CN109684993A - A kind of face identification method based on nostril information, system and equipment - Google Patents
A kind of face identification method based on nostril information, system and equipment Download PDFInfo
- Publication number
- CN109684993A CN109684993A CN201811573339.5A CN201811573339A CN109684993A CN 109684993 A CN109684993 A CN 109684993A CN 201811573339 A CN201811573339 A CN 201811573339A CN 109684993 A CN109684993 A CN 109684993A
- Authority
- CN
- China
- Prior art keywords
- face
- nostril
- information
- facial image
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000001815 facial effect Effects 0.000 claims abstract description 140
- 239000000284 extract Substances 0.000 claims abstract description 19
- 238000004590 computer program Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 26
- 230000004044 response Effects 0.000 abstract description 4
- 230000008859 change Effects 0.000 description 12
- 230000006872 improvement Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000000241 respiratory effect Effects 0.000 description 4
- 230000029058 respiratory gaseous exchange Effects 0.000 description 4
- 230000008921 facial expression Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric 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
- G06V40/168—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
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of face identification methods based on nostril information, comprising: when response recognition of face instruction, detects in the coverage of camera with the presence or absence of face;When detecting the coverage of the camera, there are the preset quantity facial images for when face, obtaining the camera shooting, and extract the nostril information in each facial image;Vivo identification is carried out to the nostril information according to pre-stored nostril size threshold value, judges whether the facial image currently obtained is living body faces image;When the facial image is living body faces image, the face information of the facial image is extracted, face template according to the pre-stored data carries out recognition of face to the face information.Invention additionally discloses a kind of face identification systems based on nostril information and a kind of face recognition device based on nostril information.Using the embodiment of the present invention, the mistake that can effectively solve face identification system knows and rejection phenomenon, improves the reliability of face recognition technology.
Description
Technical field
The present invention relates to technical field of face recognition more particularly to a kind of face identification method based on nostril information, it is
System and equipment.
Background technique
With the development of technology, biological identification technology is more and more applied on intelligent terminal, such as the finger on mobile phone
Line identification technology, face recognition technology etc. are also gradually applied there are also some biological identification technologies, such as finger vein identification technology quilt
It is applied to access control system etc..With the continuous popularization in practical application, face identification system there are the problem of also gradually highlight.Than
Such as, face characteristic has changeability, such as various additives, the variation etc. of human face expression, and these change in practical applications all
It may cause face identification system and rejection phenomenon occur.Although embedded human face identifying system usually in typing face template,
By prompting the multi-faceted features of information collections face such as remote, close, new line, rotary head, be conducive to improve recognition success rate, but this is still not
It is enough to reduce the rejection probability as caused by face characteristic variation.In addition, there are also illegal persons to utilize the changeability because of face characteristic
And the principle of face identification system rejection is caused, face recognition technology is cracked using resources such as photo, videos, so as to cause people
The mistake of face identifying system is known, and the reliability of face recognition technology reduces.
Summary of the invention
The purpose of the embodiment of the present invention is that providing a kind of face identification method based on nostril information, system and equipment, energy
The mistake for effectively solving face identification system knows and rejection phenomenon, improves the reliability of face recognition technology.
To achieve the above object, the embodiment of the invention provides a kind of face identification methods based on nostril information, comprising:
When responding recognition of face instruction, detect in the coverage of camera with the presence or absence of face;
When the coverage for detecting the camera is opened there are the preset quantity that the camera is shot when face, is obtained
Facial image, and extract the nostril information in each facial image;
Vivo identification is carried out to the nostril information according to pre-stored nostril size threshold value, judges the institute currently obtained
State whether facial image is living body faces image;
When the facial image is living body faces image, the face information of the facial image is extracted, according to depositing in advance
The face template of storage carries out recognition of face to the face information.
Compared with prior art, the face identification method disclosed by the invention based on nostril information, first in response face
It when identification instruction, detects with the presence or absence of face in the coverage of camera, and when the coverage for detecting the camera
There are when face, obtain preset quantity facial image;Then the nostril information in each facial image is extracted, to described
Nostril information carries out vivo identification;Finally when the facial image is living body faces image, the people of the facial image is extracted
Face information, face template according to the pre-stored data carry out recognition of face to the face information.It solves in the prior art because of people
Face feature has changeability, may cause face identification system and rejection phenomenon occurs, while utilizing the changeability because of face characteristic
And the principle of face identification system rejection is caused, face recognition technology is cracked using resources such as photo, videos, so as to cause people
The problem of mistake of face identifying system is known, and the reliability of face recognition technology reduces, the mistake that can effectively solve face identification system are known
With rejection phenomenon, the reliability of face recognition technology is improved.
As an improvement of the above scheme, the nostril information extracted in each facial image, comprising:
The left nose hole length of left end in left nose hole to right end is extracted in each facial image, and extracts each institute
Left end is stated in facial image in right nostril to the right nostril length of right end;
The absolute value of the difference between the left nose hole length in each facial image is obtained, and obtains each people
The absolute value of the difference between right nostril length in face image;
Take the absolute value of the difference between the absolute value of the difference between the left nose hole length and the right nostril length
In maximum value be the nostril information.
As an improvement of the above scheme, described to live according to pre-stored nostril size threshold value to the nostril information
Body identification judges whether the facial image currently obtained is living body faces image, comprising:
Judge whether the nostril information is greater than pre-stored nostril size threshold value;
If so, determining that the facial image currently obtained is living body faces image;If it is not, then determine currently to obtain
The facial image is non-living body facial image.
As an improvement of the above scheme, the face template according to the pre-stored data carries out face knowledge to the face information
Not, comprising:
If the face information and the matching degree of the face template are greater than or equal to preset matching value, determine that face is known
Cheng Gong not;
If the face information and the matching degree of the face template are less than the preset matching value, recognition of face is determined
Failure.
As an improvement of the above scheme, the face information includes but is not limited to facial contour, eye contour, eye position
Information, nose profile and nose shape information.
To achieve the above object, the embodiment of the invention also provides a kind of face identification system based on nostril information, packets
It includes:
Face datection unit when for responding recognition of face instruction, detects in the coverage of camera with the presence or absence of people
Face;
Facial image acquiring unit, for when detecting the coverage of the camera there are when face, described in acquisition
The preset quantity facial image of camera shooting;
Nostril information acquisition unit, for extracting the nostril information in each facial image;
Vivo identification unit, for carrying out living body knowledge to the nostril information according to pre-stored nostril size threshold value
Not, whether the facial image that judgement currently obtains is living body faces image;
Face identification unit, for extracting the people of the facial image when the facial image is living body faces image
Face information, face template according to the pre-stored data carry out recognition of face to the face information.
Compared with prior art, the face identification system disclosed by the invention based on nostril information, first in Face datection
It when unit responds recognition of face instruction, detects with the presence or absence of face in the coverage of camera, and works as and detect the camera shooting
For the coverage of head there are when face, facial image acquiring unit obtains preset quantity facial image;Then nostril information obtains
Unit is taken to extract the nostril information in each facial image, vivo identification unit carries out living body knowledge to the nostril information
Not;Finally when the facial image is living body faces image, face identification unit extracts the face information of the facial image,
Face template according to the pre-stored data carries out recognition of face to the face information.It solves in the prior art because face characteristic has
There is changeability, may cause face identification system and rejection phenomenon occurs, while causing people using because of the changeability of face characteristic
The principle of face identifying system rejection, cracks face recognition technology using resources such as photo, videos, so as to cause recognition of face system
The problem of mistake of system is known, and the reliability of face recognition technology reduces, the mistake that can effectively solve face identification system is known and rejection is existing
As improving the reliability of face recognition technology.
As an improvement of the above scheme, the nostril information acquisition unit is specifically used for:
The left nose hole length of left end in left nose hole to right end is extracted in each facial image, and extracts each institute
Left end is stated in facial image in right nostril to the right nostril length of right end;
The absolute value of the difference between the left nose hole length in each facial image is obtained, and obtains each people
The absolute value of the difference between right nostril length in face image;
Take the absolute value of the difference between the absolute value of the difference between the left nose hole length and the right nostril length
In maximum value be the nostril information.
As an improvement of the above scheme, the vivo identification unit is specifically used for:
Judge whether the nostril information is greater than pre-stored nostril size threshold value;
If so, determining that the facial image currently obtained is living body faces image;If it is not, then determine currently to obtain
The facial image is non-living body facial image.
As an improvement of the above scheme, if the face identification unit is for the face information and the face template
Matching degree is greater than or equal to preset matching value, then determines recognition of face success;If the face information and the face template
Matching degree is less than the preset matching value, then determines that recognition of face fails;
The face information includes but is not limited to facial contour, eye contour, eye position information, nose profile and nose
Location information.
To achieve the above object, the embodiment of the present invention also provides a kind of face recognition device based on nostril information, including
Processor, memory and storage in the memory and are configured as the computer program executed by the processor, institute
State the recognition of face based on nostril information realized as described in above-mentioned any embodiment when processor executes the computer program
Method.
Detailed description of the invention
Fig. 1 is a kind of flow chart of face identification method based on nostril information provided in an embodiment of the present invention;
Fig. 2 is extraction nostril information in a kind of face identification method based on nostril information provided in an embodiment of the present invention
Flow chart;
Fig. 3 is a kind of structural block diagram of face identification system 10 based on nostril information provided in an embodiment of the present invention;
Fig. 4 is a kind of structural block diagram of face recognition device 20 based on nostril information provided in an 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.
Embodiment one
It is a kind of process of face identification method based on nostril information provided in an embodiment of the present invention referring to Fig. 1, Fig. 1
Figure;Include:
When S1, response recognition of face instruction, detect in the coverage of camera with the presence or absence of face;
S2, when detecting the coverage of the camera, there are the present counts for when face, obtaining the camera shooting
Amount facial image, and extract the nostril information in each facial image;
S3, vivo identification is carried out to the nostril information according to pre-stored nostril size threshold value, judges current obtain
The facial image whether be living body faces image;
S4, when the facial image be living body faces image when, the face information of the facial image is extracted, according to preparatory
The face template of storage carries out recognition of face to the face information.
It is worth noting that face information described in the embodiment of the present invention does not include nostril information, the face information packet
Include but be not limited to facial contour, eye contour, eye position information, nose profile and nose shape information.The present embodiment is mentioned
The face identification method based on nostril information supplied can execute realization by terminal device, and the terminal device can be hand
Machine, tablet computer or other terminal devices include camera in the terminal device, for acquiring image.
Specifically, first establishing face before the terminal device executes the face identification method based on nostril information
Template.During establishing the face template, the facial image of multiple users is acquired by the camera, it at this time can be with
Nostril size information is got from facial image, then it, can be by described during the camera acquires information
Display reminding information on terminal device, to guide user to carry out information collection.For example go out in the display screen of the terminal device
Existing one personage's frame that posture is shot for correcting user guides user to carry out correcting posture, while also can play voice or text
It prompts user to carry out correcting posture, to get the image that can effectively identify, and then extracts the face information and institute
Nostril size information is stated, the face template and the nostril size threshold value are obtained.
In one embodiment, the calculating process of the nostril size threshold value includes: to obtain multiple facial images, from each
Left end in user's left nose hole is extracted in the facial image while extracting each face to the left nose hole length of right end
In image in right nostril left end to right end right nostril length;The left nose hole length of every facial image is obtained at this time
With right nostril length, the absolute value of the difference between multiple left nose hole lengths is then obtained again, while it is long to obtain multiple right nostrils
The absolute value of difference between degree;It takes between the absolute value of the difference between the left nose hole length and the right nostril length
The minimization of the sum of absolute value of difference is the nostril size threshold value.Because user becomes due to nose can be with breathing in respiratory
Change, therefore in multiple facial images of the camera continuous acquisition, nostril size information is inconsistent, so as to obtain
State nostril size threshold value.
In another embodiment, the nostril size threshold value can be set to 0.
Specifically, in step sl, response recognition of face instruction, the recognition of face instruction can be user in payment or
Person unlocks the instruction issued when mobile phone.Preferably, instruction can be sent by when control centre is responsive to recognition of face instruction
To the camera, so as to whether there is face in the coverage of the camera detection camera, and it is anti-to will test result
It feeds the control centre.
Specifically, in step s 2, it is preferred that when detecting that the coverage of the camera there are when face, opens
Infrared light supply, so that on infrared light supply transmitting infrared ray to face.Specifically, infrared light supply can make the camera exist
Also relatively clear facial image can be got in dark surrounds, so as to avoid being difficult in dark surrounds carrying out recognition of face
The problem of.Preferably, the camera can be infrared camera, and the infrared light supply can be the infrared camera itself
The infrared ray that the infrared ray of transmitting or other structure light source issue, all within the scope of the present invention.
Specifically, obtaining the preset quantity facial image of camera shooting, it is preferred that the camera can be
It is continuously shot in short time, for example shoots 5 facial images in 3 seconds.Then in the process, in the facial image got because
User causes nostril to change in breathing, so as to according to the situation of change for judging user nostril to determine whether for living body.
Specifically, extracting the nostril information in each facial image after obtaining the facial image.Referring to fig. 2,
Fig. 2 is the flow chart that nostril information is extracted in a kind of face identification method based on nostril information provided in an embodiment of the present invention;
Include:
S21, the left nose hole length for extracting in each facial image left end in left nose hole to right end, and extract every
In one facial image in right nostril left end to right end right nostril length;
The absolute value of the difference between left nose hole length in S22, each facial image of acquisition, and obtain each institute
State the absolute value of the difference between the right nostril length in facial image;
S23, the exhausted of difference between the absolute value and the right nostril length of the difference between the left nose hole length is taken
It is the nostril information to the maximum value in value.
Specifically, in step s3, carrying out living body knowledge to the nostril information according to pre-stored nostril size threshold value
Not, whether the facial image that judgement currently obtains is living body faces image.Preferably, judge whether the nostril information is big
In pre-stored nostril size threshold value;If the nostril information is greater than pre-stored nostril size threshold value, determine current
The facial image obtained is living body faces image, and active user is living body;If the nostril information is less than or equal to preparatory
The nostril size threshold value of storage determines the facial image currently obtained then for non-living body facial image, and active user is non-
Living body, the facial image currently obtained may be that the camera is shot according to user picture.Pass through the situation of change in nostril
To determine whether being living body, the variation for solving human face expression causes face identification system that rejection phenomenon occurs, and solves simultaneously
Using the principle for causing face identification system rejection due to the changeability because of face characteristic, cracked using resources such as photo, videos
Face recognition technology, the problem of knowledge so as to cause the mistake of face identification system.
Specifically, the nostril information is no more than nostril size limit value, because the camera is continuous in a short time
Face is shot, therefore during user carries out recognition of face, the distance between user and the camera are remained unchanged, from
And the facial image that the camera is got is almost the same, and user is to be in the shooting process of the camera
Respiratory state can occur slight change so as to cause nostril size, but not be widely varied, therefore can pass through setting
One nostril size limit value excludes to lead to the camera shooting by mobile photo when the external world carries out recognition of face using photo
Head obtain to facial image in user nostril information be variation, so as to cause misrecognition the case where, can be improved people
The reliability of face identification technology.
Specifically, in step s 4, when the facial image is living body faces image, extracting the people of the facial image
Face information, face template according to the pre-stored data carry out recognition of face to the face information.Preferably, if the face information
It is greater than or equal to preset matching value with the matching degree of the face template, then determines recognition of face success;If the face information
It is less than the preset matching value with the matching degree of the face template, then determines that recognition of face fails.
When it is implemented, detecting in the coverage of camera first when responding recognition of face instruction with the presence or absence of people
Face, and there are when face, obtain preset quantity facial image when detecting the coverage of the camera;Then it extracts every
Nostril information in one facial image carries out vivo identification to the nostril information;Finally when the facial image is to live
When body facial image, the face information of the facial image is extracted, face template according to the pre-stored data is to the face information
Carry out recognition of face.
Compared with prior art, the face identification method disclosed by the invention based on nostril information, solves the prior art
It is middle because face characteristic has changeability, may cause face identification system and rejection phenomenon occur, while using because of face characteristic
Changeability and the principle for causing face identification system rejection, face recognition technology is cracked using resources such as photo, videos, thus
Cause the mistake of face identification system to be known, the problem of reliability of face recognition technology reduces, can effectively solve face identification system
Mistake know and rejection phenomenon, improve the reliability of face recognition technology.
Embodiment two
It is a kind of structure of face identification system 10 based on nostril information provided in an embodiment of the present invention referring to Fig. 3, Fig. 3
Block diagram;Include:
Face datection unit 11, when for responding recognition of face instruction, detecting in the coverage of camera whether there is
Face;
Facial image acquiring unit 12, for when detecting that the coverage of the camera there are when face, obtains institute
State the preset quantity facial image of camera shooting;
Nostril information acquisition unit 13, for extracting the nostril information in each facial image;
Vivo identification unit 14, for carrying out living body knowledge to the nostril information according to pre-stored nostril size threshold value
Not, whether the facial image that judgement currently obtains is living body faces image;
Face identification unit 15, for extracting the facial image when the facial image is living body faces image
Face information, face template according to the pre-stored data carry out recognition of face to the face information.
It is worth noting that face information described in the embodiment of the present invention does not include nostril information, the face information packet
Include but be not limited to facial contour, eye contour, eye position information, nose profile and nose shape information.The present embodiment is mentioned
The face identification system 10 based on nostril information supplied can be mobile phone, tablet computer or other terminal devices, described to be based on nose
It include camera in the face identification system 10 of hole information, for acquiring image.
Specifically, first establishing people before the face identification system 10 based on nostril information carries out the recognition of face
Face template.During establishing the face template, the facial image of multiple users is acquired by the camera, at this time may be used
It, then, can be by institute during the camera acquires information to get nostril size information from facial image
Display reminding information on the face identification system 10 based on nostril information is stated, to guide user to carry out information collection.Such as institute
Personage's frame that appearance one shoots posture for correcting user in the display screen of the face identification system 10 based on nostril information is stated to refer to
It quotes family and carries out correcting posture, while also can play voice or text prompt user progress correcting posture, to get
The image that can be identified of effect, and then extract the face information and the nostril size information, obtain the face template and
The nostril size threshold value.
In one embodiment, the calculating process of the nostril size threshold value includes: to obtain multiple facial images, from each
Left end in user's left nose hole is extracted in the facial image while extracting each face to the left nose hole length of right end
In image in right nostril left end to right end right nostril length;The left nose hole length of every facial image is obtained at this time
With right nostril length, the absolute value of the difference between multiple left nose hole lengths is then obtained again, while it is long to obtain multiple right nostrils
The absolute value of difference between degree;It takes between the absolute value of the difference between the left nose hole length and the right nostril length
The minimization of the sum of absolute value of difference is the nostril size threshold value.Because user becomes due to nose can be with breathing in respiratory
Change, therefore in multiple facial images of the camera continuous acquisition, nostril information not of uniform size, so as to obtain
State nostril size threshold value.
In another embodiment, the nostril size threshold value can be set to 0.
Specifically, the Face datection unit 11 responds recognition of face instruction, the recognition of face instruction can be user
The instruction issued when paying or unlocking mobile phone.It preferably, can be by being responsive to face in the Face datection unit 11
When identification instruction, the camera is sent instructions to, so as to whether there is in the coverage of the camera detection camera
Face, and will test result and feed back to the Face datection unit 11.
Preferably, when the Face datection unit 11 detects that the coverage of the camera there are when face, is opened
Infrared light supply, so that on infrared light supply transmitting infrared ray to face.Specifically, infrared light supply can make the camera exist
Also relatively clear facial image can be got in dark surrounds, so as to avoid being difficult in dark surrounds carrying out recognition of face
The problem of.Preferably, the camera can be infrared camera, and the infrared light supply can be the infrared camera itself
The infrared ray that the infrared ray of transmitting or other structure light source issue, all within the scope of the present invention.
Specifically, the facial image acquiring unit 12 obtains the preset quantity facial image of the camera shooting,
Preferably, the camera can be continuously shot in a short time, for example 5 facial images are shot in 3 seconds.Then in this process
In, because user causes nostril to change in breathing in the facial image that gets, so as to according to the change for judging user nostril
Change situation to determine whether being living body.
Specifically, after the facial image acquiring unit 12 obtains the facial image, the nostril acquisition of information list
Member 13 extracts the nostril information in each facial image.Specifically, the nostril information acquisition unit 13 extracts each institute
The left nose hole length of left end in left nose hole to right end is stated in facial image, and extracts right nostril in each facial image
Middle left end to right end right nostril length;The nostril information acquisition unit 13 obtains the left side in each facial image
The absolute value of difference between the length of nostril, and obtain the exhausted of difference between the right nostril length in each facial image
To value;The nostril information acquisition unit 13 take the difference between the left nose hole length absolute value and the right nostril length
Between difference absolute value in maximum value be the nostril information.
Specifically, the vivo identification unit 14 carries out the nostril information according to pre-stored nostril size threshold value
Vivo identification judges whether the facial image currently obtained is living body faces image.Preferably, the vivo identification unit
14 judge whether the nostril information is greater than pre-stored nostril size threshold value;If the nostril information is greater than pre-stored
Nostril size threshold value, then the vivo identification unit 14 determine the facial image currently obtained for living body faces image, when
Preceding user is living body;If the nostril information is less than or equal to pre-stored nostril size threshold value, the vivo identification list
Member 14 determines that the facial image currently obtained is non-living body facial image, and active user is non-living body, the people currently obtained
Face image may be that the camera is shot according to user picture.By the situation of change in nostril to determine whether being living body,
Solve human face expression variation cause face identification system occur rejection phenomenon, while solve using because of face characteristic can
It is denaturalized and is caused the principle of face identification system rejection, cracks face recognition technology using resources such as photo, videos, to lead
The problem of causing the mistake of face identification system to know.
Specifically, the nostril information is no more than nostril size limit value, because the camera is continuous in a short time
Face is shot, therefore during user carries out recognition of face, the distance between user and the camera are remained unchanged, from
And the facial image that the camera is got is almost the same, and user is to be in the shooting process of the camera
Respiratory state can occur slight change so as to cause nostril size, but not be widely varied, therefore can pass through setting
One nostril size limit value excludes to lead to the camera shooting by mobile photo when the external world carries out recognition of face using photo
Head obtain to facial image in user nostril information be variation, so as to cause misrecognition the case where, can be improved people
The reliability of face identification technology.
Specifically, when the vivo identification unit 14 determines the facial image for living body faces image, the face
Recognition unit 15 extracts the face information of the facial image, and face template according to the pre-stored data carries out the face information
Recognition of face.Preferably, if the face information and the matching degree of the face template are greater than or equal to preset matching value, institute
It states face identification unit 15 and determines recognition of face success;If the face information and the matching degree of the face template are less than described
Preset matching value, then the face identification unit 15 determines recognition of face failure.
When it is implemented, detecting the shooting model of camera when Face datection unit 11 responds recognition of face instruction first
With the presence or absence of face in enclosing, and when detect the coverage of the camera there are when face, facial image acquiring unit 12
Obtain preset quantity facial image;Then nostril information acquisition unit 13 extracts the letter of the nostril in each facial image
Breath, vivo identification unit 14 carry out vivo identification to the nostril information;Finally when the facial image is living body faces image
When, face identification unit 15 extracts the face information of the facial image, and face template according to the pre-stored data is to the face
Information carries out recognition of face.
Compared with prior art, the face identification system 10 disclosed by the invention based on nostril information, solves existing skill
Because face characteristic has changeability in art, it may cause face identification system and rejection phenomenon occur, while using because of face characteristic
Changeability and cause the principle of face identification system rejection, face recognition technology is cracked using resources such as photo, videos, from
And the mistake of face identification system is caused to be known, the problem of reliability of face recognition technology reduces, it can effectively solve recognition of face system
The mistake of system knows and rejection phenomenon, improves the reliability of face recognition technology.
Embodiment three
Referring to fig. 4, Fig. 4 is a kind of structure of face recognition device 20 based on nostril information provided in an embodiment of the present invention
Block diagram;The face recognition device 20 based on nostril information of the embodiment includes: processor 21, memory 22 and is stored in institute
State the computer program that can be run in memory 22 and on the processor 21.The processor 21 executes the computer journey
The step in above-mentioned each screen control method embodiment, such as step S1~S4 shown in FIG. 1 are realized when sequence.Alternatively, described
Processor 21 realizes the function of each unit in above-mentioned each Installation practice, such as the face inspection when executing the computer program
Survey the function of unit 11.
Illustratively, the computer program can be divided into one or more module/units, one or more
A module/unit is stored in the memory, and is executed by the processor 21, to complete the present invention.It is one or
Multiple module/units can be the series of computation machine program instruction section that can complete specific function, and the instruction segment is for describing
Implementation procedure of the computer program in the face recognition device 20 based on nostril information.For example, the computer
Program can be divided into Face datection unit 11, facial image acquiring unit 12, nostril information acquisition unit 13, vivo identification
Unit 14 and face identification unit 15, each module concrete function are known with reference to the face in above-described embodiment two based on nostril information
The function of modules in other system 10, details are not described herein.
The face recognition device 20 based on nostril information can be desktop PC, notebook, palm PC and
Cloud server etc. calculates equipment.The face recognition device 20 based on nostril information may include, but be not limited only to, processor
21, memory 22.It will be understood by those skilled in the art that the schematic diagram is only based on the face recognition device of nostril information
20 example does not constitute the restriction to the face recognition device 20 based on nostril information, may include more or more than illustrating
Few component perhaps combines certain components or different components, such as the face recognition device 20 based on nostril information
It can also include input-output equipment, network access equipment, bus etc..
The processor 21 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng the processor 21 is the control centre of the face recognition device 20 based on nostril information, utilizes various interfaces and line
Road connects the various pieces of the entirely face recognition device 20 based on nostril information.
The memory 22 can be used for storing the computer program and/or module, the processor 22 by operation or
Computer program and/or the module stored in the memory is executed, and calls the data being stored in memory, is realized
The various functions of the face recognition device 20 based on nostril information.The memory 22 can mainly include storing program area and
Storage data area, wherein application program needed for storing program area can store operating device, at least one function (such as sound
Playing function, image player function etc.) etc.;Storage data area, which can be stored, uses created data (such as sound according to mobile phone
Frequency evidence, phone directory etc.) etc..In addition, the memory 22 may include high-speed random access memory, it can also include non-easy
The property lost memory, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital
(Secure Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other
Volatile solid-state part.
Wherein, if the integrated module/unit of the face recognition device 20 based on nostril information is with software function list
Member form realize and when sold or used as an independent product, can store in a computer-readable storage medium
In.Based on this understanding, the present invention realizes all or part of the process in above-described embodiment method, can also pass through computer
Program is completed to instruct relevant hardware, and the computer program can be stored in a computer readable storage medium, should
Computer program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program
Including computer program code, the computer program code can be source code form, object identification code form, executable file
Or certain intermediate forms etc..The computer-readable medium may include: can carry the computer program code any
Entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and
Software distribution medium etc..It should be noted that the content that the computer-readable medium includes can be according in jurisdiction
Legislation and the requirement of patent practice carry out increase and decrease appropriate, such as in certain jurisdictions, according to legislation and patent practice, meter
Calculation machine readable medium does not include electric carrier signal and telecommunication signal.
It should be noted that the apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
It needs that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.In addition, device provided by the invention
In embodiment attached drawing, the connection relationship between module indicate between them have communication connection, specifically can be implemented as one or
A plurality of communication bus or signal wire.Those of ordinary skill in the art are without creative efforts, it can understand
And implement.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (10)
1. a kind of face identification method based on nostril information characterized by comprising
When responding recognition of face instruction, detect in the coverage of camera with the presence or absence of face;
When the coverage for detecting the camera opens face there are the preset quantity that the camera is shot when face, is obtained
Image, and extract the nostril information in each facial image;
Vivo identification is carried out to the nostril information according to pre-stored nostril size threshold value, judges the people currently obtained
Whether face image is living body faces image;
When the facial image is living body faces image, the face information of the facial image is extracted, it is according to the pre-stored data
Face template carries out recognition of face to the face information.
2. the face identification method as described in claim 1 based on nostril information, which is characterized in that the extraction is each described
Nostril information in facial image, comprising:
The left nose hole length of left end in left nose hole to right end is extracted in each facial image, and extracts each people
In face image in right nostril left end to right end right nostril length;
The absolute value of the difference between the left nose hole length in each facial image is obtained, and obtains each face figure
The absolute value of the difference between right nostril length as in;
In the absolute value for taking the difference between the absolute value of the difference between the left nose hole length and the right nostril length
Maximum value is the nostril information.
3. the face identification method as claimed in claim 2 based on nostril information, which is characterized in that described according to being stored in advance
Nostril size threshold value vivo identification is carried out to the nostril information, judge whether the facial image that currently obtains is living body
Facial image, comprising:
Judge whether the nostril information is greater than pre-stored nostril size threshold value;
If so, determining that the facial image currently obtained is living body faces image;If it is not, then determining currently to obtain described
Facial image is non-living body facial image.
4. the face identification method as described in claim 1 based on nostril information, which is characterized in that the basis is stored in advance
Face template to the face information carry out recognition of face, comprising:
If the matching degree of the face information and the face template is greater than or equal to preset matching value, determine recognition of face at
Function;
If the face information and the matching degree of the face template are less than the preset matching value, determine that recognition of face is lost
It loses.
5. the face identification method as described in claim 1 based on nostril information, which is characterized in that the face information includes
But it is not limited to facial contour, eye contour, eye position information, nose profile and nose shape information.
6. a kind of face identification system based on nostril information characterized by comprising
Face datection unit when for responding recognition of face instruction, detects in the coverage of camera with the presence or absence of face;
Facial image acquiring unit, for obtaining the camera shooting when the coverage for detecting the camera is there are when face
The preset quantity facial image of head shooting;
Nostril information acquisition unit, for extracting the nostril information in each facial image;
Vivo identification unit is sentenced for carrying out vivo identification to the nostril information according to pre-stored nostril size threshold value
Whether the disconnected facial image currently obtained is living body faces image;
Face identification unit, for when the facial image is living body faces image, extracting the face letter of the facial image
Breath, face template according to the pre-stored data carry out recognition of face to the face information.
7. the face identification system as claimed in claim 6 based on nostril information, which is characterized in that the nostril acquisition of information
Unit is specifically used for:
The left nose hole length of left end in left nose hole to right end is extracted in each facial image, and extracts each people
In face image in right nostril left end to right end right nostril length;
The absolute value of the difference between the left nose hole length in each facial image is obtained, and obtains each face figure
The absolute value of the difference between right nostril length as in;
In the absolute value for taking the difference between the absolute value of the difference between the left nose hole length and the right nostril length
Maximum value is the nostril information.
8. the face identification system as claimed in claim 7 based on nostril information, which is characterized in that the vivo identification unit
It is specifically used for:
Judge whether the nostril information is greater than pre-stored nostril size threshold value;
If so, determining that the facial image currently obtained is living body faces image;If it is not, then determining currently to obtain described
Facial image is non-living body facial image.
9. the face identification system as claimed in claim 6 based on nostril information, which is characterized in that the face identification unit
If the matching degree for the face information and the face template is greater than or equal to preset matching value, determine recognition of face at
Function;If the face information and the matching degree of the face template are less than the preset matching value, determine that recognition of face fails;
The face information includes but is not limited to facial contour, eye contour, eye position information, nose profile and nose shape
Information.
10. a kind of face recognition device based on nostril information, including processor, memory and storage are in the memory
And it is configured as the computer program executed by the processor, the processor is realized when executing the computer program as weighed
Benefit require any one of 1 to 5 described in the face identification method based on nostril information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811573339.5A CN109684993B (en) | 2018-12-21 | 2018-12-21 | Face recognition method, system and equipment based on nostril information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811573339.5A CN109684993B (en) | 2018-12-21 | 2018-12-21 | Face recognition method, system and equipment based on nostril information |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109684993A true CN109684993A (en) | 2019-04-26 |
CN109684993B CN109684993B (en) | 2021-04-27 |
Family
ID=66188837
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811573339.5A Expired - Fee Related CN109684993B (en) | 2018-12-21 | 2018-12-21 | Face recognition method, system and equipment based on nostril information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109684993B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111985438A (en) * | 2020-08-31 | 2020-11-24 | 杭州海康威视数字技术股份有限公司 | Static face processing method, device and equipment |
CN112750221A (en) * | 2019-10-31 | 2021-05-04 | 深圳云天励飞技术有限公司 | Campus sign-in method and device and sign-in equipment |
CN113158773A (en) * | 2021-03-05 | 2021-07-23 | 普联技术有限公司 | Training method and training device for living body detection model |
CN113723306A (en) * | 2021-08-31 | 2021-11-30 | 上海掌门科技有限公司 | Push-up detection method, device and computer readable medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104951743A (en) * | 2015-03-04 | 2015-09-30 | 苏州大学 | Active-shape-model-algorithm-based method for analyzing face expression |
CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
CN107292290A (en) * | 2017-07-17 | 2017-10-24 | 广东欧珀移动通信有限公司 | Face vivo identification method and Related product |
CN107346422A (en) * | 2017-06-30 | 2017-11-14 | 成都大学 | A kind of living body faces recognition methods based on blink detection |
CN107451547A (en) * | 2017-07-17 | 2017-12-08 | 广东欧珀移动通信有限公司 | Identify the method and Related product of live body |
CN107590463A (en) * | 2017-09-12 | 2018-01-16 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
CN107895155A (en) * | 2017-11-29 | 2018-04-10 | 五八有限公司 | A kind of face identification method and device |
-
2018
- 2018-12-21 CN CN201811573339.5A patent/CN109684993B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104951743A (en) * | 2015-03-04 | 2015-09-30 | 苏州大学 | Active-shape-model-algorithm-based method for analyzing face expression |
CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
CN107346422A (en) * | 2017-06-30 | 2017-11-14 | 成都大学 | A kind of living body faces recognition methods based on blink detection |
CN107292290A (en) * | 2017-07-17 | 2017-10-24 | 广东欧珀移动通信有限公司 | Face vivo identification method and Related product |
CN107451547A (en) * | 2017-07-17 | 2017-12-08 | 广东欧珀移动通信有限公司 | Identify the method and Related product of live body |
CN107590463A (en) * | 2017-09-12 | 2018-01-16 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
CN107895155A (en) * | 2017-11-29 | 2018-04-10 | 五八有限公司 | A kind of face identification method and device |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112750221A (en) * | 2019-10-31 | 2021-05-04 | 深圳云天励飞技术有限公司 | Campus sign-in method and device and sign-in equipment |
CN111985438A (en) * | 2020-08-31 | 2020-11-24 | 杭州海康威视数字技术股份有限公司 | Static face processing method, device and equipment |
CN113158773A (en) * | 2021-03-05 | 2021-07-23 | 普联技术有限公司 | Training method and training device for living body detection model |
CN113158773B (en) * | 2021-03-05 | 2024-03-22 | 普联技术有限公司 | Training method and training device for living body detection model |
CN113723306A (en) * | 2021-08-31 | 2021-11-30 | 上海掌门科技有限公司 | Push-up detection method, device and computer readable medium |
Also Published As
Publication number | Publication date |
---|---|
CN109684993B (en) | 2021-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109858337A (en) | A kind of face identification method based on pupil information, system and equipment | |
CN109446981B (en) | Face living body detection and identity authentication method and device | |
KR101997371B1 (en) | Identity authentication method and apparatus, terminal and server | |
KR102387495B1 (en) | Image processing method and apparatus, electronic device and storage medium | |
WO2019080580A1 (en) | 3d face identity authentication method and apparatus | |
WO2019080578A1 (en) | 3d face identity authentication method and apparatus | |
US20150379332A1 (en) | Face authentication device and face authentication method | |
CN106951866A (en) | A kind of face authentication method and device | |
CN109684993A (en) | A kind of face identification method based on nostril information, system and equipment | |
CN108124486A (en) | Face living body detection method based on cloud, electronic device and program product | |
CN204791017U (en) | Mobile terminal users authentication device based on many biological characteristics mode | |
US20180011975A1 (en) | Human body characteristic data processing method and apparatus | |
CN107154890A (en) | Method, the apparatus and system of contact person is added in social networks | |
WO2018133282A1 (en) | Dynamic recognition method and terminal device | |
CN107506629B (en) | Unlocking control method and related product | |
CN106780819A (en) | Can be used for the work attendance punch card system of face recognition | |
KR20220042301A (en) | Image detection method and related devices, devices, storage media, computer programs | |
CN111445640A (en) | Express delivery pickup method, device, equipment and storage medium based on iris recognition | |
CN109034029A (en) | Detect face identification method, readable storage medium storing program for executing and the electronic equipment of living body | |
CN110765851A (en) | Registration method, device and equipment | |
CN110826410B (en) | Face recognition method and device | |
CN111091047B (en) | Living body detection method and device, server and face recognition equipment | |
CN108683901B (en) | Data processing method, MEC server and computer readable storage medium | |
CN110874582A (en) | Telecommunication fraud determination method and device, storage medium and electronic device | |
CN107493368B (en) | Unlocking method and related product |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210427 |
|
CF01 | Termination of patent right due to non-payment of annual fee |