CN110414452A - A kind of face searching method and system based on facial features location information - Google Patents
A kind of face searching method and system based on facial features location information Download PDFInfo
- Publication number
- CN110414452A CN110414452A CN201910704229.6A CN201910704229A CN110414452A CN 110414452 A CN110414452 A CN 110414452A CN 201910704229 A CN201910704229 A CN 201910704229A CN 110414452 A CN110414452 A CN 110414452A
- Authority
- CN
- China
- Prior art keywords
- facial
- feature point
- face
- reference picture
- feature
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of face searching methods and system based on facial features location information, the described method includes: determining at least two facial characteristics distances in the facial image searched for face, and current references are obtained according at least two facial characteristics distances and preset rules；Determine that reference picture concentrates reference value multiple reference pictures corresponding with the current references according to the current references；The facial image and multiple described reference pictures are successively compared to carry out face search, face search efficiency can be improved in the present invention.
Description
Technical field
The present invention relates to technical field of face recognition more particularly to a kind of face search based on facial features location information
Method and system.
Background technique
With the development of biological identification technology, pursuit especially to the good experience of noninductive payment, face recognition technology
Application scenarios gradually spreading out, such as recognition of face gate inhibition, the payment of brush face, ATM brush face is withdrawn the money, brush face registers.Currently, In
In the processing of the recognition of face of certain scenes, needs to search for the user that specified face shines in N number of face photograph in face database and return
Belong to, general way is that the face traversed in face database shines, and carries out contrast characteristic one by one and goes here and there, until similar value reaches preset essence
Degree requires, and completes search comparison process, and the efficiency of the algorithm is lower.Brush is used for example, having been reported that and falling gate on the ground in certain city
When face is current, since the accuracy rate and efficiency of face search are all not so good as people's will, lead to lockage low efficiency, seriously affected city
The experience of the people.
Summary of the invention
It is an object of the present invention to provide a kind of face searching methods based on facial features location information, to improve
Face search efficiency.It is another object of the present invention to provide a kind of, and the face based on facial features location information searches for system
System.It is yet a further object of the present invention to provide a kind of computer equipments.It can another purpose of the invention is that providing one kind
Read medium.
In order to reach the goals above, one aspect of the present invention discloses a kind of face search based on facial features location information
Method, which comprises
Determine at least two facial characteristics distances in the facial image searched for face, and according at least two faces
Portion's characteristic distance and preset rules obtain current references；
Determine that reference picture concentrates reference value multiple ginsengs corresponding with the current references according to the current references
Examine image；
The facial image and multiple described reference pictures are successively compared to carry out face search.
It preferably, further comprise determining at least two facial characteristics in the facial image searched for face apart from it
Before:
Determine fisrt feature point, second feature point, third feature point and the fourth feature point on multiple reference pictures；
The first facial feature reference distance between fisrt feature point and second feature point is obtained, third feature point and are obtained
The second facial characteristics reference distance between four characteristic points；
Preset rules are based on according to first facial feature reference distance and the second facial characteristics reference distance to be formed with reference to figure
The reference value of picture.
Preferably, at least two facial characteristics distances in the facial image that the determination is searched for face, and according to extremely
Few two facial characteristics distances and preset rules obtain current references and specifically include:
The fisrt feature point on the facial image, described second are determined by facial key features point detection technique
Characteristic point, third feature point and fourth feature point；
The first facial characteristic distance between the fisrt feature point and second feature point is obtained, it is special to obtain the third
The second facial characteristics distance between sign point and fourth feature point；
According between the first facial feature between distance and the second facial characteristics distance be based on preset rules obtain the people
The current references of face image.
Preferably, described to determine that reference picture concentrates reference value and the current references pair according to the current references
Multiple reference pictures answered specifically include:
Determine that reference picture concentrates multiple of difference within the scope of preset difference value between reference value and the current references
Reference picture.
Preferably, the method further includes according to the current references determine reference picture concentrate reference value with
Before multiple corresponding reference pictures of the current references:
All reference pictures that reference picture is concentrated are sorted from big to small or from small to large according to reference value.
Preferably, described successively to be compared the facial image and multiple described reference pictures to carry out face search
It specifically includes:
Obtain the feature string of the facial image；
Obtain the feature string of every reference picture in multiple described reference pictures；
If the feature string of the feature string of reference picture and the facial image reaches default similarity, reference picture and institute
It is identical to state facial image.
The invention also discloses a kind of face search system based on facial features location information, the system comprises:
Face image processing unit, for determine at least two facial characteristics in the facial image searched for face away from
From, and current references are obtained according at least two facial characteristics distances and preset rules；
Reference picture determination unit, for determining that reference picture concentrates reference value to work as with described according to the current references
Multiple corresponding reference pictures of preceding reference value；
Image comparing unit, for successively being compared the facial image and multiple described reference pictures to carry out people
Face search.
Preferably, further comprise:
Reference value determination unit, for determining the fisrt feature point on multiple reference pictures, second feature point, third feature
Point and fourth feature point, obtain the first facial feature reference distance between fisrt feature point and second feature point, obtain third spy
The second facial characteristics reference distance between sign point and fourth feature point, it is special according to first facial feature reference distance and the second face
Levy the reference value that reference distance forms reference picture based on preset rules.
Preferably, the face image processing unit is further used for determining institute by facial key features point detection technique
The fisrt feature point, second feature point, third feature point and the fourth feature point on facial image are stated, is obtained
First facial characteristic distance between the fisrt feature point and second feature point obtains the third feature point and described
The second facial characteristics distance between fourth feature point, according to distance between distance and the second facial characteristics between the first facial feature
The current references of the facial image are obtained based on preset rules.
Preferably, the reference picture determination unit is specifically used for determining that reference picture concentrates reference value and the current ginseng
Examine multiple reference pictures of the difference between value within the scope of preset difference value.
Preferably, the system further comprises reference picture sequencing unit, all ginsengs for concentrating reference picture
It examines image and sorts from big to small or from small to large according to reference value.
Preferably, described image comparing unit is specifically used for obtaining the feature string of the facial image, obtain it is described multiple
The feature string of every reference picture in reference picture, if the feature string of the feature string of reference picture and the facial image reaches pre-
If similarity, then reference picture is identical as the facial image.
The invention also discloses a kind of computer equipment, including memory, processor and storage are on a memory and can
The computer program run on a processor,
The processor realizes method as described above when executing described program.
The invention also discloses a kind of computer-readable mediums, are stored thereon with computer program,
The program realizes method as described above when being executed by processor.
The present invention can form reference value, reference value can by the face feature point of identification face in a reference image in advance
Facial characteristics distance is obtained by calculating the distance between two face feature points, is further obtained according at least two face feature points
It arrives.When carrying out face search, working as the facial image that the facial image same facial characteristic point searched for face is formed is determined
Preceding reference value concentrates the reference value of reference picture available approximately more with facial image by current references and reference picture
A reference picture reduces image and compares number, improve face search efficiency so as to reduce the range for carrying out face search.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 shows a kind of stream of one specific embodiment of face searching method based on facial features location information of the present invention
One of journey figure；
Fig. 2 shows a kind of streams of one specific embodiment of face searching method based on facial features location information of the present invention
The two of journey figure；
Fig. 3 shows a kind of stream of one specific embodiment of face searching method based on facial features location information of the present invention
The three of journey figure；
Fig. 4 shows a kind of stream of one specific embodiment of face searching method based on facial features location information of the present invention
The four of journey figure；
Fig. 5 shows a kind of stream of one specific embodiment of face searching method based on facial features location information of the present invention
The five of journey figure；
Fig. 6 shows a kind of stream of one specific embodiment of face searching method based on facial features location information of the present invention
The six of journey figure；
Fig. 7 shows a kind of stream of one specific embodiment of face searching method based on facial features location information of the present invention
The seven of journey figure；
Fig. 8 shows a kind of knot of one specific embodiment of face search system based on facial features location information of the present invention
One of composition；
Fig. 9 shows a kind of knot of one specific embodiment of face search system based on facial features location information of the present invention
The two of composition；
Figure 10 shows a kind of one specific embodiment of face search system based on facial features location information of the invention
The three of structure chart；
Figure 11 shows a kind of one specific embodiment of face search system based on facial features location information of the invention
The four of structure chart；
Figure 12 shows the structural schematic diagram for being suitable for the computer equipment for being used to realize the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
According to an aspect of the present invention, the face search based on facial features location information that present embodiment discloses a kind of
Method.As shown in Figure 1, in the present embodiment, which comprises
S100: at least two facial characteristics distances in the facial image searched for face are determined, and according at least two
The facial characteristics distance and preset rules obtain current references.
S200: determine that reference picture concentrates reference value corresponding with the current references more according to the current references
Open reference picture.
S300: the facial image and multiple described reference pictures are successively compared to carry out face search.
The present invention can form reference value, reference value can by the face feature point of identification face in a reference image in advance
Facial characteristics distance is obtained by calculating the distance between two face feature points, is further obtained according at least two face feature points
It arrives.When carrying out face search, working as the facial image that the facial image same facial characteristic point searched for face is formed is determined
Preceding reference value concentrates the reference value of reference picture available approximately more with facial image by current references and reference picture
A reference picture reduces image and compares number, improve face search efficiency so as to reduce the range for carrying out face search, from
And improve customer experience.
In a preferred embodiment, as shown in Fig. 2, the method further includes before S100:
S010: fisrt feature point, second feature point, third feature point and the fourth feature on multiple reference pictures are determined
Point.
S020: the first facial feature reference distance between fisrt feature point and second feature point is obtained, third feature is obtained
The second facial characteristics reference distance between point and fourth feature point.
S030: preset rules are based on according to first facial feature reference distance and the second facial characteristics reference distance and form ginseng
Examine the reference value of image.
Preferably, it can be identified to obtain the of face face to reference picture by facial key features point detection technique
One characteristic point, second feature point, third feature point and fourth feature point.Wherein, second feature point and third feature point can be same
One characteristic point.For example, in a specific example, fisrt feature point can be the one eye eyeball of people on the face, second feature point and
Third feature point is the another eyes on face, and third feature point can be mouth.Certainly, in other embodiments,
The characteristic point of different face faces can also be used in two characteristic points and third feature point, can also pass through more than two facial characteristics
Reference distance forms reference value, to improve the accuracy of the determining reference picture compared for image.
Preferably, first facial feature reference distance can be obtained by calculating the distance between two eyes, passes through calculating
The second facial characteristics reference distance can be obtained in the distance between another eyes and mouth, passes through first facial feature reference distance
The reference value of reference picture can be obtained based on preset rules with the second facial characteristics reference distance.
Preferably, forming reference value by preset rules can be by first facial feature reference distance and the second facial characteristics
Reference distance asks difference to obtain reference value, and by forming reference value previously according to face features point, which can be certain
The face characteristic on reference picture is indicated in degree, when carrying out face search, needs to be focused to find out from reference picture and to people
The identical target reference picture of facial image of face search, then the face characteristic of target reference picture is inevitable and to face search
The face characteristic of facial image is close, and the model of the reference picture of search is compared to can reduce by being pre-formed reference value
It encloses, reduces image and compare number, avoid meaningless image and compare, improve face search efficiency.
In a preferred embodiment, as shown in figure 3, the S100 is specific can include:
S110: the fisrt feature point on the facial image, institute are determined by facial key features point detection technique
State second feature point, third feature point and fourth feature point.
S120: obtaining the first facial characteristic distance between the fisrt feature point and second feature point, obtains described
The second facial characteristics distance between third feature point and fourth feature point.
S130: according between the first facial feature between distance and the second facial characteristics distance be based on preset rules obtain institute
State the current references of facial image.
When carrying out face image searching, need to determine identical as being chosen when forming reference picture reference value on facial image
Human face characteristic point, according to facial image identify fisrt feature point to fourth feature point, and be based on identical preset rules shape
At facial image current references corresponding with reference value, by being identically formed the face that mode obtains with reference picture reference value
The current references of image can obtain the standard for carrying out reference picture range shorter, and accurate positionin may include and facial image
The range of corresponding reference picture, improves comparison efficiency.
In a preferred embodiment, as shown in figure 4, the S200 is specific can include:
S210: determine that reference picture concentrates the difference between reference value and the current references within the scope of preset difference value
Multiple reference pictures.By be arranged preset difference value range, the range of the reference picture of comparison can be limited, when reference value with
When difference between current references exceeds preset difference value range, the face characteristic and facial image to be searched of reference picture are indicated
Face characteristic there are significant difference, do not have a possibility that identical, do not have and compare value, and the reference picture that difference is bigger
It is also same reason, so as to avoid the useless comparison process for the reference picture being not the same.
In a preferred embodiment, as shown in figure 5, the S300 is specific can include:
S310: the feature string of the facial image is obtained.
S320: the feature string of every reference picture in multiple described reference pictures is obtained.
S330: if the feature string of the feature string of reference picture and the facial image reaches default similarity, with reference to figure
As identical as the facial image.A reference picture is taken out i.e. from multiple reference pictures to be compared with facial image, if
It compares successfully, obtains reference picture identical with facial image, then face search terminates, if comparing failure, under further taking out
One reference picture is compared with facial image, repeat above step until obtain reference picture identical with facial image or
All reference picture comparisons finish, and exit face searching process.
Wherein, default similarity may include similar proportion and range parameter, for example, in a specific example, the likelihood ratio
Example may be selected 90%, and [- 0.01 ,+0.01] may be selected in range parameter, then presetting similarity is 90%-0.01 to 90%+0.01.
When the similarity of the feature string of facial image to be searched and the feature string of a reference picture compared 90%-0.01 extremely
When between 90%+0.01, judge that the reference picture of the comparison is identical as facial image to be searched, can Corresponding matching it is to be searched
Facial image identity information, the authentication for user.
In a preferred embodiment, as shown in fig. 6, the step of the method may additionally include before the S200:
S040: all reference pictures that reference picture is concentrated are sorted from big to small or from small to large according to reference value.It is logical
It crosses and is ranked up all reference pictures according to the size of reference value, when carrying out face search, can preferentially choose comparison reference
Value is compared with the most similar reference picture of current references, if not meeting default similarity, then compares most similar reference
Reference picture and facial image to be searched before and after image, until obtaining the ginseng for meeting default similarity with facial image to be searched
The difference of the reference value and current references of examining the reference picture of image or comparison has exceeded preset difference value range.
In a preferred embodiment, as shown in fig. 7, before the method may additionally include the S100:
S000: pass through image acquisition device facial image.Wherein, video camera, photograph can be used in image collecting device
The first-class equipment with image collecting function of machine, monitoring camera.
Based on same principle, the present embodiment also discloses a kind of face search system based on facial features location information.
As shown in figure 8, the system comprises face image processing unit 11, reference picture determination unit 12 and image comparing units 13.
Face image processing unit 11 for determine at least two facial characteristics in the facial image searched for face away from
From, and current references are obtained according at least two facial characteristics distances and preset rules.
Reference picture determination unit 12 be used for according to the current references determine reference picture concentrate reference value with it is described
Multiple corresponding reference pictures of current references.
Image comparing unit 13 is used to successively be compared the facial image and multiple described reference pictures to carry out
Face search.
In a preferred embodiment, as shown in figure 9, the system further comprises reference value determination unit 10.
Reference value determination unit 10 is used to determine fisrt feature point, second feature point, third spy on multiple reference pictures
Sign point and fourth feature point, obtain the first facial feature reference distance between fisrt feature point and second feature point, obtain third
The second facial characteristics reference distance between characteristic point and fourth feature point, according to first facial feature reference distance and the second face
Feature reference distance forms the reference value of reference picture based on preset rules.
Preferably, it can be identified to obtain the of face face to reference picture by facial key features point detection technique
One characteristic point, second feature point, third feature point and fourth feature point.Wherein, second feature point and third feature point can be same
One characteristic point.For example, in a specific example, fisrt feature point can be the one eye eyeball of people on the face, second feature point and
Third feature point is the another eyes on face, and third feature point can be mouth.Certainly, in other embodiments,
The characteristic point of different face faces can also be used in two characteristic points and third feature point, can also pass through more than two facial characteristics
Reference distance forms reference value, to improve the accuracy of the determining reference picture compared for image.
Preferably, first facial feature reference distance can be obtained by calculating the distance between two eyes, passes through calculating
The second facial characteristics reference distance can be obtained in the distance between another eyes and mouth, passes through first facial feature reference distance
The reference value of reference picture can be obtained based on preset rules with the second facial characteristics reference distance.
Preferably, forming reference value by preset rules can be by first facial feature reference distance and the second facial characteristics
Reference distance asks difference to obtain reference value, and by forming reference value previously according to face features point, which can be certain
The face characteristic on reference picture is indicated in degree, when carrying out face search, needs to be focused to find out from reference picture and to people
The identical target reference picture of facial image of face search, then the face characteristic of target reference picture is inevitable and to face search
The face characteristic of facial image is close, and the model of the reference picture of search is compared to can reduce by being pre-formed reference value
It encloses, reduces image and compare number, avoid meaningless image and compare, improve face search efficiency.
In a preferred embodiment, the face image processing unit 11 is further used for through facial key features point
Detection technique determines the fisrt feature point, second feature point, third feature point and institute on the facial image
Fourth feature point is stated, the first facial characteristic distance between the fisrt feature point and second feature point is obtained, is obtained described
The second facial characteristics distance between third feature point and fourth feature point, according to distance between the first facial feature and
Distance obtains the current references of the facial image based on preset rules between two facial characteristics.
When carrying out face image searching, need to determine identical as being chosen when forming reference picture reference value on facial image
Human face characteristic point, according to facial image identify fisrt feature point to fourth feature point, and be based on identical preset rules shape
At facial image current references corresponding with reference value, by being identically formed the face that mode obtains with reference picture reference value
The current references of image can obtain the standard for carrying out reference picture range shorter, and accurate positionin may include and facial image
The range of corresponding reference picture, improves comparison efficiency.
In a preferred embodiment, the reference picture determination unit 12 is specifically used for determining that reference picture concentrates reference
Multiple reference pictures of difference within the scope of preset difference value between value and the current references.
By the way that preset difference value range is arranged, the range of the reference picture of comparison can be limited, when reference value and currently
When difference between reference value exceeds preset difference value range, the face characteristic of reference picture and the people of facial image to be searched are indicated
Face feature does not have a possibility that identical there are significant difference, does not have and compares value, and the bigger reference picture of difference is also
Same reason, so as to avoid the useless comparison process for the reference picture being not the same.
In a preferred embodiment, as shown in Figure 10, the reference picture determination unit 12 further comprises with reference to figure
As sequencing unit 121.Reference picture sequencing unit 121 be used for all reference pictures for concentrating reference picture according to reference value from
It arrives greatly small or sorts from small to large.
By being ranked up all reference pictures according to the size of reference value, when carrying out face search, can preferentially select
It takes comparison reference value to be compared with the most similar reference picture of current references, if not meeting default similarity, then compares most
Reference picture and facial image to be searched before and after similar reference picture, until obtaining meeting with facial image to be searched default
The reference value of reference picture and the difference of current references of the reference picture or comparison of similarity have exceeded preset difference value range.
In a preferred embodiment, described image comparing unit 13 is specifically used for obtaining the feature of the facial image
String obtains the feature string of every reference picture in multiple described reference pictures, if the feature string of reference picture and the face figure
The feature string of picture reaches default similarity, then reference picture is identical as the facial image.
A reference picture is taken out i.e. from multiple reference pictures to be compared with facial image, if comparing successfully, is obtained
Reference picture identical with facial image, then face search terminate, if compare failure, further take out next reference picture with
Facial image is compared, and repeats above step until obtaining reference picture identical with facial image or all reference pictures ratio
To finishing, face searching process is exited.
Wherein, default similarity may include similar proportion and range parameter, for example, in a specific example, the likelihood ratio
Example may be selected 90%, and [- 0.01 ,+0.01] may be selected in range parameter, then presetting similarity is 90%-0.01 to 90%+0.01.
When the similarity of the feature string of facial image to be searched and the feature string of a reference picture compared 90%-0.01 extremely
When between 90%+0.01, judge that the reference picture of the comparison is identical as facial image to be searched, can Corresponding matching it is to be searched
Facial image identity information, the authentication for user.
In a preferred embodiment, as shown in figure 11, the system may also include image collecting device 00.Figure can be passed through
As acquisition device acquires facial image.Wherein, image collecting device can be used that video camera, camera, monitoring camera are first-class to be had
The equipment of image collecting function.
Since the principle that the system solves the problems, such as is similar with above method, the implementation of this system may refer to method
Implement, details are not described herein.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer equipment, specifically, computer is set
It is standby for example can for personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant,
Media player, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
In any equipment combination.
Computer equipment specifically includes memory, processor and storage on a memory simultaneously in a typical example
The computer program that can be run on a processor is realized when the processor executes described program and is held as described above by client
Capable method, alternatively, the processor realizes the method executed as described above by server when executing described program.
Below with reference to Figure 12, it illustrates the structures for the computer equipment 600 for being suitable for being used to realize the embodiment of the present application to show
It is intended to.
As shown in figure 12, computer equipment 600 includes central processing unit (CPU) 601, can be read-only according to being stored in
Program in memory (ROM) 602 is loaded into random access storage device (RAM) from storage section 608) program in 603
And execute various work appropriate and processing.In RAM603, also it is stored with system 600 and operates required various program sum numbers
According to.CPU601, ROM602 and RAM603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to
Bus 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal ultramagnifier (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.；
And including such as LAN card, the communications portion 609 of the network interface card of modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 606 as needed.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon
Computer program be mounted as needed such as storage section 608.
Particularly, according to an embodiment of the invention, may be implemented as computer above with reference to the process of flow chart description
Software program.For example, the embodiment of the present invention includes a kind of computer program product comprising be tangibly embodied in machine readable
Computer program on medium, the computer program include the program code for method shown in execution flow chart.At this
In the embodiment of sample, which can be downloaded and installed from network by communications portion 609, and/or from removable
Medium 611 is unloaded to be mounted.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when application.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The application can describe in the general context of computer-executable instructions executed by a computer, such as program
Module.Generally, program module includes routines performing specific tasks or implementing specific abstract data types, programs, objects, group
Part, data structure etc..The application can also be practiced in a distributed computing environment, in these distributed computing environments, by
Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with
In the local and remote computer storage media including storage equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The above description is only an example of the present application, is not intended to limit this application.For those skilled in the art
For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal
Replacement, improvement etc., should be included within the scope of the claims of this application.
Claims (14)
1. a kind of face searching method based on facial features location information, base are characterized in that, which comprises
Determine at least two facial characteristics distances in the facial image searched for face, and special according at least two faces
Sign distance and preset rules obtain current references；
According to the current references determine reference picture concentrate reference value it is corresponding with the current references multiple with reference to figure
Picture；
The facial image and multiple described reference pictures are successively compared to carry out face search.
2. face searching method according to claim 1, which is characterized in that further comprise being searched for determining to face
Before at least two facial characteristics distances in facial image:
Determine fisrt feature point, second feature point, third feature point and the fourth feature point on multiple reference pictures；
The first facial feature reference distance between fisrt feature point and second feature point is obtained, third feature point and the 4th spy are obtained
The second facial characteristics reference distance between sign point；
Reference picture is formed based on preset rules according to first facial feature reference distance and the second facial characteristics reference distance
Reference value.
3. face searching method according to claim 2, which is characterized in that the facial image that the determination is searched for face
In at least two facial characteristics distances, and obtain current reference according at least two facial characteristics distances and preset rules
Value specifically includes:
The fisrt feature point on the facial image, the second feature are determined by facial key features point detection technique
Point, third feature point and fourth feature point；
The first facial characteristic distance between the fisrt feature point and second feature point is obtained, the third feature point is obtained
The second facial characteristics distance between the fourth feature point；
According between the first facial feature between distance and the second facial characteristics distance be based on preset rules obtain the face figure
The current references of picture.
4. face searching method according to claim 1, which is characterized in that described determined according to the current references is joined
Multiple reference pictures corresponding with the current references of reference value in image set are examined to specifically include:
Determine multiple references that reference picture concentrates the difference between reference value and the current references within the scope of preset difference value
Image.
5. face searching method according to claim 1, which is characterized in that the method further includes according to
Before current references determine that reference picture concentrates reference value multiple reference pictures corresponding with the current references:
All reference pictures that reference picture is concentrated are sorted from big to small or from small to large according to reference value.
6. face searching method according to claim 1, which is characterized in that it is described by the facial image and it is described multiple
Reference picture is successively compared to carry out face search and specifically include:
Obtain the feature string of the facial image；
Obtain the feature string of every reference picture in multiple described reference pictures；
If the feature string of the feature string of reference picture and the facial image reaches default similarity, reference picture and the people
Face image is identical.
7. a kind of face search system based on facial features location information, base are characterized in that, the system comprises:
Face image processing unit, for determining at least two facial characteristics distances in the facial image searched for face, and
Current references are obtained according at least two facial characteristics distances and preset rules；
Reference picture determination unit, for determining that reference picture concentrates reference value and the current ginseng according to the current references
Examine multiple corresponding reference pictures of value；
Image comparing unit, for successively being compared the facial image with multiple described reference pictures to carry out face and search
Rope.
8. face search system according to claim 7, which is characterized in that further comprise:
Reference value determination unit, for determine the fisrt feature point on multiple reference pictures, second feature point, third feature point and
Fourth feature point obtains the first facial feature reference distance between fisrt feature point and second feature point, obtains third feature point
The second facial characteristics reference distance between fourth feature point is joined according to first facial feature reference distance and the second facial characteristics
Examine the reference value that distance forms reference picture based on preset rules.
9. face search system according to claim 8, which is characterized in that the face image processing unit is further used
In determining the fisrt feature point on the facial image, the second feature by facial key features point detection technique
Point, third feature point and fourth feature point, obtain first between the fisrt feature point and second feature point
Facial characteristics distance obtains the second facial characteristics distance between the third feature point and fourth feature point, according to described
Distance based on preset rules obtains the current reference of the facial image between distance and the second facial characteristics between first facial feature
Value.
10. face search system according to claim 7, which is characterized in that the reference picture determination unit is specifically used
In determining that reference picture concentrates multiple of difference within the scope of preset difference value between reference value and the current references with reference to figure
Picture.
11. face search system according to claim 7, which is characterized in that the system further comprises reference picture
Sequencing unit, all reference pictures for concentrating reference picture sort from big to small or from small to large according to reference value.
12. face search system according to claim 7, which is characterized in that described image comparing unit is specifically used for
To the feature string of the facial image, the feature string of every reference picture in multiple described reference pictures is obtained, if reference picture
Feature string and the feature string of the facial image reach default similarity, then reference picture is identical as the facial image.
13. a kind of computer equipment, can run on a memory and on a processor including memory, processor and storage
Computer program, which is characterized in that
The processor is realized when executing described program such as any one of claim 1-6 the method.
14. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that
It realizes when the program is executed by processor such as any one of claim 1-6 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910704229.6A CN110414452A (en) | 2019-07-31 | 2019-07-31 | A kind of face searching method and system based on facial features location information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910704229.6A CN110414452A (en) | 2019-07-31 | 2019-07-31 | A kind of face searching method and system based on facial features location information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110414452A true CN110414452A (en) | 2019-11-05 |
Family
ID=68364885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910704229.6A Pending CN110414452A (en) | 2019-07-31 | 2019-07-31 | A kind of face searching method and system based on facial features location information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110414452A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110879986A (en) * | 2019-11-21 | 2020-03-13 | 上海眼控科技股份有限公司 | Face recognition method, apparatus and computer-readable storage medium |
| CN111222448A (en) * | 2019-12-31 | 2020-06-02 | 深圳云天励飞技术有限公司 | Image conversion method and related products |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2672426A2 (en) * | 2012-06-04 | 2013-12-11 | Sony Mobile Communications AB | Security by z-face detection |
| CN104573634A (en) * | 2014-12-16 | 2015-04-29 | 苏州福丰科技有限公司 | Three-dimensional face recognition method |
| CN106203308A (en) * | 2016-06-30 | 2016-12-07 | 美的集团股份有限公司 | Face identification method and face identification device |
| CN109376596A (en) * | 2018-09-14 | 2019-02-22 | 广州杰赛科技股份有限公司 | Face matching process, device, equipment and storage medium |
| CN109753577A (en) * | 2018-12-29 | 2019-05-14 | 深圳云天励飞技术有限公司 | A method and related device for searching face |
-
2019
- 2019-07-31 CN CN201910704229.6A patent/CN110414452A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2672426A2 (en) * | 2012-06-04 | 2013-12-11 | Sony Mobile Communications AB | Security by z-face detection |
| CN104573634A (en) * | 2014-12-16 | 2015-04-29 | 苏州福丰科技有限公司 | Three-dimensional face recognition method |
| CN106203308A (en) * | 2016-06-30 | 2016-12-07 | 美的集团股份有限公司 | Face identification method and face identification device |
| CN109376596A (en) * | 2018-09-14 | 2019-02-22 | 广州杰赛科技股份有限公司 | Face matching process, device, equipment and storage medium |
| CN109753577A (en) * | 2018-12-29 | 2019-05-14 | 深圳云天励飞技术有限公司 | A method and related device for searching face |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110879986A (en) * | 2019-11-21 | 2020-03-13 | 上海眼控科技股份有限公司 | Face recognition method, apparatus and computer-readable storage medium |
| CN111222448A (en) * | 2019-12-31 | 2020-06-02 | 深圳云天励飞技术有限公司 | Image conversion method and related products |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112052789B (en) | Face recognition method and device, electronic equipment and storage medium | |
| CN113255694B (en) | Training image feature extraction model and method and device for extracting image features | |
| CN107291945B (en) | High-precision clothing image retrieval method and system based on visual attention model | |
| CN105468742B (en) | The recognition methods of malice order and device | |
| CN112101437A (en) | Fine-grained classification model processing method based on image detection and related equipment thereof | |
| CN109671103A (en) | Method for tracking target and device | |
| CN108460681A (en) | A kind of risk management and control method and device | |
| CN109711440A (en) | A kind of data exception detection method and device | |
| TW201833851A (en) | Risk control event automatic processing method and apparatus | |
| CN108205580A (en) | A kind of image search method, device and computer readable storage medium | |
| CN113065614A (en) | Training method of classification model and method for classifying target object | |
| CN108875487A (en) | Pedestrian is identified the training of network again and is identified again based on its pedestrian | |
| CN112395390A (en) | Training corpus generation method of intention recognition model and related equipment thereof | |
| US20220122343A1 (en) | Image feature extraction and network training method, apparatus, and device | |
| CN110414452A (en) | A kind of face searching method and system based on facial features location information | |
| CN106910101A (en) | Colony's wash sale recognition methods and device | |
| CN113902898A (en) | Training of target detection model, target detection method, device, equipment and medium | |
| CN111598713B (en) | Cluster recognition method and device based on similarity weight updating and electronic equipment | |
| CN109753577A (en) | A method and related device for searching face | |
| CN108460038A (en) | Rule matching method and its equipment | |
| CN110046278A (en) | Video classification methods, device, terminal device and storage medium | |
| CN107315984A (en) | A kind of method and device of pedestrian retrieval | |
| WO2023124869A1 (en) | Liveness detection method, device and apparatus, and storage medium | |
| CN110188798A (en) | A kind of object classification method and model training method and device | |
| CN110456921A (en) | Predict the method and device of user's keyboard operation behavior |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191105 |
|
| RJ01 | Rejection of invention patent application after publication |