CN109034139A - Face identification method, device, storage medium and electronic equipment - Google Patents
Face identification method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN109034139A CN109034139A CN201811065714.5A CN201811065714A CN109034139A CN 109034139 A CN109034139 A CN 109034139A CN 201811065714 A CN201811065714 A CN 201811065714A CN 109034139 A CN109034139 A CN 109034139A
- Authority
- CN
- China
- Prior art keywords
- facial image
- grid
- grid group
- face
- group
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of face identification method, device, storage medium and electronic equipment.Method includes the following steps: facial image to be identified is converted into standard picture；The standard picture is divided into multiple grid subregions；Root is by multiple grid sub-zone dividing at multiple groups grid group；Feature extraction is carried out to multiple grid subregions of each grid group, to obtain the fisrt feature data of corresponding organic region；Multiple facial images to be selected are retrieved from database according to fisrt feature data, wherein, each fisrt feature data correspond at least one facial image to be selected, and the matching degree of the second feature information of the correspondence grid group of at least one facial image to be selected and the fisrt feature data is greater than preset value；By each grid group of multiple facial images to be selected, grid group corresponding with facial image to be identified carries out characteristic matching respectively, to select target facial image from multiple facial image to be selected.
Description
Technical field
This application involves technical field of face recognition, in particular to a kind of face identification method, device, storage medium and electricity
Sub- equipment.
Background technique
In the prior art, it needs to carry out the face images in facial image to be identified and database when recognition of face
Complete contrast, low efficiency.
Therefore, the prior art is defective, needs to improve.
Summary of the invention
The embodiment of the present application provides a kind of face identification method, device, storage medium and electronic equipment, can be with recognition of face
Efficiency.
The embodiment of the present application provides a kind of face identification method, comprising the following steps:
Facial image to be identified is converted into the standard picture of normal size, the boundary line of the standard picture is square
Shape, and the rectangle is the maximum boundary rectangle of the facial contour line in the standard picture；
The standard picture is divided into multiple equal-sized grid subregions；
According to the distribution of each organic region of face by multiple grid sub-zone dividing at multiple groups grid group；
Feature extraction is carried out to multiple grid subregions of each grid group, to obtain the first of corresponding organic region
Characteristic；
Multiple facial images to be selected are retrieved from database according to the fisrt feature data, wherein each described
One characteristic corresponds at least one facial image to be selected, and the second of the correspondence grid group of at least one facial image to be selected
The matching degree of characteristic information and the fisrt feature data is greater than preset value；
By each grid group of the multiple facial image to be selected counterparty with the facial image to be identified respectively
Lattice group carries out characteristic matching, to select target facial image from multiple facial image to be selected.
In face identification method of the present invention, the distribution of each organic region according to face will be multiple
Grid sub-zone dividing at the step of multiple groups grid group include: by multiple grid sub-zone dividings of facial image to be identified at
Left face grid group, right face grid group, forehead grid group, ear grid group, glasses grid group, eyebrow grid group, mouth grid group
And nose grid group.
In face identification method of the present invention, multiple grid subregions to each grid group are carried out
Feature extraction, to include: the step of obtaining the fisrt feature data of corresponding organic region
Each party's grid area of each grid group is identified to obtain the colouring information of the grid group, profile information
And dimension information.
In face identification method of the present invention, each grid component by the multiple facial image to be selected
Characteristic matching is not carried out with the corresponding grid group of the facial image to be identified, to select from multiple facial image to be selected
The step of target face figure includes:
By each grid group of the multiple facial image to be selected, grid group corresponding with the facial image is carried out respectively
Characteristic matching filters out at least one most first face figure of matched grid group from the multiple facial image to be selected
Picture；
If the quantity of at least one first facial image is one, using first facial image as target face figure
Picture；
If the quantity of at least one first facial image be it is multiple, according to default weight equation from multiple first
Target facial image is filtered out in facial image.
In the face identification method of some embodiments of the invention, the default weight equation is Y=A1B1+A2B2+
A3B3+...+AnBn, wherein A1, A2, A3...An are respectively the matching degree of a grid group, and B1, B2, B3...Bn are respectively couple
Answer the weight coefficient of grid group.
A kind of face identification device, comprising:
Conversion module, for facial image to be identified to be converted into the standard picture of normal size, the standard picture
Boundary line be rectangle, and the rectangle be the standard picture in facial contour line maximum boundary rectangle；
First division module, for the standard picture to be divided into multiple equal-sized grid subregions；
Second division module, for according to the distribution of each organic region of face by multiple grid sub-zone dividing at
Multiple groups grid group；
Extraction module carries out feature extraction for multiple grid subregions to each grid group, to be corresponded to
The fisrt feature data of organic region；
Retrieval module, for retrieving multiple facial images to be selected from database according to the fisrt feature data,
In, each fisrt feature data correspond at least one facial image to be selected, and pair of at least one facial image to be selected
The matching degree of the second feature information and the fisrt feature data of answering grid group is greater than preset value；
Selecting module, for by each grid group of the multiple facial image to be selected respectively with the face to be identified
The correspondence grid group of image carries out characteristic matching, to select target facial image from multiple facial image to be selected.
In face identification device of the present invention, first division module is used for facial image to be identified
Multiple grid sub-zone dividings are at left face grid group, right face grid group, forehead grid group, ear grid group, glasses grid group, eyebrow
Cant lattice group, mouth grid group and nose grid group.
In face identification device of the present invention, the extraction module is used for each grid to the facial image
Group is identified to obtain the colouring information of the grid group, profile information and dimension information.
A kind of storage medium is stored with computer program in the storage medium, when the computer program is in computer
When upper operation, so that the computer executes method described in any of the above embodiments.
A kind of electronic equipment, including processor and memory are stored with computer program, the processing in the memory
Device is by calling the computer program stored in the memory, for executing any of the above-described method.
From the foregoing, it will be observed that facial image to be identified by being converted into the standard picture of normal size, the mark by the present invention
The boundary line of quasi- image is rectangle, and the rectangle is the maximum boundary rectangle of the facial contour line in the standard picture；By the mark
Quasi- image is divided into multiple equal-sized grid subregions；According to the distribution of each organic region of face by multiple grid
Sub-zone dividing is at multiple groups grid group；Feature extraction is carried out to multiple grid subregions of each grid group, to obtain pair
Answer the fisrt feature data of organic region；Multiple face figures to be selected are retrieved from database according to the fisrt feature data
Picture, wherein each fisrt feature data correspond at least one facial image to be selected, and at least one facial image to be selected
Correspondence grid group second feature information and the fisrt feature data matching degree be greater than preset value；By the multiple wait choose
Each grid group of face image carries out characteristic matching with the corresponding grid group of the facial image to be identified respectively, with more from this
Target facial image is selected in a facial image to be selected.To realize that fast face identifies, due to not having to all numbers of face
It is compared one by one according to all features of the face images in library, substantially increases recognition efficiency.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described.It should be evident that the drawings in the following description are only some examples of the present application, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is recognition of face flow diagram provided by the embodiments of the present application.
Fig. 2 is the structural schematic diagram of face identification device provided by the embodiments of the present application.
Fig. 3 is the structural schematic diagram of electronic equipment provided by the embodiments of the present application.
Specific embodiment
Presently filed embodiment is described below in detail, the example of the embodiment is shown in the accompanying drawings, wherein from beginning
Same or similar element or element with the same or similar functions are indicated to same or similar label eventually.Below by ginseng
The embodiment for examining attached drawing description is exemplary, and is only used for explaining the application, and should not be understood as the limitation to the application.
In the description of the present application, it is to be understood that term " center ", " longitudinal direction ", " transverse direction ", " length ", " width ",
" thickness ", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside", " up time
The orientation or positional relationship of the instructions such as needle ", " counterclockwise " is to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of
It describes the application and simplifies description, rather than the device or element of indication or suggestion meaning must have a particular orientation, with spy
Fixed orientation construction and operation, therefore should not be understood as the limitation to the application.In addition, term " first ", " second " are only used for
Purpose is described, relative importance is not understood to indicate or imply or implicitly indicates the quantity of indicated technical characteristic.
" first " is defined as a result, the feature of " second " can explicitly or implicitly include one or more feature.?
In the description of the present application, the meaning of " plurality " is two or more, unless otherwise specifically defined.
In the description of the present application, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected or can mutually communicate；It can be directly connected, it can also be by between intermediary
It connects connected, can be the connection inside two elements or the interaction relationship of two elements.For the ordinary skill of this field
For personnel, the concrete meaning of above-mentioned term in this application can be understood as the case may be.
In this application unless specifically defined or limited otherwise, fisrt feature second feature "upper" or "lower"
It may include that the first and second features directly contact, also may include that the first and second features are not direct contacts but pass through it
Between other characterisation contact.Moreover, fisrt feature includes the first spy above the second feature " above ", " above " and " above "
Sign is right above second feature and oblique upper, or is merely representative of first feature horizontal height higher than second feature.Fisrt feature exists
Second feature " under ", " lower section " and " following " include that fisrt feature is directly below and diagonally below the second feature, or is merely representative of
First feature horizontal height is less than second feature.
Following disclosure provides many different embodiments or example is used to realize the different structure of the application.In order to
Simplify disclosure herein, hereinafter the component of specific examples and setting are described.Certainly, they are merely examples, and
And purpose does not lie in limitation the application.In addition, the application can in different examples repeat reference numerals and/or reference letter,
This repetition is for purposes of simplicity and clarity, itself not indicate between discussed various embodiments and/or setting
Relationship.In addition, this application provides various specific techniques and material example, but those of ordinary skill in the art can be with
Recognize the application of other techniques and/or the use of other materials.
The description and claims of this application and term " first " in above-mentioned attached drawing, " second ", " third " etc.
(if present) is to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be appreciated that this
The object of sample description is interchangeable under appropriate circumstances.In addition, term " includes " and " having " and their any deformation, meaning
Figure, which is to cover, non-exclusive includes.For example, containing the process, method of series of steps or containing a series of modules or list
The device of member, terminal, system those of are not necessarily limited to be clearly listed step or module or unit, can also include unclear
The step of ground is listed or module or unit also may include its intrinsic for these process, methods, device, terminal or system
Its step or module or unit.
It is the flow chart of the face identification method in some embodiments of the invention with reference to Fig. 1, Fig. 1.This method is applied to hand
In the electronic equipments such as machine, IPAD, the face identification method, comprising the following steps:
S101, the standard picture that facial image to be identified is converted into normal size, the boundary line of the standard picture
For rectangle, and the rectangle is the maximum boundary rectangle of the facial contour line in the standard picture.
After getting facial image to be identified, the facial contour line in facial image is first obtained, the people is then drawn
The maximum boundary rectangle of face contour line, obtains the first facial image, then zooms in and out first facial image, by this first
The size of facial image is adjusted to the size of standard, obtains standard picture.
S102, the standard picture is divided into multiple equal-sized grid subregions.
The standard picture is divided using a plurality of reference line parallel with the long side of the maximum boundary rectangle and broadside respectively
At multiple equal-sized grid subregions.Specifically, the number of party's grid area is preset value, for example, using 100*150
Format.
S103, according to the distribution of each organic region of face by multiple grid sub-zone dividing at multiple groups grid group.
According to the contour line of each organ select the grid group of the organ corresponding to all grid subregions, wherein
The grid subregion within grid subregion area defined where the contour line of the organ belongs to the grid of the organ
The grid subregion of group.In particular, by multiple grid sub-zone dividings of facial image to be identified at left face grid group, the right side
Face grid group, forehead grid group, ear grid group, glasses grid group, eyebrow grid group, mouth grid group and nose grid
Group.
S104, feature extraction is carried out to multiple grid subregions of each grid group, to obtain corresponding organic region
Fisrt feature data.
When being identified to each grid group, it can be identified using face recognition algorithms in the prior art, wherein
The fisrt feature data include but is not limited to following characteristics information: colouring information, profile information and dimension information etc..When
So, it is possible to understand that ground in some embodiments, can be according to the age information of people to each grid group in order to improve accuracy
Characteristic information carry out small optimization.
S105, multiple facial images to be selected are retrieved from database according to the fisrt feature data, wherein Mei Yisuo
It states fisrt feature data and corresponds at least one facial image to be selected, and the correspondence grid group of at least one facial image to be selected
The matching degree of second feature information and the fisrt feature data is greater than preset value.
In this step, it is only necessary to by other grid groups not compared of facial image to be selected respectively with the facial image
Grid group is compared, and efficiency can be improved.
S106, by each grid group of the multiple facial image to be selected pair with the facial image to be identified respectively
Grid group is answered to carry out characteristic matching, to select target facial image from multiple facial image to be selected.
Wherein, it is different for the threshold value of different grid groups being set, and the feature of different grid groups is mainly withdrawn deposit not
Same aspect.For example, for length difference away from relatively small, the main distinction is width for eye areas.And for nose and
Speech, mainly withdraws deposit in the height of nose and width etc..Therefore, different threshold values to be used using different grid groups.
In some embodiments, step S106 includes following sub-step:
S1061, by each grid group of the multiple facial image to be selected respectively with the corresponding grid of the facial image
Group carries out characteristic matching, and it is the first that at least one of matched grid group at most is filtered out from the multiple facial image to be selected
Face image；If the quantity of S1062, at least one first facial image is one, using first facial image as target
Facial image；If the quantity of S1063, at least one first facial image be it is multiple, according to default weight equation from this
Target facial image is filtered out in multiple first facial images.The default weight equation is Y=A1B1+A2B2+A3B3+...+
AnBn, wherein A1, A2, A3...An are respectively the matching degree of a grid group, and B1, B2, B3...Bn are respectively corresponding grid group
Weight coefficient.And the target facial image is that Y value is maximum in multiple first facial image.
From the foregoing, it will be observed that facial image to be identified by being converted into the standard picture of normal size, the mark by the present invention
The boundary line of quasi- image is rectangle, and the rectangle is the maximum boundary rectangle of the facial contour line in the standard picture；By the mark
Quasi- image is divided into multiple equal-sized grid subregions；According to the distribution of each organic region of face by multiple grid
Sub-zone dividing is at multiple groups grid group；Feature extraction is carried out to multiple grid subregions of each grid group, to obtain pair
Answer the fisrt feature data of organic region；Multiple face figures to be selected are retrieved from database according to the fisrt feature data
Picture, wherein each fisrt feature data correspond at least one facial image to be selected, and at least one facial image to be selected
Correspondence grid group second feature information and the fisrt feature data matching degree be greater than preset value；By the multiple wait choose
Each grid group of face image carries out characteristic matching with the corresponding grid group of the facial image to be identified respectively, with more from this
Target facial image is selected in a facial image to be selected.To realize that fast face identifies, due to not having to all numbers of face
It is compared one by one according to all features of the face images in library, substantially increases recognition efficiency.
Referring to figure 2., Fig. 2 is the structure chart of the face identification device 200 in some embodiments of the invention.The recognition of face
Device, comprising:
Wherein, which is used to for facial image to be identified being converted into the standard picture of normal size, described
The boundary line of standard picture is rectangle, and the rectangle is the maximum boundary rectangle of the facial contour line in the standard picture.It is obtaining
After getting facial image to be identified, the facial contour line in facial image is first obtained, then draws the face contour line most
Big boundary rectangle obtains the first facial image, then zooms in and out first facial image, by the big of first facial image
The small size for being adjusted to standard, obtains standard picture.
Wherein, which is used to the standard picture being divided into multiple equal-sized grid subregions；
The standard picture is divided into using a plurality of reference line parallel with the long side of the maximum boundary rectangle and broadside respectively multiple big
Small equal grid subregion.Specifically, the number of party's grid area is preset value, for example, using the format of 100*150.
Wherein, which is used for multiple cage according to the distribution of each organic region of face
Region division is at multiple groups grid group；According to the contour line of each organ select the grid group of the organ corresponding to all grids
Subregion, wherein the grid subregion within grid subregion area defined where the contour line of the organ belongs to
The grid subregion of the grid group of the organ.In particular, by multiple grid sub-zone dividings of facial image to be identified at
Left face grid group, right face grid group, forehead grid group, ear grid group, glasses grid group, eyebrow grid group, mouth grid group
And nose grid group.
Wherein, which is used to carry out feature extraction to multiple grid subregions of each grid group, with
Obtain the fisrt feature data of corresponding organic region；When identifying to each grid group, people in the prior art can be used
Face recognizer is identified, wherein the fisrt feature data include but is not limited to following characteristics information: colouring information, wheel
Wide information and dimension information etc..It will of course be understood that ground in some embodiments, can be according to people in order to improve accuracy
Age information small optimization is carried out to the characteristic information of each grid group.
Wherein, the retrieval module 205 is multiple wait choose for being retrieved from database according to the fisrt feature data
Face image, wherein each fisrt feature data correspond at least one facial image to be selected, and at least one face to be selected
The second feature information of the correspondence grid group of image and the matching degree of the fisrt feature data are greater than preset value；Only needing will be to be selected
Other grid groups not compared of facial image are compared with the grid group of the facial image respectively, and effect can be improved
Rate.
Wherein, the selecting module 206 be used for by each grid group of the multiple facial image to be selected respectively with it is described to
The correspondence grid group of the facial image of identification carries out characteristic matching, to select target face figure from multiple facial image to be selected
Picture.
Wherein, it is different for the threshold value of different grid groups being set, and the feature of different grid groups is mainly withdrawn deposit not
Same aspect.For example, for length difference away from relatively small, the main distinction is width for eye areas.And for nose and
Speech, mainly withdraws deposit in the height of nose and width etc..Therefore, different threshold values to be used using different grid groups.
In some embodiments, which is used for each grid component of the multiple facial image to be selected
Grid group not corresponding with the facial image carries out characteristic matching, filters out from the multiple facial image to be selected matched
At least one most first facial image of grid group；If the quantity of at least one first facial image is one, with
First facial image is target facial image；If the quantity of at least one first facial image be it is multiple, according to pre-
If weight equation filters out target facial image from multiple first facial image.The default weight equation is Y=A1B1+
A2B2+A3B3+...+AnBn, wherein A1, A2, A3...An are respectively the matching degree of a grid group, B1, B2, B3...Bn difference
For the weight coefficient of corresponding grid group.And the target facial image is that Y value is maximum in multiple first facial image.
From the foregoing, it will be observed that facial image to be identified by being converted into the standard picture of normal size, the mark by the present invention
The boundary line of quasi- image is rectangle, and the rectangle is the maximum boundary rectangle of the facial contour line in the standard picture；By the mark
Quasi- image is divided into multiple equal-sized grid subregions；According to the distribution of each organic region of face by multiple grid
Sub-zone dividing is at multiple groups grid group；Feature extraction is carried out to multiple grid subregions of each grid group, to obtain pair
Answer the fisrt feature data of organic region；Multiple face figures to be selected are retrieved from database according to the fisrt feature data
Picture, wherein each fisrt feature data correspond at least one facial image to be selected, and at least one facial image to be selected
Correspondence grid group second feature information and the fisrt feature data matching degree be greater than preset value；By the multiple wait choose
Each grid group of face image carries out characteristic matching with the corresponding grid group of the facial image to be identified respectively, with more from this
Target facial image is selected in a facial image to be selected.To realize that fast face identifies, due to not having to all numbers of face
It is compared one by one according to all features of the face images in library, substantially increases recognition efficiency.
Referring to figure 3., the embodiment of the present application also provides a kind of electronic equipment.The electronic equipment can be smart phone, put down
Plate apparatus such as computer.Such as show, electronic equipment 300 includes processor 301 and memory 302.Wherein, processor 301 and memory
302 are electrically connected.
Processor 301 is the control centre of terminal 300, utilizes each portion of various interfaces and the entire terminal of connection
Point, by running or calling the computer program being stored in memory 302, and the number that calling is stored in memory 302
According to, execute terminal various functions and processing data, thus to terminal carry out integral monitoring.
In the present embodiment, processor 301 in electronic equipment 300 can according to following step, by one or one with
On the corresponding instruction of process of computer program be loaded into memory 302, and run by processor 301 and be stored in storage
Computer program in device 302, to realize various functions: facial image to be identified is converted into the standard drawing of normal size
Picture, the boundary line of the standard picture is rectangle, and the rectangle is the external square of maximum of the facial contour line in the standard picture
Shape；The standard picture is divided into multiple equal-sized grid subregions；It will according to the distribution of each organic region of face
Multiple grid sub-zone dividing is at multiple groups grid group；Feature is carried out to multiple grid subregions of each grid group to mention
It takes, to obtain the fisrt feature data of corresponding organic region；It is retrieved from database according to the fisrt feature data multiple
Facial image to be selected, wherein each fisrt feature data correspond at least one facial image to be selected, and this at least one wait for
The second feature information of the correspondence grid group for face image of choosing and the matching degree of the fisrt feature data are greater than preset value；It will be described
Each grid group of multiple facial images to be selected carries out feature with the corresponding grid group of the facial image to be identified respectively
Match, to select target facial image from multiple facial image to be selected.
Memory 302 can be used for storing computer program and data.Include in the computer program that memory 302 stores
The instruction that can be executed in the processor.Computer program can form various functional modules.Processor 301 is stored in by calling
The computer program of memory 302, thereby executing various function application and data processing.
From the foregoing, it will be observed that facial image to be identified by being converted into the standard picture of normal size, the mark by the present invention
The boundary line of quasi- image is rectangle, and the rectangle is the maximum boundary rectangle of the facial contour line in the standard picture；By the mark
Quasi- image is divided into multiple equal-sized grid subregions；According to the distribution of each organic region of face by multiple grid
Sub-zone dividing is at multiple groups grid group；Feature extraction is carried out to multiple grid subregions of each grid group, to obtain pair
Answer the fisrt feature data of organic region；Multiple face figures to be selected are retrieved from database according to the fisrt feature data
Picture, wherein each fisrt feature data correspond at least one facial image to be selected, and at least one facial image to be selected
Correspondence grid group second feature information and the fisrt feature data matching degree be greater than preset value；By the multiple wait choose
Each grid group of face image carries out characteristic matching with the corresponding grid group of the facial image to be identified respectively, with more from this
Target facial image is selected in a facial image to be selected.To realize that fast face identifies, due to not having to all numbers of face
It is compared one by one according to all features of the face images in library, substantially increases recognition efficiency.
The embodiment of the present application also provides a kind of storage medium, is stored with computer program in the storage medium, when the calculating
When machine program is run on computers, which executes face identification method described in any of the above-described embodiment.
It should be noted that those of ordinary skill in the art will appreciate that whole in the various methods of above-described embodiment or
Part steps are relevant hardware can be instructed to complete by program, which can store in computer-readable storage medium
In matter, which be can include but is not limited to: read-only memory (ROM, Read Only Memory), random access memory
Device (RAM, Random Access Memory), disk or CD etc..
Above to big data safe encryption method, device, storage medium and electronic equipment provided by the embodiment of the present application
It is described in detail, specific examples are used herein to illustrate the principle and implementation manner of the present application, the above reality
The explanation for applying example is merely used to help understand the present processes and its core concept；Meanwhile for those skilled in the art,
According to the thought of the application, there will be changes in the specific implementation manner and application range, in conclusion in this specification
Hold the limitation that should not be construed as to the application.
Claims (10)
1. a kind of face identification method, which comprises the following steps:
Facial image to be identified is converted into the standard picture of normal size, the boundary line of the standard picture is rectangle, and
The rectangle is the maximum boundary rectangle of the facial contour line in the standard picture；
The standard picture is divided into multiple equal-sized grid subregions；
According to the distribution of each organic region of face by multiple grid sub-zone dividing at multiple groups grid group；
Feature extraction is carried out to multiple grid subregions of each grid group, to obtain the fisrt feature of corresponding organic region
Data；
Multiple facial images to be selected are retrieved from database according to the fisrt feature data, wherein each described first is special
Sign data correspond at least one facial image to be selected, and the second feature of the correspondence grid group of at least one facial image to be selected
The matching degree of information and the fisrt feature data is greater than preset value；
By each grid group of the multiple facial image to be selected respectively with the corresponding grid group of the facial image to be identified
Characteristic matching is carried out, to select target facial image from multiple facial image to be selected.
2. face identification method according to claim 1, which is characterized in that each organic region according to face
Multiple grid sub-zone dividing is included: by multiple grids of facial image to be identified at the step of multiple groups grid group by distribution
Sub-zone dividing is at left face grid group, right face grid group, forehead grid group, ear grid group, glasses grid group, eyebrow grid
Group, mouth grid group and nose grid group.
3. face identification method according to claim 1, which is characterized in that multiple sides to each grid group
Grid area carries out feature extraction, to include: the step of obtaining the fisrt feature data of corresponding organic region
Each party's grid area of each grid group is identified with obtain the colouring information of the grid group, profile information and
Dimension information.
4. face identification method according to claim 1, which is characterized in that described by the multiple facial image to be selected
Each grid group respectively with the corresponding grid group of the facial image to be identified carry out characteristic matching, with from multiple wait choose
The step of target face figure is selected in face image include:
By each grid group of the multiple facial image to be selected, grid group corresponding with the facial image carries out feature respectively
Matching filters out at least one most first facial image of matched grid group from the multiple facial image to be selected；
If the quantity of at least one first facial image is one, using first facial image as target facial image；
If the quantity of at least one first facial image be it is multiple, according to default weight equation from multiple first face
Target facial image is filtered out in image.
5. face identification method according to claim 4, which is characterized in that the default weight equation is Y=A1B1+
A2B2+A3B3+...+AnBn, wherein A1, A2, A3...An are respectively the matching degree of a grid group, B1, B2, B3...Bn difference
For the weight coefficient of corresponding grid group.
6. a kind of face identification device characterized by comprising
Conversion module, for facial image to be identified to be converted into the standard picture of normal size, the side of the standard picture
Boundary line is rectangle, and the rectangle is the maximum boundary rectangle of the facial contour line in the standard picture；
First division module, for the standard picture to be divided into multiple equal-sized grid subregions；
Second division module, for the distribution according to each organic region of face by multiple grid sub-zone dividing at multiple groups
Grid group；
Extraction module carries out feature extraction for multiple grid subregions to each grid group, to obtain corresponding organ
The fisrt feature data in region；
Retrieval module, for retrieving multiple facial images to be selected from database according to the fisrt feature data, wherein every
The one fisrt feature data correspond at least one facial image to be selected, and the correspondence grid of at least one facial image to be selected
The second feature information of group and the matching degree of the fisrt feature data are greater than preset value；
Selecting module, for by each grid group of the multiple facial image to be selected respectively with the facial image to be identified
Correspondence grid group carry out characteristic matching, to select target facial image from multiple facial image to be selected.
7. face identification device according to claim 6, which is characterized in that first division module is used for will be to be identified
Facial image multiple grid sub-zone dividings at left face grid group, right face grid group, forehead grid group, ear grid group,
Glasses grid group, eyebrow grid group, mouth grid group and nose grid group.
8. face identification device according to claim 6, which is characterized in that the extraction module is used for the face figure
Each grid group of picture is identified to obtain the colouring information of the grid group, profile information and dimension information.
9. a kind of storage medium, be stored with computer program in the storage medium, when the computer program on computers
When operation, so that the computer perform claim requires the described in any item methods of 1-5.
10. a kind of electronic equipment, including processor and memory, computer program, the processing are stored in the memory
Device requires any one of 1-5 method by calling the computer program stored in the memory, for perform claim.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811065714.5A CN109034139A (en) | 2018-09-13 | 2018-09-13 | Face identification method, device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811065714.5A CN109034139A (en) | 2018-09-13 | 2018-09-13 | Face identification method, device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109034139A true CN109034139A (en) | 2018-12-18 |
Family
ID=64621311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811065714.5A Withdrawn CN109034139A (en) | 2018-09-13 | 2018-09-13 | Face identification method, device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109034139A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034141A (en) * | 2018-09-17 | 2018-12-18 | 王虹 | Face identification method, device, storage medium and electronic equipment |
-
2018
- 2018-09-13 CN CN201811065714.5A patent/CN109034139A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034141A (en) * | 2018-09-17 | 2018-12-18 | 王虹 | Face identification method, device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110909611B (en) | Method and device for detecting attention area, readable storage medium and terminal equipment | |
| CN110197146B (en) | Face image analysis method based on deep learning, electronic device and storage medium | |
| CN108520222A (en) | Identification identification method, device, storage medium and electronic equipment based on face's intelligent scanning | |
| CN102667810B (en) | Face recognition in digital images | |
| CN106408037B (en) | Image recognition method and device | |
| CN111597884A (en) | Facial action unit identification method and device, electronic equipment and storage medium | |
| CN109800749A (en) | A kind of character recognition method and device | |
| CN110348511A (en) | A kind of picture reproduction detection method, system and electronic equipment | |
| CN106331254B (en) | A kind of protection processing method and processing device that mobile terminal falls | |
| CN108875797A (en) | A kind of method of determining image similarity, photograph album management method and relevant device | |
| CN112949750B (en) | Image classification method and computer readable storage medium | |
| CN110472460A (en) | Face image processing process and device | |
| CN109498037A (en) | The brain cognitive measurement method of feature and multiple dimension-reduction algorithm is extracted based on deep learning | |
| CN111178196B (en) | Cell classification method, device and equipment | |
| CN109711441A (en) | Image classification method, device, storage medium and electronic equipment | |
| CN115862113A (en) | Stranger abnormity identification method, device, equipment and storage medium | |
| CN109145812A (en) | Squatter building monitoring method and device | |
| CN111429409A (en) | Method and system for identifying glasses worn by person in image and storage medium thereof | |
| CN109034139A (en) | Face identification method, device, storage medium and electronic equipment | |
| CN109002804A (en) | Face identification method, device, storage medium and electronic equipment | |
| CN106651803B (en) | Method and device for identifying house type data | |
| CN108875713A (en) | Face identification method, device, storage medium and electronic equipment | |
| CN113870196A (en) | Image processing method, device, equipment and medium based on anchor point cutting graph | |
| CN109034141A (en) | Face identification method, device, storage medium and electronic equipment | |
| CN110766938B (en) | Road network topological structure construction method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181218 |