is precisely matched with photo library, is found out similar with user
Photo is those skilled in the art's technical problems to be solved.
Summary of the invention
The present invention provides a kind of photo matching process of mobile terminal, with solve it is existing cannot be accurately by user images
The technical issues of being matched with photo library, and finding out the photo most like with user.
The present invention provides a kind of photo matching process of mobile terminal, and this method comprises the following steps:
User images are obtained, the user images include at least the face of user;
Identify that the information of the user images, the information include, the face information of the user images and pass through described five
The user's face angle information of official's information acquisition;
The information of the user images is compared with the information of image in photo library;
Push photo library in the highest image of user images matching degree.
It further, further include that the user images are carried out with U.S. face processing before the information for identifying the user images.
Further, include by the method for the face information acquisition user's face angle information,
Pupil position is obtained, the angle of the pupil position line and horizontal direction is calculated;
Nose position is obtained, the ratio calculated between the distance and each distance of the nose position and face contour surrounding is closed
System.
It further, further include knowing before the information of the user images being compared with the information of image in photo library
The shooting pose information of the not described user images, by identifying, user profile determines that the shooting posture is believed in the user images
Breath.
It further, further include knowing before the information of the user images being compared with the information of image in photo library
The gender information of the not described user images and/or age information.
Further, identify that the gender information of the user images includes the hair length judged in the user images
And/or Adam's apple position profile.
Further, identify the user images age information include identify the user images facial wrinkles and/
Or the heavy degree in canthus and/or face skin situation.
It further, further include knowing before the information of the user images being compared with the information of image in photo library
The geographical location information of the not described user images.
The present invention also provides a kind of mobile terminal, including display module, photographing module and for storing the camera shooting mould
The image storage module of the shooting picture of block, further includes:
User images obtain module, for obtaining user images by the photographing module or described image memory module;
Data Analysis Services module identifies for the information to the user images, the Data Analysis Services module packet
Include face information identification module and user's face angle recognition module;
Information comparison module, for the information of the user images to be compared with the information of image in photo library;
Photo pushing module, for push in photo library with the highest image of user images matching degree.
Further, the user's face angle information identification module includes, for obtaining pupil position and described in calculating
The pupil position computing module of pupil position line and the angle of horizontal direction, and for obtaining nose position, described in calculating
The nose position computation module of proportionate relationship of the nose position at a distance from face contour surrounding and between each distance.
Further, the Data Analysis Services module further includes shooting gesture recognition module, the shooting gesture recognition
By identifying, user profile determines the shooting pose information to module in the user images.
Further, the Data Analysis Services module further includes Sexual discriminating module and/or age identification module, described
The gender information of Sexual discriminating module user images for identification, Age estimation module user's figure for identification
The age information of picture.
Further, the Data Analysis Services module further includes location identification module, and the location identification module is used for
Identify the geographical location information of the user images.
Beneficial effects of the present invention:
A kind of matched method of photo provided by the invention and mobile terminal, the user images got particular by identification
Then the face information and face angle information of middle user will be schemed in the face information of user and face angle information and photo library
The corresponding information of picture is compared, found out from photo library with the highest image of user images matching degree, by comparing
On the basis of face information, also increase and compare this comparison factor of face angle information, to help user smart from photo library
The photo most like with itself is found out quasi-ly.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.
Fig. 1 is a kind of flow chart of photo matching process of the present invention.
Fig. 2 is a kind of mobile terminal module frame diagram of the present invention.
Specific embodiment
Further explaination explanation now is made to the present invention by way of specific embodiment combination attached drawing.
It should be understood that any technical characteristic, any technical solution in the present embodiment are the technologies of plurality of optional
One or more of feature or optional technical solution, in order to describe it is succinct need it is impossible to exhaust of the invention in this document
All alternative technical characteristics and alternative technical solution, the embodiment for being also not easy to each technical characteristic are emphasized
It is one of for optional numerous embodiments, so those skilled in the art will appreciate that can will be provided by the invention any
Technological means is replaced or is combined with each other any two provided by the invention or more
And obtain new technical solution.Any technical characteristic and any technical solution in the present embodiment do not limit guarantor of the invention
Protect range, protection scope of the present invention should include that those skilled in the art not make the creative labor that institute is thinkable any to be replaced
Generation technique scheme and those skilled in the art are mutual by any two provided by the invention or more
New technical solution obtained from being mutually combined.
Fig. 1 is a kind of step flow chart of photo matching process of the present invention.
As shown in Figure 1, a kind of photo matching process of the present invention, includes the following steps:
Step 1 obtains user images, and the user images include at least the face of user;
User images are obtained by photographing module, which includes at least the face of user, refer specifically to include complete the five of user
Official's feature, five features refer specifically to eye, ear, nose, eyebrow, mouth feature, and in a preferred embodiment of the present invention, which is intelligence
Camera possessed by mobile phone itself, which, which can be, is immediately shot by photographing module, be also possible to user it
Before have been saved in this ground and either store image beyond the clouds.
Step 2 identifies that the information of the user images, the information include, the face information of the user images and
Pass through the user's face angle information of the face information acquisition;
The accessed user images information of identification is believed including face information and by the face angle of face information acquisition
Breath, identification face information specifically refer to eyes size, ear size, nose height, eyebrows bushed together, mouth in identification user images
Size cases, the angle where plane where face angle information refers to the face of acquired image and photographic device between plane
Relationship, including horizontal sextant angle and vertical angle, the acquisition of horizontal sextant angle are to obtain pupil position by first positioning face position
It sets, then calculates the angle of the horizontal center line of pupil position line and photographic device and obtain, the acquisition of vertical angle is first
Before this by positioning face position, nose position is obtained, then calculates the nose position at a distance from face contour surrounding
And the proportionate relationship between each distance, and then it is perpendicular between plane where plane where the face of acquisition image and photographic device
Straight angle, for example, in the case where the image got is all overlapped with the horizontal and vertical center line of filming apparatus, it is acquired
The angle of the horizontal center line of the line and photographic device of image pupil position be zero, it is believed that the shooting height that image is is
It is flat to clap, the nose position of acquired image with face contour at left and right sides of at a distance from ratio be 1:1, profile on nose position to face
Distance at a distance from facial bottom profiled ratio be 2:1, plane where plane where obtaining the face of image at this time and photographic device
Between vertical angle be also be zero, it is believed that the shooting direction of image is positive shooting, pass through calculate acquired image pupil
The occurrence and nose position of hole site line and the angle of horizontal direction are at a distance from face contour surrounding and each distance
Between ratio value obtain image face angle information.
The information of the user images is compared step 3 with the information of image in photo library;
The information of the face information of user images and face angle information and image in photo library is carried out the degree of approach to compare, face
Information comparison is specifically to compare to identify by adding in facial face position, compares registration, and be respectively compared the spy of face
Sign refers specifically to the registration comparison of eyes size, ear size, nose height, eyebrows bushed together, mouth size cases, facial angle
Degree information comparison is specifically to compare image in the pupil position line of acquired image and the angle and photo library of horizontal direction
The degree of closeness of the angle of the pupil position line and horizontal direction of personage, and compare nose position and face in two images and take turns
The degree of closeness of the wide ratio value between the distance of left and right up and down, five features registration is high, the pupil position of personage in two images
Set nose position and the upper and lower ratio between the distance of left and right of face contour in the angle and two images of line and horizontal direction
It is worth closer, the matching degree highest of two images, i.e. image at this time in photo library are the image most like with user, wherein
Face information is that user can voluntarily select setting with specific gravity shared by face angle information in comparison process, can also be write from memory
Recognize.
Wherein include star's photo of popular understanding in photo library, while further including the photo of historical personage, network expression
There are also cartoon character photo, one of image can have multiple pictures, corresponding different scene, such as a star has
Multiple pictures, corresponding all ages and classes stage, shooting angle, shooting posture, location information, the photo origin of photo library can be this
Ground, it is also possible to cloud acquisition or that two kinds of source modes combinations form.
Step 4 push photo library in the highest image of user images matching degree.
Push the facial face and the highest photo of face angle information degree of closeness in photo library with user images, default
Highest matching degree, while other the similar photos also stored are pushed, such as can be carried out according to the height of similarity degree
Sequence, so that user checks according to the height of similarity degree and is selectively shared.
The embodiment obtains the image with the complete five features of user first, then identifies institute by face recognition technology
The face position and characteristic value for obtaining image identify the face angle information of acquired image according to face position ratio, in turn
Obtain information of shooting angles, then compare the corresponding informance of image in the information identified respectively photo library, obtain with
The highest photo of user images matching degree finally pushes the photo with highest matching degree.
By this embodiment, user not only only matches five features when the matching photo most like with oneself
Similarity degree, further include the degree of closeness for comparing face shots angle, help user find out more accurately in photo library with
Oneself similar photo.
In addition, U.S. face processing is carried out to user images before the face information and face angle information of identification user images,
User adjusts the image to make oneself beautiful by U.S. face function, obtains customer satisfaction system image, then again to the five of user images
Official's information and face angle information identify, find again from photo library and the user images matching degree by U.S. face processing
Highest photo, by the way that the image of user is carried out U.S. face processing in advance, can help user search cross with U.S. face oneself
With the highest photo of degree, matching result can more be liked by user in this case.
In addition, increasing the shooting pose information of identification user images, i.e., in addition to comparing image in user images and photo library
Five features and face angle degree of closeness outside, it is also contemplated that whether the shooting posture of personage identical in two images, specifically
It is compared and character moulding is carried out linear processing, moves towards the comparison of registration height according to lines to identify and clap
The similarity degree for taking the photograph posture shoots this comparison factor of posture by increasing, and user is helped to find not only facial five features phase
Seemingly, face angle is close when shooting, photo also identical with oneself shooting posture, so that matching result is more accurate and is full of
Entertaining, as soon as example, user put the POSE to thumb up, match it is similar with user's face, shoot when face angle connect
The all identical photo of moulding that close and while shooting puts, five features, shooting angle, the registration for shooting three information of posture are got over
It is high, it is believed that photo is more similar.
In addition, increasing gender information and/or the age information of identification user images, i.e., in addition to comparing user images and photo
In library other than the five features of image, the degree of closeness of face angle, shooting pose information, it is also contemplated that compare user and photo library
Image in personage gender it is whether identical and/or whether the age is wanted to approach, gender particular by user in image hair
Length and/or the whether outstanding judgement of Adam's apple, in general, the hair of user is long and/or will provide the user without Adam's apple and be
The judging result of women, conversely, the age is the facial wrinkles by user in image by the judging result that this is male is provided
And/or the heavy degree in canthus and/or face skin situation identify, wherein facial wrinkles particular by blee uniform journey
For degree to identify, blee is more uneven, provides age bigger recognition result, the heavy degree in canthus is particular by circumference of eyes skin
The uniformity of color identifies, face skin is identified by the light levels of blee and the uniformity coefficient at each position,
In general, blee is brighter, uniform, age smaller recognition result is provided, otherwise provides age bigger identification knot
Fruit can help user to find not only with similar image, can further look for by increasing identification gender and age information
Similar photo that is identical to gender, being of the similar age, is defined as the high photo of cohesion, is the photo with high cohesion, parent
Density is to consider the gender of personage and age in two images on the basis of similarity, it is however generally that, with high similarity
On the basis of, if gender is identical and/or is of the similar age, then it is assumed that be the photo with high cohesion, identify gender by increasing
With the two factors of age, user can be helped to find most intimate similar photo that is identical as oneself gender, being of the similar age, than
Photo similar with oneself has been found as some user has passed through five features, face angle and shooting pose information, but
It is intended to further to find and oneself be the same sex and the age differs in a small range of image, gender can be increased at this time
With two factors of age, user is helped to realize the purpose.
In addition, increasing location information when identification user images obtain, i.e., in the five features of two images of comparison, facial angle
Other than degree, shooting posture, gender and age information, image in the position and photo library when also being obtained by comparing user images
The location tags of corresponding personage, find the image being closely located to, geographical location between the two is closer, it is believed that the two it is intimate
Spend it is higher, it is on the contrary, it is believed that cohesion is lower, the location tags that image corresponds to personage in photo library can be personage birthplace or
Person is photograph taking, for example, some user wants to find and oneself has the shooting location of high similarity and photo also similar
Star's photo, so that it may increase and consider this comparison factor of status information, user is helped to search out target star's photo.
User can be helped to find the photo with high similarity and high cohesion from photo library through the foregoing embodiment,
Specifically, similarity is to consider face information, face angle information and shooting three factors of pose information, wherein specifically making
It oneself can be adjusted with the weight relationship of middle three and choice user, cohesion is to increase on the basis of similarity and consider property
The matching degree of other information, age information and location information, the higher registration the more intimate, wherein it is each compare the factor weight and
Choice is that user can be adjusted and select according to their own needs.
Fig. 2 is a kind of mobile terminal system module rack composition of the present invention.
The mobile terminal system includes display module 201, photographing module 202 and the bat for storing the photographing module
Take the photograph the image storage module 203 of picture, further includes:
User images obtain module 204, for obtaining user images by the photographing module or described image memory module;
User images obtain module 204 and obtain user images by photographing module 202, which includes at least the face of user,
Refer specifically to include user complete five features, five features refers specifically to eye, ear, nose, eyebrow, mouth feature, of the invention preferably real
It applies in example, which is camera possessed by smart phone itself, which can be immediately through camera shooting mould
Block shooting, it is also possible to user and has been saved in this ground either image of storage beyond the clouds before.
Data Analysis Services module 205 identifies for the information to the user images, the Data Analysis Services
Module includes face information identification module 208 and user's face angle recognition module 209;
Data Analysis Services module 205 identifies accessed user images information, is identified by face information identification module 208
Face information and the face angle information that face information acquisition is identified by by user's face angle recognition module 209, five
Official's information specifically refers to eyes size, ear size, nose height, eyebrows bushed together, mouth size cases in identification user images,
Angular relationship where plane where face angle information refers to the face of acquired image and photographic device between plane, including
Horizontal sextant angle and vertical angle, the acquisition of horizontal sextant angle are to obtain pupil position by first positioning face position, then count
Calculate the angle of the horizontal center line of pupil position line and photographic device and obtain, the acquisition of vertical angle be first pass through by
Face position positioning, obtains nose position, then calculates the nose position at a distance from face contour surrounding and each distance
Between proportionate relationship, and then vertical angle where obtaining the face of image where plane and photographic device between plane,
For example, in the case where the image got is all overlapped with the horizontal and vertical center line of filming apparatus, acquired image pupil
The angle of the horizontal center line of the line and photographic device of position be zero, it is believed that the shooting height that image is is flat bat, institute
Obtain the nose position of image with face contour at left and right sides of at a distance from ratio be 1:1, the distance of profile on nose position to face
It is 2:1 with ratio at a distance from facial bottom profiled, where plane where obtaining the face of image at this time and photographic device between plane
Vertical angle be also be zero, it is believed that the shooting direction of image is positive shooting, passes through the pupil position for calculating acquired image
The occurrence and nose position of line and the angle of horizontal direction are at a distance from face contour surrounding and between each distance
The face angle information of ratio value acquisition image.
Information comparison module 206, for the information of the user images to be compared with the information of image in photo library;
Information comparison module 206 by the face information of the user images recognized by face information identification module 208 and by with
The face angle information that family face angle identification module 209 recognizes and the information of image in photo library carry out the degree of approach and compare,
Face information comparison is specifically to compare to identify by adding in facial face position, compares registration, and be respectively compared face
Feature, refer specifically to eyes size, ear size, nose height, eyebrows bushed together, mouth size cases registration comparison, face
Portion's angle information module 209 includes pupil position computing module 210 and nose position computation module 211, and pupil position calculates mould
Block 210 is used to obtain pupil position and calculates the angle of the pupil position line and horizontal direction, nose position computation module
211, for obtaining nose position, calculate the ratio between the distance and each distance of the nose position and face contour surrounding
Relationship, comparing is specifically the people for comparing image in the pupil position line of acquired image and the angle and photo library of horizontal direction
The degree of closeness of the angle of the pupil position line and horizontal direction of object, and compare nose position and face contour in two images
The degree of closeness of ratio value between the distance of left and right up and down, five features registration is high, the pupil position of personage in two images
Nose position and the upper and lower ratio value between the distance of left and right of face contour in line and the angle and two images of horizontal direction
Closer, the matching degree highest of two images, i.e. image at this time in photo library are the image most like with user, wherein
Face information is that user can voluntarily select setting with specific gravity shared by face angle information in comparison process, can also be defaulted
's.
Wherein include star's photo of popular understanding in photo library, while further including the photo of historical personage, network expression
There are also cartoon character photo, one of image can have multiple pictures, corresponding different scene, such as a star has
Multiple pictures, corresponding all ages and classes stage, shooting angle, shooting posture, location information, the photo origin of photo library can be this
Ground, it is also possible to cloud acquisition or that two kinds of source modes combinations form.
Photo pushing module 207, for push in photo library with the highest image of user images matching degree;
Photo pushing module 207 pushes the facial face and face angle information degree of closeness highest in photo library with user images
Photo, default push highest matching degree, while other similar photos for also storing, such as can be according to similarity degree
Height be ranked up, so that user checks according to the height of similarity degree and is selectively shared.
In addition, Data Analysis Services module 205 further includes shooting gesture recognition module 212, gesture recognition module 212 is shot
By identifying, user profile determines the shooting pose information in the user images, carries out line particular by by character moulding
Itemization is handled and is compared, and is moved towards the comparison of registration height according to lines to identify the similarity degree of shooting posture, is led to
Increase shooting this comparison factor of posture is crossed, face angle phase when user being helped to find similar not only facial five features, shooting
It is close, photo also identical with oneself shooting posture, so that matching result is more accurate and is full of entertaining.
In addition, Data Analysis Services module 205 further includes Sexual discriminating module 213 and/or age identification module 214, property
The gender information of other judgment module 213 user images for identification, the user's figure for identification of Age estimation module 214
The age information of picture, gender are generally come particular by the whether outstanding judgement of hair length and/or Adam's apple of user in image
It says, the hair of user is long and/or will provide the user without Adam's apple as the judging result of women, conversely, this will be provided as male
Judging result, the age is that degree and/or face skin situation are sunk by the facial wrinkles and/or canthus of user in image to identify
, wherein facial wrinkles identify that blee is more uneven particular by the uniformity coefficient of blee, provide the age and get over
Big recognition result, the heavy degree in canthus identify that face skin is to pass through face particular by the uniformity of the circumference of eyes colour of skin
The light levels of the colour of skin and the uniformity coefficient at each position identify, it is however generally that, blee is brighter, uniform, provides year
Age smaller recognition result, on the contrary provide age bigger recognition result.
In addition, Data Analysis Services module 205 further includes age identification module 214, location identification module 215 is for identification
The geographical location information of the user images, i.e., identify the five features of two images, face angle, shooting posture, gender with
And other than age information, the location tags of the position personage corresponding with image in photo library when also being obtained by user images are sought
The image being closely located to is looked for, geographical location between the two is closer, it is believed that the cohesion of the two is higher, on the contrary, it is believed that intimate
Degree is lower, and image is corresponding in photo library
The location tags of personage can be the birthplace either photograph taking of personage, for example, some users want to find with from
Oneself has the shooting location of high similarity and photo also similar star's photo, so that it may increase and consider this ratio of status information
To the factor, user is helped to search out target star's photo.
Implementation through the invention, at least exist it is following the utility model has the advantages that
A kind of matched method of photo provided by the invention and mobile terminal, the user images got particular by identification
Then the face information and face angle information of middle user will be schemed in the face information of user and face angle information and photo library
The corresponding information of picture is compared, found out from photo library with the highest image of user images matching degree, by comparing
On the basis of face information, also increase and compare this comparison factor of face angle information, to help user smart from photo library
The photo most like with itself is found out quasi-ly.
Finally it should be noted that: the above embodiments are merely illustrative of the technical scheme of the present invention and are not intended to be limiting thereof;To the greatest extent
The present invention is described in detail with reference to preferred embodiments for pipe, it should be understood by those ordinary skilled in the art that: still
It can modify to a specific embodiment of the invention or some technical features can be equivalently replaced, without departing from this hair
The spirit of bright technical solution should all cover within the scope of the technical scheme claimed by the invention.
Claims (4)
1. a kind of photo matching process of mobile terminal includes the following steps: to obtain user images, the user images are at least wrapped
Include the face of user;Identify that the information of the user images, the information include, the face information of the user images and logical
Cross the user's face angle information of the face information acquisition;By the information of image in the information and photo library of the user images
It is compared;Push photo library in the highest image of user images matching degree;Identify the information of the user images
Before, it further include that the user images are carried out with U.S. face processing;Pass through the side of the face information acquisition user's face angle information
Method includes obtaining pupil position, calculating the angle of the pupil position line and horizontal direction;Nose position is obtained, institute is calculated
State proportionate relationship of the nose position at a distance from face contour surrounding and between each distance;By the information of the user images with
It further include the shooting pose information for identifying the user images before the information of image is compared in photo library, by identifying institute
It states user profile in user images and determines the shooting pose information;By image in the information and photo library of the user images
Information further includes identifying gender information and/or the age information of the user images before being compared;Identify the user images
Gender information include the hair length and/or Adam's apple position profile judged in the user images;Identify the user images
Age information include identifying the heavy degree of the facial wrinkles of the user images and/or canthus and/or face skin situation;By institute
State user images information be compared with the information of image in photo library before further include the geographical position for identifying the user images
Confidence breath;A kind of mobile terminal, including display module, photographing module and shooting picture for storing the photographing module
Image storage module, which is characterized in that further include that user images obtain module, for passing through the photographing module or described image
Memory module obtains user images;Data Analysis Services module identifies for the information to the user images, the number
It include face information identification module and user's face angle recognition module according to analysis and processing module;Information comparison module, being used for will
The information of the user images is compared with the information of image in photo library;Photo pushing module, for pushing in photo library
With the highest image of user images matching degree.
2. mobile terminal as described in claim 1, which is characterized in that the user's face angle information identification module includes,
For obtain pupil position and calculate the pupil position line and horizontal direction angle pupil position computing module, and
For obtaining nose position, proportionate relationship of the nose position at a distance from face contour surrounding and between each distance is calculated
Nose position computation module.
Mobile terminal as described in claim 1, which is characterized in that the Data Analysis Services module further includes that shooting posture is known
Other module, by identifying, user profile determines that the shooting posture is believed to the shooting gesture recognition module in the user images
Breath.
3. the mobile terminal as described in claim 1-3, which is characterized in that the Data Analysis Services module further includes that gender is sentenced
Disconnected module and/or age identification module, the gender information of Sexual discriminating module user images for identification, the year
The age information of age judgment module user images for identification.
4. the mobile terminal as described in claim 1-3, which is characterized in that the Data Analysis Services module further includes that position is known
Other module, the geographical location information of location identification module user images for identification.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711330944.5A CN110019890A (en) | 2017-12-13 | 2017-12-13 | A kind of photo matching process of mobile terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711330944.5A CN110019890A (en) | 2017-12-13 | 2017-12-13 | A kind of photo matching process of mobile terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110019890A true CN110019890A (en) | 2019-07-16 |
Family
ID=67186900
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711330944.5A Pending CN110019890A (en) | 2017-12-13 | 2017-12-13 | A kind of photo matching process of mobile terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110019890A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111401331A (en) * | 2020-04-27 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Face recognition method and device |
CN112562216A (en) * | 2020-12-01 | 2021-03-26 | 合肥大多数信息科技有限公司 | Intelligent charging machine for electric power business hall |
-
2017
- 2017-12-13 CN CN201711330944.5A patent/CN110019890A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111401331A (en) * | 2020-04-27 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Face recognition method and device |
WO2021218659A1 (en) * | 2020-04-27 | 2021-11-04 | 支付宝(杭州)信息技术有限公司 | Face recognition |
CN112562216A (en) * | 2020-12-01 | 2021-03-26 | 合肥大多数信息科技有限公司 | Intelligent charging machine for electric power business hall |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Dhall et al. | Emotiw 2016: Video and group-level emotion recognition challenges | |
US9330296B2 (en) | Recognizing entity interactions in visual media | |
CN105245786B (en) | A kind of self-timer method based on intelligent testing light, self-heterodyne system and camera terminal | |
KR102174595B1 (en) | System and method for identifying faces in unconstrained media | |
US10140515B1 (en) | Image recognition and classification techniques for selecting image and audio data | |
KR100714724B1 (en) | Apparatus and method for estimating facial pose, and face recognition system by the method | |
US20080298643A1 (en) | Composite person model from image collection | |
CN100438580C (en) | Method and apparatus for converting a photo to a caricature image | |
Black Jr et al. | Framework for performance evaluation of face recognition algorithms | |
WO2020151750A1 (en) | Image processing method and device | |
US9443307B2 (en) | Processing of images of a subject individual | |
CN110111418A (en) | Create the method, apparatus and electronic equipment of facial model | |
CN107278369A (en) | Method, device and the communication system of people finder | |
KR20150080728A (en) | Acquisition System and Method of Iris image for iris recognition by using facial component distance | |
CN106815309A (en) | A kind of image method for pushing, device and mobile terminal | |
US9116926B2 (en) | Sharing photos | |
KR20190004073A (en) | Authentication method and authentication apparatus using infrared ray(ir) image | |
WO2021027540A1 (en) | Lost person information matching method and apparatus, computer device, and storage medium | |
Lu et al. | Localize me anywhere, anytime: a multi-task point-retrieval approach | |
WO2021169754A1 (en) | Photographic composition prompting method and apparatus, storage medium, and electronic device | |
CN109697749A (en) | A kind of method and apparatus for three-dimensional modeling | |
CN110019890A (en) | A kind of photo matching process of mobile terminal | |
US11308313B2 (en) | Hybrid deep learning method for recognizing facial expressions | |
WO2023138403A1 (en) | Method and apparatus for determining trigger gesture, and device | |
CN105631404B (en) | The method and device that photo is clustered |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190716 |