CN106372615A - Face anti-counterfeiting identification method and apparatus - Google Patents
Face anti-counterfeiting identification method and apparatus Download PDFInfo
- Publication number
- CN106372615A CN106372615A CN201610830818.5A CN201610830818A CN106372615A CN 106372615 A CN106372615 A CN 106372615A CN 201610830818 A CN201610830818 A CN 201610830818A CN 106372615 A CN106372615 A CN 106372615A
- Authority
- CN
- China
- Prior art keywords
- face
- facial image
- identified
- thermal infrared
- infrared
- 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
- 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
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiments of the invention discloses a face anti-counterfeiting identification method and apparatus, for improving security of face identification. The method provided by the embodiments of the invention comprises the following steps: obtaining a thermal infrared image and a near-infrared image of a to-be-acquired object, wherein the thermal infrared image and the near-infrared image comprises a to-be-identified face; extracting the to-be-identified face in the thermal infrared image and the near-infrared image to obtain a target thermal infrared face image and a target near-infrared face image; and according to correlation between the target thermal infrared face image and the target near-infrared face image, or according to a decision fusion result of a first identification result and a second identification result, performing true and false identification on the to-be-identified face, wherein the first identification result is an identification result of the target thermal infrared face image and the second identification result is an identification result of the target near-infrared face image. According to the invention, the to-be-identified face is identified by use of a mode of combining the acquired thermal infrared image with the near-infrared image, and thus the face identification security can be improved.
Description
Technical field
The present invention relates to recognition of face field of anti-counterfeit technology, more particularly, to a kind of face Antiforge recognizing method and device.
Background technology
Recognition of face is big priority research areass in current biological feature identification field.It and the finger being widely used at present
Stricture of vagina technology of identification is compared, and has the significant features such as compare intuitive, convenience, untouchable, user's acceptance is higher.
When visible ray changes, the recognition of face of near-infrared facial image still can keep good performance, but due to
Near-infrared belong to reflection infrared, the human face photo of personation still can be imaged, and for thermal infrared facial image reflection edge
Profile and minutia cornea, some physiological changies (as ethanol reflection) and external environment condition change (as the change of ambient temperature) meeting
Impact is produced on the heat radiation of face, thus affecting the performance of thermal infrared recognition of face, in business application stage, thermal infrared imaging
Recognition of face performance fails to reach.But thermal infrared imaging is related to the heat of object radiation, directly reflect people for face
The situation of face temperature distribution, this is that photo, video do not have, and the face that therefore thermal infrared images inherently indicates in image is alive
Body, it is not subject to photo deception and spoof attack.
And have the true and false to recognize face with thermal infrared commercial measurement face temperature or thermal infrared Face datection at present.Right
The method of measurement face temperature, personator can be come fraud system by human face photo is placed on the hot water bag of warm.Heat
Infrared face detection method, is equivalent to investigate face profiling temperatures, and for this detection intravital method, we can be with heat
The characteristic of infrared glass reflection is forging living body faces.For example, attacker places one before about 45 degree of angles of human face photo
Block simple glass, has stronger reflection because thermal infrared runs into, thermal infrared photographic head can be in the position of human face photo during glass
Put and photograph hot rising star's face it is possible to the intravital method of fraud detection thermal infrared face, for thermal infrared recognition of face, its
Recognition of face performance also certain gap compared with near-infrared recognition of face, utilizes merely thermal infrared technology identification face true and false
Mode is still not safe.
Content of the invention
Embodiments provide a kind of face Antiforge recognizing method and device, the safety of recognition of face can be improved
Property.
In view of this, first aspect present invention provides a kind of face Antiforge recognizing method, comprising:
Obtain thermal infrared images and the near-infrared image of object to be collected, described object to be collected includes people to be identified
Face, described thermal infrared images and near-infrared image comprise described face to be identified；
The face to be identified extracting in described thermal infrared images obtains target thermal infrared facial image, extracts described near-infrared
Face to be identified in image obtains target near-infrared facial image；
According to the dependency of described target thermal infrared facial image and described target near-infrared facial image, or according to
The Decision fusion result of the first recognition result and the second recognition result carries out true and false identification to described face to be identified, and described
One recognition result is the recognition result of described target thermal infrared facial image, and described second recognition result is described target near-infrared
The recognition result of facial image.
In conjunction with first aspect present invention, in first aspect present invention first embodiment, described according to dependency to institute
State face to be identified carry out true and false identification include:
Determine described dependency according to Canonical Correlation Analysis；
True and false identification is carried out to described face to be identified according to described dependency.
In conjunction with first aspect present invention first embodiment, in first aspect present invention second embodiment, described basis
Described dependency carries out true and false identification and includes to described face to be identified:
Determine whether described dependency is more than or equal to the first preset value；
If it is determined that described face to be identified is real human face；
If not it is determined that described face to be identified is false face.
In conjunction with first aspect present invention second embodiment, in first aspect present invention the 3rd embodiment, described basis
Canonical Correlation Analysis determine that described dependency includes:
Described dependency is calculated according to below equation:
Wherein,Described s is described dependency, and described v is described target thermal infrared face figure
The face feature vector of picture, described u is the face feature vector of described target near-infrared facial image；Described u ' exists for described u
wxProjection on direction；Described v ' is described v in wyProjection on direction.
In conjunction with the present invention first face, in first aspect present invention the 4th embodiment, the described thermal infrared images of described extraction
In face to be identified obtain target thermal infrared facial image after, methods described also includes:
Described target thermal infrared facial image is mated with the image in default thermal infrared facial image database, is determined institute
State the first recognition result；
After the described face to be identified extracting in described near-infrared image obtains target near-infrared facial image, described side
Method also includes:
Described target near-infrared facial image is mated with the image in default near-infrared facial image database, is determined institute
State the second recognition result.
In conjunction with first aspect present invention the 4th embodiment, in first aspect present invention the 5th embodiment, described basis
Described Decision fusion result carries out true and false identification to described face to be identified, comprising:
Determine whether described Decision fusion result is more than or equal to the second preset value；
If it is determined that described face to be identified is false face；
If not it is determined that described face to be identified is real human face.
In conjunction with first aspect present invention the 5th embodiment, in first aspect present invention the 6th embodiment, described by institute
State target thermal infrared facial image to be mated with the image in default thermal infrared facial image database, determine described first identification knot
Fruit includes:
H is determined according to below equation1j；
Wherein, described h1jRepresent that described target thermal infrared facial image is jth in described default thermal infrared facial image database
Total confidence level of class face, described h1jFor described first recognition result, described αiFor the first weight coefficient, described n1 is described default
The number of jth class face, described h in thermal infrared facial image database1jiRepresent that described target thermal infrared facial image is described default
The confidence level of i-th facial image of thermal infrared facial image database jth class face；
Described described target near-infrared facial image is mated with the image in default near-infrared facial image database, really
Fixed described second recognition result includes:
H is determined according to below equation2j:
Wherein, described h2jRepresent that described target near-infrared facial image is jth in described default near-infrared facial image database
Total confidence level of class face, described h2jFor described second recognition result, described βiFor the second weight coefficient, described n2 is described default
The number of jth class face, described h in near-infrared facial image database2jiRepresent that described target near-infrared facial image is described default
The confidence level of i-th facial image of near-infrared facial image database jth class face；
Described Decision fusion result is obtained according to below equation:
R=argmax (α h1j+βh2j), wherein, described r is described Decision fusion result, and described α is the 3rd weight coefficient, institute
Stating β is the 4th weight coefficient.
Second aspect present invention provides a kind of face Anti-Counterfeit Identification Device, and this face Anti-Counterfeit Identification Device includes:
Acquisition module, for obtaining thermal infrared images and the near-infrared image of object to be collected, described object to be collected
Include face to be identified, described thermal infrared images and near-infrared image comprise described face to be identified；
Extraction module, obtains target thermal infrared facial image for extracting the face to be identified in described thermal infrared images,
The face to be identified extracting in described near-infrared image obtains target near-infrared facial image；
Identification module, for the phase according to described target thermal infrared facial image and described target near-infrared facial image
Guan Xing, or according to the Decision fusion result of the first recognition result and the second recognition result, described face to be identified is carried out very
False identification, described first recognition result is the recognition result of described target thermal infrared facial image, and described second recognition result is
The recognition result of described target near-infrared facial image.
In conjunction with second aspect present invention, in second aspect present invention first embodiment, described identification module includes:
Determining unit, for determining described dependency according to Canonical Correlation Analysis；
Recognition unit, the described dependency for being determined according to described determining unit carries out true and false to described face to be identified
Identification.
In conjunction with second aspect present invention first embodiment, in second aspect present invention second embodiment, described identification
Unit specifically for:
Determine whether described dependency is more than or equal to the first preset value；
If it is determined that described face to be identified is real human face；
If not it is determined that described face to be identified is false face.
In conjunction with second aspect present invention second embodiment, in second aspect present invention the 3rd embodiment, described determination
Unit specifically for:
Described dependency is calculated according to below equation:
Wherein,Described s is described dependency, and described v is described target thermal infrared face figure
The face feature vector of picture, described u is the face feature vector of described target near-infrared facial image；Described u ' exists for described u
wxProjection on direction；Described v ' is described v in wyProjection on direction.
In conjunction with second party aspect of the present invention, in second aspect present invention the 4th embodiment, described face anti-counterfeit recognition dress
Put and also include:
First determining module, for by the figure in described target thermal infrared facial image and default thermal infrared facial image database
As being mated, determine described first recognition result；
Second determining module, for by the figure in described target near-infrared facial image and default near-infrared facial image database
As being mated, determine described second recognition result.
In conjunction with second aspect present invention the 4th embodiment, in second aspect present invention the 5th embodiment, described identification
Module, for determining whether described Decision fusion result is more than or equal to the second preset value；
If it is determined that described face to be identified is false face；
If not it is determined that described face to be identified is real human face.
In conjunction with second aspect present invention the 5th embodiment, in second aspect present invention the 6th embodiment, described first
Determining module specifically for:
Determine total confidence level h of described target thermal infrared facial image according to below equation1j:
Wherein, αiFor weight coefficient, described n1 is the sample of described target thermal infrared facial image
Number, described h1jiConfidence level for i-th target thermal infrared facial image in the sample number of described target thermal infrared facial image；
According to below equation, described second determining module, for determining that described target near-infrared facial image is described j class
Total confidence level h of face2j:
Wherein, βiFor weight coefficient, described n2 is the sample of described target near-infrared facial image
This number；Described h2jiConfidence for i-th target near-infrared facial image in the sample number of described target near-infrared facial image
Degree；
Described face Anti-Counterfeit Identification Device also includes:
3rd determining module, for described Decision fusion result is obtained according to below equation:
R=argmax (α h1j+βh2j), wherein, described r is described Decision fusion result, and described α is the 3rd weight coefficient, institute
Stating β is the 4th weight coefficient.
Third aspect present invention provides a kind of computer-readable storage medium, has program stored therein generation in this computer-readable storage medium
Code, this program code is used for the method that instruction executes above-mentioned first aspect.
As can be seen from the above technical solutions, see in the embodiment of the present invention, by obtaining the thermal infrared figure of object to be collected
Picture and near-infrared image, wherein, object to be collected includes face to be identified, and thermal infrared images and near-infrared image comprise
Face to be identified；The face to be identified extracting in thermal infrared images obtains target thermal infrared facial image, extracts near-infrared image
In face to be identified obtain target near-infrared facial image；According to target thermal infrared facial image and target near-infrared face
The dependency of image, or according to the Decision fusion result of the first recognition result and the second recognition result, face to be identified is entered
The true and false identification of row, the first recognition result is the recognition result of target thermal infrared facial image, and the second recognition result is that target is closely red
The recognition result of outer facial image.I.e. in the embodiment of the present invention, by the thermal infrared images that collects and near-infrared image two
The mode that person combines is identified to face to be identified, can improve the safety of recognition of face.
Brief description
In order to be illustrated more clearly that embodiment of the present invention technical scheme, below will be to institute in embodiment and description of the prior art
Need use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only the present invention some enforcement
Example, for those of ordinary skill in the art, on the premise of not paying creative work, can also obtain according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is a kind of present invention one embodiment schematic flow sheet of face Antiforge recognizing method；
Fig. 2 is a kind of another embodiment schematic flow sheet of present invention face Antiforge recognizing method；
Fig. 3 is a kind of another embodiment schematic flow sheet of present invention face Antiforge recognizing method；
Fig. 4 is a kind of present invention one example structure schematic diagram of face Anti-Counterfeit Identification Device；
Fig. 5 is a kind of another example structure schematic diagram of present invention face Anti-Counterfeit Identification Device.
Specific embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention it is clear that described embodiment is only
The embodiment of a present invention part, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained under the premise of not making creative work, all should belong to the model of present invention protection
Enclose.
Term " first " in description and claims of this specification and above-mentioned accompanying drawing, " second ", " the 3rd ", "
Four " etc. (if present) is for distinguishing similar object, without for describing specific order or precedence.Should manage
The data that solution so uses can be exchanged, in the appropriate case so that the embodiments described herein can be with except illustrating here
Or the order enforcement beyond the content of description.Additionally, term " inclusion " and and they any deformation it is intended that cover not
Exclusive comprises, for example, contain series of steps or unit process, method, system, product or equipment be not necessarily limited to clear
Those steps of listing or unit, but may include clearly not listing or for these processes, method, product or set
Standby intrinsic other steps or unit.
Described from background technology, existing, do not utilize merely the true and false mode of thermal infrared technology identification face still not
Enough safety, therefore in the present invention, by way of combining with reference to both thermal infrared facial image and near-infrared facial image pair
Face to be identified carries out the process of true and false identification.
Refer to Fig. 1, Fig. 1 is a kind of present invention one embodiment schematic flow sheet of face Antiforge recognizing method, comprising:
101st, thermal infrared images and the near-infrared image of object to be collected are obtained, object to be collected includes people to be identified
Face；
Thermal infrared images and the near-infrared image of object to be collected in the present embodiment, can be obtained, in object to be collected
Including facial image to be identified, that is, the thermal infrared images of the object to be collected getting includes face to be identified, equally, obtains
To the near-infrared image of object to be collected also include face to be identified.
102nd, the face to be identified extracting in thermal infrared images obtains target thermal infrared facial image, extracts near-infrared image
In face to be identified obtain target near-infrared facial image；
In the present embodiment, after the thermal infrared images obtaining above-mentioned object to be collected and near-infrared image, corresponding
The face to be identified that can extract in thermal infrared images obtains target thermal infrared facial image, and extracts treating in near-infrared image
Identification face obtains target near-infrared facial image.
103rd, the dependency according to target thermal infrared facial image and target near-infrared facial image, or according to first
The Decision fusion result of recognition result and the second recognition result carries out true and false identification to face to be identified, and the first recognition result is
The recognition result of target thermal infrared facial image, the second recognition result is the recognition result of target near-infrared facial image.
In the present embodiment, after obtaining target thermal infrared facial image and target near-infrared facial image, permissible
True and false identification is carried out to face to be identified according to the dependency of target thermal infrared facial image and target near-infrared facial image,
Or true and false identification is carried out to face to be identified according to the Decision fusion result of the first recognition result and the second recognition result,
Wherein, the first recognition result is the recognition result of target thermal infrared facial image, and the second recognition result is target near-infrared face
The recognition result of image.
As can be seen from the above technical solutions, see in embodiments of the present invention, by obtaining the thermal infrared of object to be collected
Image and near-infrared image, wherein, object to be collected includes face to be identified, thermal infrared images and near-infrared image bag
Containing face to be identified；The face to be identified extracting in thermal infrared images obtains target thermal infrared facial image, extracts near-infrared figure
Face to be identified in picture obtains target near-infrared facial image；According to target thermal infrared facial image and target near-infrared people
The dependency of face image, or according to the Decision fusion result of the first recognition result and the second recognition result to face to be identified
Carry out true and false identification, the first recognition result is the recognition result of target thermal infrared facial image, the second recognition result is that target is near
The recognition result of infrared face image.I.e. in the embodiment of the present invention, by the thermal infrared images that collects and near-infrared image
The mode that both combine is identified to face to be identified, can improve the safety of recognition of face.
Wherein, for the ease of understanding and narration, below will be by more specifically embodiment, to above-mentioned red according to target heat
The dependency of outer facial image and target near-infrared facial image carries out true and false identification to face to be identified, and according to first
The Decision fusion result of recognition result and the second recognition result carries out true and false identification to face to be identified, carries out expansion respectively and chats
State:
First, according to the dependency of target thermal infrared facial image and target near-infrared facial image, face to be identified is entered
The true and false identification of row.
Specifically refer to Fig. 2, Fig. 2 is a kind of another embodiment schematic flow sheet of present invention face Antiforge recognizing method, bag
Include:
201st, thermal infrared images and the near-infrared image of object to be collected are obtained；
Thermal infrared images and the near-infrared image of object to be collected in the present embodiment, can be obtained, for example, pass through heat red
Outer imaging device shoots object to be collected, thus obtaining the thermal infrared images of object to be collected, is clapped by near-infrared image forming apparatus
Take the photograph object to be collected, thus obtaining the near-infrared image of object to be collected.In the thermal infrared images obtaining and near-infrared image
Include face to be identified.
For example: in the present embodiment, dual camera can be set, transmitting near infrared ray and Thermal Infra-Red irradiate and wait to adopt respectively
Collection object, one of photographic head obtains the near-infrared image of object to be collected, and another obtains the thermal infrared of object to be collected
Image.
It should be noted that thermal infrared images and the near-infrared figure of object to be collected can be obtained simultaneously or asynchronously
Picture, does not specifically limit herein.
It is further to note that before the thermal infrared images obtaining object to be collected and near-infrared image, this reality
Apply example also to include:
Judge whether above-mentioned object to be collected comprises face to be identified, if object to be collected includes face to be identified,
The step triggering above-mentioned acquisition thermal infrared images to be collected and near-infrared image.
202nd, the face to be identified extracting in thermal infrared images obtains target thermal infrared facial image, extracts near-infrared image
In face to be identified obtain target near-infrared facial image；
In the present embodiment, after the thermal infrared images obtaining object to be collected and near-infrared head portrait, heat can be extracted
Face to be identified in infrared image obtains target thermal infrared facial image, and the face to be identified extracting in near-infrared image obtains
Obtain target near-infrared facial image.
It should be understood that in step 201, it utilizes in the thermal infrared images of object to be collected that thermal infrared imaging instrument shoots,
The process that thermal infrared images extracts target thermal infrared facial image is to thermal infrared images filter process, that is, exclude dry
Disturb, retain need part to be processed, filter out unwanted part.Thermal infrared imaging equipment can expand when reading in face to be identified
Big viewfinder range, wherein contains much invalid pixel, and this can affect the process of subsequent step, increases overall calculation amount, therefore
Complete first is to take out the part comprising face to be identified as precisely as possible from the thermal infrared images obtaining.This process
Main difficulty be to judge whether image belongs to the part of needs reservation, and it is essential to ensure that its accuracy, otherwise will under
One step recognition of face impacts.I.e. in the present embodiment, the human face region in thermal infrared images need to only be extracted, that is, to be identified
Face part, obtains target thermal infrared facial image, in the same manner, only need to extract the human face region in near-infrared image, that is,
Face part to be identified, obtains target near-infrared facial image.
203rd, pretreatment is carried out to target thermal infrared facial image and target near-infrared facial image；
In the present embodiment, after being extracted target thermal infrared facial image and target near-infrared facial image, to target
Thermal infrared facial image and target near-infrared facial image carry out pretreatment.
It should be understood that due to target thermal infrared facial image, the imaging mechanism of target nearly rising star face image and visible images
Difference, target thermal infrared and target near-infrared facial image are to detect face region to be identified by infrared thermoviewer
Infra-red radiation and formed, its gray level image reflects Temperature Distribution and the substance characteristics of face region to be identified.And this
The temperature change of body and surrounding can quickly cause the change treating face gray level image, and thermal infrared imaging and near-infrared pole
Be also easy to produce various noises thus affecting the quality of final facial image to be identified, therefore to target thermal infrared facial image and
In the pretreatment of near-infrared facial image, corresponding measure must be taken to improve picture quality, reduce above-mentioned factor to people to be identified
The impact of face identification.The target thermal infrared facial image extracting and target near-infrared facial image can be carried out with a pre- place
The process of reason.For the ease of description, will be described with the specific preprocess method of target thermal infrared facial image below:
For example, the image calibration to target thermal infrared facial image, the dynamic range of thermal infrared imaging equipment of eliminating the effects of the act
Factor；After calibration, the enhancing to target thermal infrared facial image and coarse segmentation, for example, histogram equalization can be adopted
Change enhancement process, improve its image resolution ratio and picture quality, using edge detection method, target thermal infrared facial image is entered
Row is processed, make face and the edge about organ in thermal infrared facial image become apparent from substantially；Then to target thermal infrared
The geometrical normalization of facial image is processed, and the human eye spacing in face to be identified is transformed to a unified size.To image
Zoom in and out process, then by image rotation it is ensured that eyes center in the same horizontal line, by fixed target thermal infrared
Facial image cheek, hair, lower jaw, eye and mouth position, cutting loses hair, the right boundary of lower jaw and face with outer portion, extremely
This completes the preprocessing process of target thermal infrared facial image.
It should be noted that target near-infrared facial image is using the pre- place with above-mentioned thermal infrared facial image in the present invention
Reason method is identical.
It is further to note that above-mentioned preprocessing process is citing here illustrate, but not in the present invention
The preprocessing process of target thermal infrared facial image and target near-infrared facial image is caused to limit, as long as making finally pre-
The target thermal infrared facial image having processed and target near-infrared facial image facilitate follow-up identification process, specifically this
Place does not limit.
204th, pretreated target thermal infrared facial image and target near-infrared people are determined according to typicality method of correlation
The dependency s of face image；
In the present embodiment, after pretreatment is carried out to target thermal infrared facial image and near-infrared facial image, permissible
Determine the dependency of pretreated target thermal infrared facial image and near-infrared facial image according to typicality method of correlation.
Typicality method of correlation (English full name: (canonical correspondence analusis, abbreviation: cca), it is
A kind of multidimensional variable between set up the method for linear relationship, in the present embodiment, target thermal infrared is determined by cca method
Facial image and the dependency of target near-infrared facial image, here false pretreated target thermal infrared facial image and
The dependency of near-infrared facial image is s:
For face feature vector v of given target thermal infrared facial image, the face of target near-infrared facial image
Characteristic vector u, can determine dependency s by below equation:
Wherein,U is u in wxProjection on direction；V is v in wyProjection on direction.
It should be noted that except determining target thermal infrared facial image and target near-infrared people by the way of cca
Outside the dependency of face image, can also have and other determine target thermal infrared facial images and target near-infrared facial image
Correlation method, does not specifically limit herein, also repeats no more.
205th, determine whether dependency s is more than or equal to the first preset value, if so, then trigger step 206；If it is not, then touching
Send out step 207；
It is determined that after dependency s, may further determine that whether dependency s is pre- more than or equal to first in the present embodiment
If value, if dependency s is more than or equal to the first preset value, trigger step 206；If dependency s is less than the first preset value, touch
Send out step 207.
It should be noted that the first preset value is to be obtained according to empirical data, can be joined according to practical situations
Put, specifically do not limit herein.
206th, determine that face to be identified is real human face；
207th, determine that face to be identified is false face.
As can be seen from the above technical solutions, see in the embodiment of the present invention, by obtaining the thermal infrared figure of object to be collected
Picture and near-infrared image, wherein, object to be collected includes face to be identified, and thermal infrared images and near-infrared image comprise
Face to be identified；The face to be identified extracting in thermal infrared images obtains target thermal infrared facial image, extracts near-infrared image
In face to be identified obtain target near-infrared facial image, according to pretreated target thermal infrared facial image and target
The dependency of near-infrared facial image, carries out true and false identification to face to be identified.I.e. in the embodiment of the present invention, treated by collecting
The dependency that both the thermal infrared images of identification face and near-infrared image combine carries out true and false identification to face to be identified,
The safety of recognition of face can be improved.
2nd, the Decision fusion result according to the first recognition result and the second recognition result face to be identified is carried out true and false
Identification, the first recognition result is the recognition result of target thermal infrared facial image, and the second recognition result is target near-infrared face
The recognition result of image.
Specifically refer to Fig. 3, Fig. 3 is a kind of another embodiment schematic diagram of present invention face Antiforge recognizing method, comprising:
301st, thermal infrared images and the near-infrared image of object to be collected are obtained；
302nd, the face to be identified extracting in thermal infrared images obtains target thermal infrared facial image, extracts near-infrared image
In face to be identified obtain target near-infrared facial image；
303rd, pretreatment is carried out to target thermal infrared facial image and target near-infrared facial image；
Wherein, step 301,302 and 303, specifically can be corresponding refering to above-described embodiment step 201,202 and 203
Process, specifically here is omitted.
304th, pretreated target thermal infrared facial image and the image in default thermal infrared facial image database are carried out
Coupling, determines the first recognition result, target near-infrared facial image is carried out with the image in default near-infrared facial image database
Coupling, determines the second recognition result；
In the present embodiment, can be by the image in described target thermal infrared facial image and default thermal infrared facial image database
Mated, determined described first recognition result, by described target near-infrared facial image and default near-infrared facial image database
In image mated, determine described second recognition result.
Wherein, described image in described target thermal infrared facial image and default thermal infrared facial image database is carried out
Join, determine that described first recognition result includes:
H is determined according to below equation1j；
Wherein, h1jRepresent that target thermal infrared facial image is always the putting of jth class face in default thermal infrared facial image database
Reliability, h1jFor the first recognition result, αiFor the first weight coefficient, n1 is the individual of jth class face in default thermal infrared facial image database
Number, h1jiRepresent that target thermal infrared facial image is i-th facial image of default thermal infrared facial image database jth class face
Confidence level.
It should be noted that the first weight coefficient αiFor empirical data, can be configured according to practical situations, specifically
Do not limit herein.It is further to note that comprise how many class images in default thermal infrared facial image database, and each class
In image, how many sample number, does not also limit here, can be configured according to practical situations.
Target near-infrared facial image is mated with the image in default near-infrared facial image database, is determined the second knowledge
Other result includes:
H is determined according to below equation2j:
Wherein, h2jRepresent that target near-infrared facial image is always the putting of jth class face in default near-infrared facial image database
Reliability, h2jFor the second recognition result, βiFor the second weight coefficient, n2 is the individual of jth class face in default near-infrared facial image database
Number, h2jiRepresent that target near-infrared facial image is i-th facial image of default near-infrared facial image database jth class face
Confidence level.
Equally, it should be noted that the second weight coefficient αiFor empirical data, can be joined according to practical situations
Put, specifically do not limit herein.It is further to note that comprising how many class images in default near-infrared facial image database, with
And how many sample number in each class image, also do not limit here, can be configured according to practical situations.
305th, Decision fusion result r is determined according to the first recognition result and the second recognition result；
In the present embodiment, after determining the first recognition result and the second recognition result, according to the first recognition result with
And second recognition result determine Decision fusion result.
For instance, it is preferred that according to so that described Decision fusion result is obtained according to below equation:
R=argmax (α h1j+βh2j), wherein, r is described Decision fusion result, and described α is the 3rd weight coefficient, described β
For the 4th weight coefficient.
It should be noted that the 3rd weight coefficient α and the 4th weight coefficient β is empirical value, can be according to practical application feelings
Condition is configured, and does not specifically limit herein.
306th, determine whether r is more than or equal to the second preset value；If so, then trigger step 307；If it is not, then triggering step
308；
I.e. however, it is determined that the Decision fusion result calculating in step 305 is more than or equal to second preset value in the present embodiment,
Then triggering step 307, if being less than the second preset value, triggering step 307.
It should be noted that the second preset value can rule of thumb data obtain, you can be entered according to practical situations
Row configuration, does not specifically limit, as long as making final true and false recognition result more accurately herein.
307th, determine that described face to be identified is false face；
308th, determine that described face to be identified is real human face.
As can be seen from the above technical solutions, see in the embodiment of the present invention, by obtaining the thermal infrared figure of object to be collected
Picture and near-infrared image, wherein, object to be collected includes face to be identified, and thermal infrared images and near-infrared image comprise
Face to be identified；The face to be identified extracting in thermal infrared images obtains target thermal infrared facial image, extracts near-infrared image
In face to be identified obtain target near-infrared facial image, according to the identification knot of pretreated target thermal infrared facial image
The Decision fusion result of the recognition result of fruit and target near-infrared facial image, carries out true and false identification to face to be identified.I.e.
In the embodiment of the present invention, by thermal infrared images and the method for combining both near-infrared image collecting face to be identified it is
True and false identification is carried out to face to be identified, the safety of recognition of face can be improved.
Above the face Antiforge recognizing method in the present invention is described, the false proof knowledge to the face in the present invention below
Other device is described:
3rd, according to the dependency of target thermal infrared facial image and target near-infrared facial image, face to be identified is entered
The face Anti-Counterfeit Identification Device of the true and false identification of row.
Specifically refer to Fig. 4, Fig. 4 is a kind of present invention one example structure schematic diagram of face Anti-Counterfeit Identification Device, bag
Include: acquisition module 401, extraction module 402 and identification module 403.
Wherein, acquisition module 401, for obtaining thermal infrared images and the near-infrared image of object to be collected, described treat
Acquisition target includes face to be identified, and described thermal infrared images and near-infrared image comprise described face to be identified；
Extraction module 402, obtains target thermal infrared face figure for extracting the face to be identified in described thermal infrared images
Picture, the face to be identified extracting in described near-infrared image obtains target near-infrared facial image；
Identification module 403, for according to described target thermal infrared facial image and described target near-infrared facial image
Dependency, true and false identification is carried out to described face to be identified.
In conjunction with above-described embodiment, further, identification module 403 also includes determining unit 4031 and recognition unit
4032.
Wherein it is determined that unit 4031, for determining described dependency according to Canonical Correlation Analysis；
Recognition unit 4032, the described dependency for being determined according to described determining unit is carried out to described face to be identified
True and false identification.
In conjunction with above-described embodiment, determining unit 4031 is specifically for being calculated described dependency s according to below equation:
Wherein,V is the face feature vector of target thermal infrared facial image, and u is that target is near
The face feature vector of infrared face image；U is u in wxProjection on direction；V is v in wyProjection on direction.
In conjunction with above-described embodiment, recognition unit 4032 specifically for:
Determine whether described dependency s is more than or equal to the first preset value；
If it is determined that described face to be identified is real human face；
If not it is determined that described face to be identified is false face.
It should be noted that the function of face Anti-Counterfeit Identification Device in the present embodiment, step and more details, can
So that refering to the corresponding process in preceding method embodiment one, specifically here is omitted.
As can be seen from the above technical solutions, see in the embodiment of the present invention, acquisition module 401 passes through to obtain object to be collected
Thermal infrared images and near-infrared image, wherein, object to be collected includes face to be identified, thermal infrared images and closely red
Outer image comprises face to be identified, and the face to be identified that extraction module 402 extracts in thermal infrared images obtains target thermal infrared people
The face image face to be identified extracting in near-infrared image obtains target near-infrared facial image, identification module 403 is according to pre-
Target thermal infrared facial image after process and the dependency of target near-infrared facial image, carry out true and false to face to be identified
Identification.I.e. face Anti-Counterfeit Identification Device in the embodiment of the present invention, by collect face to be identified thermal infrared images and
The dependency that both near-infrared images combine carries out true and false identification to face to be identified, can improve the safety of recognition of face
Property.
4th, the Decision fusion result according to the first recognition result and the second recognition result face to be identified is carried out true and false
The face Anti-Counterfeit Identification Device of identification, wherein, the first recognition result is the recognition result of target thermal infrared facial image, the second knowledge
Other result is the recognition result of target near-infrared facial image.
Specifically refer to Fig. 5, Fig. 5 is a kind of another example structure schematic diagram of present invention face Anti-Counterfeit Identification Device, bag
Include: acquisition module 501, extraction module 502 and identification module 503.
Wherein, acquisition module 501, for obtaining thermal infrared images and the near-infrared image of object to be collected, described treat
Acquisition target includes face to be identified, and described thermal infrared images and near-infrared image comprise described face to be identified；
Extraction module 501, obtains target thermal infrared face figure for extracting the face to be identified in described thermal infrared images
Picture, the face to be identified extracting in described near-infrared image obtains target near-infrared facial image；
Identification module 503, for according to the Decision fusion result of the first recognition result and the second recognition result to described
Face to be identified carries out true and false identification, and the first recognition result is the recognition result of target thermal infrared facial image, the second identification knot
Fruit is the recognition result of target near-infrared facial image.
In conjunction with above-described embodiment, face Anti-Counterfeit Identification Device also includes:
First determining module 504, for by the figure in target thermal infrared facial image and default thermal infrared facial image database
As being mated, determine the first recognition result；
Second determining module 505, for by the figure in target near-infrared facial image and default near-infrared facial image database
As being mated, determine the second recognition result.
In conjunction with above-described embodiment, the first determining module 504 specifically for: target thermal infrared face is determined according to below equation
Total confidence level h of image1j:
Wherein, αiFor weight coefficient, n1 is the sample number of target thermal infrared facial image, h1jiFor
The confidence level of i-th target thermal infrared facial image in the sample number of target thermal infrared facial image；
According to below equation, second determining module 504, specifically for determining that target near-infrared facial image is j class face
Total confidence level h2j:
Wherein, βiFor weight coefficient, n2 is the sample number of target near-infrared facial image；h2jiFor
The confidence level of i-th target near-infrared facial image in the sample number of target near-infrared facial image；
In conjunction with above-described embodiment, face Anti-Counterfeit Identification Device also includes:
3rd determining module 506, for Decision fusion result is obtained according to below equation:
R=argmax (α h1j+βh2j), wherein, r is Decision fusion result, and α is the 3rd weight coefficient, and β is the 4th weight coefficient.
In conjunction with above-described embodiment, identification module 503, specifically for determining whether r is more than or equal to the second preset value；
If it is determined that face to be identified is false face；
If not it is determined that face to be identified is real human face.
As can be seen from the above technical solutions, see in the embodiment of the present invention, acquisition module 501 passes through to obtain object to be collected
Thermal infrared images and near-infrared image, wherein, object to be collected includes face to be identified, thermal infrared images and closely red
Outer image comprises face to be identified, and the face to be identified that extraction module 502 extracts in thermal infrared images obtains target thermal infrared people
The face image face to be identified extracting in near-infrared image obtains target near-infrared facial image, identification module 503 is according to mesh
The mark recognition result of thermal infrared facial image and the recognition result of target near-infrared facial image, the decision-making between both is melted
Close result and true and false identification is carried out to described face to be identified.I.e. face Anti-Counterfeit Identification Device in the embodiment of the present invention, by adopting
Collect the Decision fusion result that both the thermal infrared images of face to be identified and near-infrared image combine to face to be identified
Carry out true and false identification, the safety of recognition of face can be improved.
Those skilled in the art can be understood that, for convenience and simplicity of description, the system of foregoing description,
Device and the specific work process of unit, may be referred to the corresponding process in preceding method embodiment, will not be described here.
It should be understood that disclosed system in several embodiments provided herein, apparatus and method are permissible
Realize by another way.For example, device embodiment described above is only schematically, for example, described unit
Divide, only a kind of division of logic function, actual can have other dividing mode when realizing, for example multiple units or assembly
Can in conjunction with or be desirably integrated into another system, or some features can be ignored, or does not execute.Another, shown or
The coupling each other discussing or direct-coupling or communication connection can be by some interfaces, the indirect coupling of device or unit
Close or communicate to connect, can be electrical, mechanical or other forms.
The described unit illustrating as separating component can be or may not be physically separate, show as unit
The part showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.The mesh to realize this embodiment scheme for some or all of unit therein can be selected according to the actual needs
's.
In addition, can be integrated in a processing unit in each functional unit in each embodiment of the present invention it is also possible to
It is that unit is individually physically present it is also possible to two or more units are integrated in a unit.Above-mentioned integrated list
Unit both can be to be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If described integrated unit is realized and as independent production marketing or use using in the form of SFU software functional unit
When, can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part in other words prior art being contributed or all or part of this technical scheme can be in the form of software products
Embody, this computer software product is stored in a storage medium, including some instructions with so that a computer
Equipment (can be personal computer, server, or network equipment etc.) executes the complete of each embodiment methods described of the present invention
Portion or part steps.And aforesaid storage medium includes: u disk, portable hard drive, read only memory (English full name: read-only
Memory, English abbreviation: rom), random access memory (English full name: random access memory, English abbreviation:
Ram), magnetic disc or CD etc. are various can be with the medium of store program codes.
The above, above example only in order to technical scheme to be described, is not intended to limit；Although with reference to front
State embodiment the present invention has been described in detail, it will be understood by those within the art that: it still can be to front
State the technical scheme described in each embodiment to modify, or equivalent is carried out to wherein some technical characteristics；And these
Modification or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (14)
1. a kind of face Antiforge recognizing method is it is characterised in that include:
Obtain thermal infrared images and the near-infrared image of object to be collected, described object to be collected includes face to be identified,
Described thermal infrared images and near-infrared image comprise described face to be identified；
The face to be identified extracting in described thermal infrared images obtains target thermal infrared facial image, extracts described near-infrared image
In face to be identified obtain target near-infrared facial image；
According to the dependency of described target thermal infrared facial image and described target near-infrared facial image, or according to first
The Decision fusion result of recognition result and the second recognition result carries out true and false identification, described first knowledge to described face to be identified
Other result is the recognition result of described target thermal infrared facial image, and described second recognition result is described target near-infrared face
The recognition result of image.
2. face Antiforge recognizing method according to claim 1 is it is characterised in that described wait to know to described according to dependency
Others' face carries out true and false identification and includes:
Determine described dependency according to Canonical Correlation Analysis；
True and false identification is carried out to described face to be identified according to described dependency.
3. method according to claim 2 is it is characterised in that described enter to described face to be identified according to described dependency
The true and false identification of row includes:
Determine whether described dependency is more than or equal to the first preset value；
If it is determined that described face to be identified is real human face；
If not it is determined that described face to be identified is false face.
4. the face Antiforge recognizing method according to Claims 2 or 3 it is characterised in that described according to canonical correlation analysis
Method determines that described dependency includes:
Described dependency is calculated according to below equation:
Wherein,Described s is described dependency, and described v is described target thermal infrared facial image
Face feature vector, described u is the face feature vector of described target near-infrared facial image；Described u ' is described u in wxSide
Projection upwards；Described v ' is described v in wyProjection on direction.
5. face Antiforge recognizing method according to claim 1 is it is characterised in that in the described thermal infrared images of described extraction
Face to be identified obtain target thermal infrared facial image after, methods described also includes:
Described target thermal infrared facial image is mated with the image in default thermal infrared facial image database, is determined described
One recognition result；
After the described face to be identified extracting in described near-infrared image obtains target near-infrared facial image, methods described is also
Including:
Described target near-infrared facial image is mated with the image in default near-infrared facial image database, is determined described
Two recognition results.
6. according to claim 1 or 5 face Antiforge recognizing method it is characterised in that described according to described Decision fusion
Result carries out true and false identification to described face to be identified, comprising:
Determine whether described Decision fusion result is more than or equal to the second preset value；
If it is determined that described face to be identified is false face；
If not it is determined that described face to be identified is real human face.
7. face Antiforge recognizing method according to claim 6 it is characterised in that described by described target thermal infrared face
Image is mated with the image in default thermal infrared facial image database, determines that described first recognition result includes:
H is determined according to below equation1j；
Wherein, described h1jRepresent that described target thermal infrared facial image is jth class people in described default thermal infrared facial image database
Total confidence level of face, described h1jFor described first recognition result, described αiFor the first weight coefficient, described n1 is that described default heat is red
The number of jth class face, described h in outer facial image database1jiRepresent that described target thermal infrared facial image is that described default heat is red
The confidence level of i-th facial image of outer facial image database jth class face；
Described described target near-infrared facial image is mated with the image in default near-infrared facial image database, determine institute
State the second recognition result to include:
H is determined according to below equation2j:
Wherein, described h2jRepresent that described target near-infrared facial image is jth class people in described default near-infrared facial image database
Total confidence level of face, described h2jFor described second recognition result, described βiFor the second weight coefficient, described n2 is described default closely red
The number of jth class face, described h in outer facial image database2jiRepresent that described target near-infrared facial image is described default closely red
The confidence level of i-th facial image of outer facial image database jth class face；
Described Decision fusion result is obtained according to below equation:
R=argmax (α h1j+βh2j), wherein, described r is described Decision fusion result, and described α is the 3rd weight coefficient, and described β is
4th weight coefficient.
8. a kind of face Anti-Counterfeit Identification Device is it is characterised in that include:
Acquisition module, for obtaining thermal infrared images and the near-infrared image of object to be collected, wraps in described object to be collected
Include face to be identified, described thermal infrared images and near-infrared image comprise described face to be identified；
Extraction module, obtains target thermal infrared facial image for extracting the face to be identified in described thermal infrared images, extracts
Face to be identified in described near-infrared image obtains target near-infrared facial image；
Identification module, for the correlation according to described target thermal infrared facial image and described target near-infrared facial image
Property, or according to the Decision fusion result of the first recognition result and the second recognition result, described face to be identified is carried out true and false
Identification, described first recognition result is the recognition result of described target thermal infrared facial image, and described second recognition result is institute
State the recognition result of target near-infrared facial image.
9. face Anti-Counterfeit Identification Device according to claim 8 is it is characterised in that described identification module includes:
Determining unit, for determining described dependency according to Canonical Correlation Analysis；
Recognition unit, the described dependency for being determined according to described determining unit carries out true and false knowledge to described face to be identified
Not.
10. face Anti-Counterfeit Identification Device according to claim 9 it is characterised in that described recognition unit specifically for:
Determine whether described dependency s is more than or equal to the first preset value；
If it is determined that described face to be identified is real human face；
If not it is determined that described face to be identified is false face.
The 11. face Anti-Counterfeit Identification Devices according to claim 9 or 10 are it is characterised in that described determining unit is specifically used
In:
Described dependency is calculated according to below equation:
Wherein,Described s is described dependency, and described v is described target thermal infrared facial image
Face feature vector, described u is the face feature vector of described target near-infrared facial image；Described u ' is described u in wxSide
Projection upwards；Described v ' is described v in wyProjection on direction.
12. face Anti-Counterfeit Identification Devices according to claim 8 it is characterised in that described face Anti-Counterfeit Identification Device also
Including:
First determining module, for entering described target thermal infrared facial image and the image in default thermal infrared facial image database
Row coupling, determines described first recognition result；
Second determining module, for entering described target near-infrared facial image and the image in default near-infrared facial image database
Row coupling, determines described second recognition result.
13. face Anti-Counterfeit Identification Devices according to claim 11 or 12 it is characterised in that
Described identification module, for determining whether described Decision fusion result is more than or equal to the second preset value；
If it is determined that described face to be identified is false face；
If not it is determined that described face to be identified is real human face.
14. face Anti-Counterfeit Identification Devices according to claim 12 are it is characterised in that described first determining module is specifically used
In:
Determine total confidence level h of described target thermal infrared facial image according to below equation1j:
Wherein, αiFor weight coefficient, described n1 is the sample number of described target thermal infrared facial image,
Described h1jiConfidence level for i-th target thermal infrared facial image in the sample number of described target thermal infrared facial image；
According to below equation, described second determining module, for determining that described target near-infrared facial image is described j class face
Total confidence level h2j:
Wherein, βiFor weight coefficient, described n2 is the sample number of described target near-infrared facial image；
Described h2jiConfidence level for i-th target near-infrared facial image in the sample number of described target near-infrared facial image；
Described face Anti-Counterfeit Identification Device also includes:
3rd determining module, for described Decision fusion result is obtained according to below equation:
R=argmax (α h1j+βh2j), wherein, described r is described Decision fusion result, and described α is the 3rd weight coefficient, and described β is
4th weight coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610830818.5A CN106372615A (en) | 2016-09-19 | 2016-09-19 | Face anti-counterfeiting identification method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610830818.5A CN106372615A (en) | 2016-09-19 | 2016-09-19 | Face anti-counterfeiting identification method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106372615A true CN106372615A (en) | 2017-02-01 |
Family
ID=57897578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610830818.5A Pending CN106372615A (en) | 2016-09-19 | 2016-09-19 | Face anti-counterfeiting identification method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106372615A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108376239A (en) * | 2018-01-25 | 2018-08-07 | 努比亚技术有限公司 | A kind of face identification method, mobile terminal and storage medium |
| CN108549886A (en) * | 2018-06-29 | 2018-09-18 | 汉王科技股份有限公司 | A kind of human face in-vivo detection method and device |
| CN108764071A (en) * | 2018-05-11 | 2018-11-06 | 四川大学 | It is a kind of based on infrared and visible images real human face detection method and device |
| CN109460485A (en) * | 2018-10-12 | 2019-03-12 | 咪咕文化科技有限公司 | A kind of image library method for building up, device and storage medium |
| CN109543640A (en) * | 2018-11-29 | 2019-03-29 | 中国科学院重庆绿色智能技术研究院 | A kind of biopsy method based on image conversion |
| CN109961025A (en) * | 2019-03-11 | 2019-07-02 | 烟台市广智微芯智能科技有限责任公司 | A kind of true and false face recognition detection method and detection system based on image degree of skewness |
| CN109977741A (en) * | 2017-12-28 | 2019-07-05 | 北京京东尚科信息技术有限公司 | Face identification method, device, system and medium |
| CN110728215A (en) * | 2019-09-26 | 2020-01-24 | 杭州艾芯智能科技有限公司 | Face living body detection method and device based on infrared image |
| CN111967296A (en) * | 2020-06-28 | 2020-11-20 | 北京中科虹霸科技有限公司 | Iris living body detection method, entrance guard control method and entrance guard control device |
| CN113628148A (en) * | 2021-09-17 | 2021-11-09 | 福建库克智能科技有限公司 | Infrared image noise reduction method and device |
| CN113807329A (en) * | 2021-11-18 | 2021-12-17 | 深圳市沃特沃德软件技术有限公司 | Fusion monitoring method and device and computer equipment |
| CN114092864A (en) * | 2022-01-19 | 2022-02-25 | 湖南信达通信息技术有限公司 | Fake video identification method and device, electronic equipment and computer storage medium |
| US11869272B2 (en) | 2019-11-21 | 2024-01-09 | Samsung Electronics Co., Ltd. | Liveness test method and apparatus and biometric authentication method and apparatus |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101404060A (en) * | 2008-11-10 | 2009-04-08 | 北京航空航天大学 | Human face recognition method based on visible light and near-infrared Gabor information amalgamation |
| CN101964056A (en) * | 2010-10-26 | 2011-02-02 | 徐勇 | Bimodal face authentication method with living body detection function and system |
| CN103136516A (en) * | 2013-02-08 | 2013-06-05 | 上海交通大学 | Face recognition method and system fusing visible light and near-infrared information |
| WO2013131407A1 (en) * | 2012-03-08 | 2013-09-12 | 无锡中科奥森科技有限公司 | Double verification face anti-counterfeiting method and device |
| CN104700087A (en) * | 2015-03-23 | 2015-06-10 | 上海交通大学 | Mutual conversion method of visible light and near-infrared human face images |
| CN105069448A (en) * | 2015-09-29 | 2015-11-18 | 厦门中控生物识别信息技术有限公司 | True and false face identification method and device |
| CN105654028A (en) * | 2015-09-29 | 2016-06-08 | 厦门中控生物识别信息技术有限公司 | True and false face identification method and apparatus thereof |
| CN105938546A (en) * | 2016-04-14 | 2016-09-14 | 苏州优化智能科技有限公司 | Real living identity verification terminal equipment based on infrared technology |
-
2016
- 2016-09-19 CN CN201610830818.5A patent/CN106372615A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101404060A (en) * | 2008-11-10 | 2009-04-08 | 北京航空航天大学 | Human face recognition method based on visible light and near-infrared Gabor information amalgamation |
| CN101964056A (en) * | 2010-10-26 | 2011-02-02 | 徐勇 | Bimodal face authentication method with living body detection function and system |
| WO2013131407A1 (en) * | 2012-03-08 | 2013-09-12 | 无锡中科奥森科技有限公司 | Double verification face anti-counterfeiting method and device |
| CN103136516A (en) * | 2013-02-08 | 2013-06-05 | 上海交通大学 | Face recognition method and system fusing visible light and near-infrared information |
| CN104700087A (en) * | 2015-03-23 | 2015-06-10 | 上海交通大学 | Mutual conversion method of visible light and near-infrared human face images |
| CN105069448A (en) * | 2015-09-29 | 2015-11-18 | 厦门中控生物识别信息技术有限公司 | True and false face identification method and device |
| CN105654028A (en) * | 2015-09-29 | 2016-06-08 | 厦门中控生物识别信息技术有限公司 | True and false face identification method and apparatus thereof |
| CN105938546A (en) * | 2016-04-14 | 2016-09-14 | 苏州优化智能科技有限公司 | Real living identity verification terminal equipment based on infrared technology |
Non-Patent Citations (3)
| Title |
|---|
| DIEGO A. SOCOLINSKY等: "《Face recognition with visible and thermal infrared imagery》", 《COMPUTER VISION AND IMAGE UNDERSTANDING》 * |
| 孙霖: "《人脸识别中的活体检测技术研究》", 《中国博士学位论文全文数据库》 * |
| 赵云丰等: "《基于决策融合的红外与可见光图像人脸识别研究》", 《激光与红外》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977741A (en) * | 2017-12-28 | 2019-07-05 | 北京京东尚科信息技术有限公司 | Face identification method, device, system and medium |
| CN108376239A (en) * | 2018-01-25 | 2018-08-07 | 努比亚技术有限公司 | A kind of face identification method, mobile terminal and storage medium |
| CN108764071A (en) * | 2018-05-11 | 2018-11-06 | 四川大学 | It is a kind of based on infrared and visible images real human face detection method and device |
| CN108764071B (en) * | 2018-05-11 | 2021-11-12 | 四川大学 | Real face detection method and device based on infrared and visible light images |
| CN108549886A (en) * | 2018-06-29 | 2018-09-18 | 汉王科技股份有限公司 | A kind of human face in-vivo detection method and device |
| WO2020000908A1 (en) * | 2018-06-29 | 2020-01-02 | 汉王科技股份有限公司 | Method and device for face liveness detection |
| CN109460485A (en) * | 2018-10-12 | 2019-03-12 | 咪咕文化科技有限公司 | A kind of image library method for building up, device and storage medium |
| CN109543640A (en) * | 2018-11-29 | 2019-03-29 | 中国科学院重庆绿色智能技术研究院 | A kind of biopsy method based on image conversion |
| CN109543640B (en) * | 2018-11-29 | 2022-06-17 | 中国科学院重庆绿色智能技术研究院 | Living body detection method based on image conversion |
| CN109961025A (en) * | 2019-03-11 | 2019-07-02 | 烟台市广智微芯智能科技有限责任公司 | A kind of true and false face recognition detection method and detection system based on image degree of skewness |
| CN109961025B (en) * | 2019-03-11 | 2020-01-24 | 烟台市广智微芯智能科技有限责任公司 | True and false face identification and detection method and detection system based on image skewness |
| CN110728215A (en) * | 2019-09-26 | 2020-01-24 | 杭州艾芯智能科技有限公司 | Face living body detection method and device based on infrared image |
| US11869272B2 (en) | 2019-11-21 | 2024-01-09 | Samsung Electronics Co., Ltd. | Liveness test method and apparatus and biometric authentication method and apparatus |
| CN111967296A (en) * | 2020-06-28 | 2020-11-20 | 北京中科虹霸科技有限公司 | Iris living body detection method, entrance guard control method and entrance guard control device |
| CN111967296B (en) * | 2020-06-28 | 2023-12-05 | 北京中科虹霸科技有限公司 | Iris living body detection method, access control method and device |
| CN113628148A (en) * | 2021-09-17 | 2021-11-09 | 福建库克智能科技有限公司 | Infrared image noise reduction method and device |
| CN113628148B (en) * | 2021-09-17 | 2024-05-10 | 福建库克智能科技有限公司 | Method and device for reducing noise of infrared image |
| CN113807329A (en) * | 2021-11-18 | 2021-12-17 | 深圳市沃特沃德软件技术有限公司 | Fusion monitoring method and device and computer equipment |
| CN114092864A (en) * | 2022-01-19 | 2022-02-25 | 湖南信达通信息技术有限公司 | Fake video identification method and device, electronic equipment and computer storage medium |
| CN114092864B (en) * | 2022-01-19 | 2022-04-12 | 湖南信达通信息技术有限公司 | Fake video identification method and device, electronic equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106372615A (en) | Face anti-counterfeiting identification method and apparatus | |
| US11288504B2 (en) | Iris liveness detection for mobile devices | |
| CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
| CN102622588B (en) | Dual-certification face anti-counterfeit method and device | |
| CN105518711B (en) | Biopsy method, In vivo detection system and computer program product | |
| CN105956572A (en) | In vivo face detection method based on convolutional neural network | |
| CN102542281B (en) | Non-contact biometric feature identification method and system | |
| CN107590430A (en) | Biopsy method, device, equipment and storage medium | |
| CN105844206A (en) | Identity authentication method and identity authentication device | |
| CN104700094B (en) | A kind of face identification method for intelligent robot and system | |
| CN104881632A (en) | Hyperspectral face recognition method | |
| WO2021056974A1 (en) | Vein recognition method and apparatus, device, and storage medium | |
| CN107622246A (en) | Face identification method and Related product | |
| US11568681B2 (en) | Iris authentication device, iris authentication method and recording medium | |
| Hossain et al. | Next generation identity verification based on face-gait Biometrics | |
| CN108304800A (en) | A kind of method of Face datection and face alignment | |
| WO2021025627A1 (en) | A transaction processing system and a transaction method based on facial recognition | |
| CN110110606A (en) | The fusion method of visible light neural network based and infrared face image | |
| Galdi et al. | PROTECT: Pervasive and useR fOcused biomeTrics bordEr projeCT–a case study | |
| CN112308035A (en) | Image detection method, image detection device, computer equipment and storage medium | |
| Garg et al. | Biometric authentication using soft biometric traits | |
| Sharma et al. | Lip print recognition for security systems: an up-coming biometric solution | |
| CN115953822A (en) | Face video false distinguishing method and device based on rPPG physiological signal | |
| CN206249452U (en) | A kind of self-help bank's safety-protection system | |
| Pandey et al. | Survey on finger vein recognition using convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170824 Address after: 361008, Xiamen three software park, Fujian Province, 8 North Street, room 2001 Applicant after: Xiamen Central Intelligent Information Technology Co., Ltd. Address before: 361000 Fujian province Xiamen software park two sunrise Road No. 32 403 unit 02 District Applicant before: XIAMEN ZHONGKONG BIOLOGICAL RECOGNITION INFORMATION TECHNOLOGY CO., LTD. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170201 |