CN109086718A - Biopsy method, device, computer equipment and storage medium - Google Patents
Biopsy method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109086718A CN109086718A CN201810869464.4A CN201810869464A CN109086718A CN 109086718 A CN109086718 A CN 109086718A CN 201810869464 A CN201810869464 A CN 201810869464A CN 109086718 A CN109086718 A CN 109086718A
- Authority
- CN
- China
- Prior art keywords
- human face
- face region
- measured
- living body
- 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.)
- 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
- G06V40/168—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
- G06V40/10—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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention relates to biopsy method, device, computer equipment and storage medium, this method includes obtaining facial image；Facial image is detected to obtain human face region to be measured；Human face region to be measured is analyzed, carries out the judgement of living body faces, face living body attack protection and face three-dimensional mask attack protection based on the analysis results, obtains and determines result；Output determines result.The present invention is by obtaining color image and infrared depth image, by carrying out deep learning model inspection face to color image, the screen pixels texture of binding analysis human face region to be measured, and determine whether human face region to be measured meets preset condition using Surf algorithm, living body faces judgement and face living body are carried out to human face region, the attack protection of face three-dimensional mask determines, greatly improve three-dimensional artificial mask, the anti-attack ability of video and general picture, effectively defence mask, three-dimensional artificial face, the attack of video non-living body, greatly improve the accuracy of recognition of face.
Description
Technical field
The present invention relates to In vivo detections, more specifically refer to that biopsy method, device, computer equipment and storage are situated between
Matter.
Background technique
With the continuous development of deep learning and artificial intelligence technology, face identification system is increasingly used in pacifying
Anti-, intelligence new retail, finance, subway, hotel, airport etc. need in the scene of authentication, and such as bank remotely opens an account, nobody
Super quotient is automatically performed payment, access control system by brush face, and the payment of subway brush face, airport carry out testimony of a witness veritification etc. automatically.At these
The application field of high security level especially relates to the fields relevant with money such as brush face payment, in addition to ensuring that authenticatee
Human face similarity degree meet outside the data stored in database, it is also necessary to confirm that authenticatee is a legal biological living,
That is face identification system is required to preventing malice attacker and uses photo, 3D faceform, mask or mobile video
Etc. modes attacked.
Solution to the problems described above is normally referred to as In vivo detection, by judging whether the biological characteristic got is one
It is a have life, at the scene, true people.3D In vivo detection technical products currently on the market generally acknowledge that mature living body is tested not yet
Card scheme, existing 3D In vivo detection technology almost rely on hardware device, such as infrared camera, depth camera, and can only
Still photo attack is taken precautions against, it is bad to 3D mask, HD video attack effect.Chinese patent 201580000356.8 discloses one
Kind biopsy method and equipment, computer program product specifically detect human face action from shooting image, dynamic according to face
Make carry out In vivo detection, this method is easy to be attacked by video or mask.Chinese patent 201610371250.5 discloses one
Kind biopsy method and In vivo detection system, are to be by human face region in a depth image and a RGB color image
No reciprocal correspondence determines whether as human body living body, but the technology does not have good attack protection to mask or 3 D video
Method, in conclusion at present 3D biopsy method static images are attacked it is more effective, to mask and three-dimensional artificial face,
Video attacks no effective ways.
Therefore, it is necessary to design a kind of new method, realize that effectively defence mask, three-dimensional artificial face, video etc. are non-live
Body attack, greatly improves the accuracy of recognition of face.
Summary of the invention
It is an object of the invention to overcome the deficiencies of existing technologies, provide biopsy method, device, computer equipment and
Storage medium.
To achieve the above object, the invention adopts the following technical scheme: biopsy method, comprising:
Obtain facial image；
Facial image is detected to obtain human face region to be measured；
Human face region to be measured is analyzed, it is three-dimensional to carry out living body faces, face living body attack protection and face based on the analysis results
The judgement of mask attack protection obtains and determines result；
Output determines result.
Its further technical solution are as follows: the acquisition facial image, comprising:
Color image and infrared depth image are obtained, to obtain facial image.
Its further technical solution are as follows: described facial image to be detected to obtain human face region to be measured, comprising:
Several color images of continuous acquisition；
Deep learning model inspection face is passed sequentially through to several color images, to obtain the face area in color image
Domain；
Corresponding human face region in infrared depth image is determined according to the human face region of color image, to obtain face to be measured
Region.
Its further technical solution are as follows: the analysis human face region to be measured carries out living body faces, face based on the analysis results
The judgement of living body attack protection and face three-dimensional mask attack protection obtains and determines result, comprising:
Judge the face area for thering is the pixel of depth information to account for infrared depth image in the human face region of infrared depth image
Whether the specific gravity in domain is more than preset threshold；
If so, judging in human face region specified range to be detected with the presence or absence of frame；
If it is not, then analyzing the screen pixels texture of human face region to be measured；
Judge human face region to be measured with the presence or absence of predetermined condition according to screen pixels texture analysis result；
If it is not, determining whether human face region to be measured meets preset condition using Surf algorithm；
If so, the object of human face region to be measured is living body faces, to form judgement result.
Its further technical solution are as follows: it is described to determine whether human face region to be measured meets preset condition using Surf algorithm,
Include:
Obtain the human face region Surf characteristic point of several color images；
Surf characteristic point is matched, to obtain matching result；
Judge whether the matching number in the matching result is greater than matching threshold；
If it is not, then human face region to be measured meets preset condition；
If so, human face region to be measured is unsatisfactory for preset condition.
Its further technical solution are as follows: there is the pixel of depth information to account for face to be measured in the infrared depth image of judgement
After whether the specific gravity in region is more than preset threshold, further includes:
If it is not, then the object of human face region to be measured is non-living body face, to form judgement result.
Its further technical solution are as follows: after whether there is frame in the judgement human face region specified range to be detected,
Further include:
If so, the object of human face region to be measured is non-living body face, to form judgement result.
The present invention also provides living body detection devices, comprising:
Image acquisition unit, for obtaining facial image；
Area acquisition unit, for being detected to facial image to obtain human face region to be measured；
Judging unit carries out living body faces, face living body attack protection for analyzing human face region to be measured based on the analysis results
And the judgement of face three-dimensional mask attack protection, it obtains and determines result；
Output unit determines result for exporting.
The present invention also provides a kind of computer equipment, including memory, processor and it is stored on the memory simultaneously
The computer program that can be run on the processor, the processor realize above-mentioned living body when executing the computer program
Detection method.
The present invention also provides a kind of storage medium, the storage medium is stored with computer program, the computer journey
Sequence includes program instruction, and described program instruction makes the processor execute above-mentioned In vivo detection side when being executed by a processor
Method.
Compared with the prior art, the invention has the advantages that: the present invention is by obtaining color image and infrared depth map
Picture, by color image carry out deep learning model inspection face, the screen pixels texture of binding analysis human face region to be measured,
And determine whether human face region to be measured meets preset condition using Surf algorithm, to human face region carry out living body faces determine with
And the attack protection of face living body, face three-dimensional mask determines, greatly improves the anti-of three-dimensional artificial mask, video and general picture
Attacking ability, effectively defence mask, three-dimensional artificial face, the attack of video non-living body, greatly improve the accuracy of recognition of face.
The invention will be further described in the following with reference to the drawings and specific embodiments.
Detailed description of the invention
Fig. 1 is the application scenario diagram for the biopsy method that the specific embodiment of the invention provides；
Fig. 2 is the flow diagram of biopsy method provided in an embodiment of the present invention；
Fig. 3 is the sub-process schematic diagram of biopsy method provided in an embodiment of the present invention；
Fig. 4 is the sub-process schematic diagram of biopsy method provided in an embodiment of the present invention；
Fig. 5 is the sub-process schematic diagram of biopsy method provided in an embodiment of the present invention；
Fig. 6 is the schematic block diagram of living body detection device provided in an embodiment of the present invention；
Fig. 7 is the schematic block diagram of the area acquisition unit of living body detection device provided in an embodiment of the present invention；
Fig. 8 is the schematic block diagram of the judging unit of living body detection device provided in an embodiment of the present invention；
Fig. 9 is that the three-dimensional mask of living body detection device provided in an embodiment of the present invention determines the schematic block diagram of subelement；
Figure 10 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
In order to more fully understand technology contents of the invention, combined with specific embodiments below to technical solution of the present invention into
One step introduction and explanation, but not limited to this.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this present specification merely for the sake of description specific embodiment
And be not intended to limit the application.As present specification and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in present specification and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Fig. 1 and Fig. 2 are please referred to, Fig. 1 is the application scenarios schematic diagram of biopsy method provided in an embodiment of the present invention.Figure
2 be the schematic flow chart of biopsy method provided in an embodiment of the present invention.The biopsy method can be applied to server
In 20, exist in the form of In vivo detection platform, which can carry out data interaction with user terminal 10.Wherein, user
The user of terminal 10 is usually a certain user using platform, such as the user of payment platform, can pass through user terminal 10
Detection APP to server 20 send facial image, server 20 based on the received facial image and to terminal feed back phase
The judgement result answered.
In addition, above-mentioned activity detection approach can also be applied to mobile terminal, exist in the form of In vivo detection APP,
After user obtains facial image by In vivo detection APP, In vivo detection is carried out according to facial image inside mobile terminal, and show
Show corresponding judgement result.
As shown in Fig. 2, the biopsy method of the embodiment of the present invention includes step S110~S140.
S110, facial image is obtained.
In the present embodiment, facial image refers to the facial image obtained using the shooting of 3D camera.Specifically, can pass through
The detection APP of mobile terminal, which is clicked, obtains facial image, shoots facial image using the 3D camera integrated on mobile terminal.
Specifically, by obtaining color image and infrared depth image, to obtain facial image.3D camera is included
SDK (Software Development Kit, Software Development Kit) calls SDK that can obtain the infrared depth with depth information
Image is spent, spatial depth and infrared image is obtained using the sensor in 3D camera, the frame source of infrared image is first obtained, from frame
Frame reader is opened in source, recycles the cache information that depth image is read out of frame reader, which includes each point
Depth information, and be it is one-dimensional, by the cache information be implanted into infrared image in, to obtain infrared depth image.
In the present embodiment, object passes through two to the distance of camera in the pixel value reflection scene of infrared depth image
The image that the binocular camera of RGB camera or an infrared camera and a RGB camera composition acquires is infrared
Depth image.
S120, facial image is detected to obtain human face region to be measured.
In the present embodiment, human face region to be measured refers to the face that acquisition is analyzed from color image and infrared depth image
Region.In particular it is required that first human face region and background area are distinguished, to improve detection efficiency.
In one embodiment, as shown in figure 3, the step S120 may include step S121~S123.
Several color images of S121, continuous acquisition.
In the present embodiment, several color images are continuously acquired using 3D camera, is generally at least 6.
S122, several color images are passed sequentially through with deep learning model inspection face, to obtain in color image
Human face region.
In the present embodiment, several color images are passed sequentially through into open source MTCNN (Face datection, Multi-task
Cascaded Convolutional Networks) deep learning model inspection face.The deep learning is a kind of machine learning
Method.
Specifically, it during detecting face, first by color image ratio at different zoom, is scaled to different size of
Picture forms the feature pyramid of image；Using full convolutional neural networks, candidate forms and boundary regression vector are obtained, with this
Bounding box returns, and candidate forms are calibrated according to bounding box, utilizes NMS (non-maxima suppression, non maximum
Suppression) method removal overlapping forms；The determining image comprising candidate forms is trained in R-Net network, network
The mode connected entirely is finally selected to be trained.Candidate forms are finely tuned using the regressand value of bounding box vector, recycle NMS removal
It is overlapped forms.One layer of convolution more than network structure ratio R-Net, function and R-Net effect, only in removal overlapping candidate window
While, show five face key point positioning.
S123, corresponding human face region in infrared depth image is determined according to the human face region of color image, with obtain to
Survey human face region.
In the present embodiment, the position of the human face region determined from color image, obtains same in infrared depth image
The human face region of position determines human face region to be measured with this.
S130, analysis human face region to be measured, carry out living body faces, face living body attack protection and face based on the analysis results
The judgement of three-dimensional mask attack protection obtains and determines result.
Judgement, face living body attack protection and the face three-dimensional mask of living body faces are carried out for the human face region to be measured of acquisition
The judgement of attack protection is realized in the case where cooperating on one's own initiative without user, effectively defence mask, three-dimensional artificial face, video
Equal non-living bodies attack, greatly improves the accuracy, ease for use and user experience of face identification system.
In one embodiment, as shown in figure 4, above-mentioned step S130 may include step S131~S137.
S131, judge the people for thering is the pixel of depth information to account for infrared depth image in the human face region of infrared depth image
Whether the specific gravity in face region is more than preset threshold.
In the present embodiment, depth information be obtained according to infrared range image analysis infrared depth image about depth
Information.
Above-mentioned preset threshold is a specific gravity values being set according to actual conditions.If in the face area of color image
There are corresponding depth informations in domain, and are true man by scene analysis, then preliminary judgement is living body faces；By comparing cromogram
The human face region of the human face region of picture and corresponding infrared depth image, if having depth in the human face region of corresponding infrared depth image
The specific gravity for the human face region that the pixel of degree information accounts for infrared depth image was more than 70% (being also possible to other numerical value), then tentatively
The human face region to be measured is determined for candidate living body faces region, wherein 70% is preset threshold, the living body faces area of the candidate
Domain refers to the human face region to be measured having an opportunity as living body faces region.
S132, if it is not, then the object of human face region to be measured be non-living body face, to form judgement result.
If the face area of corresponding depth information or infrared depth image is not present in the human face region of color image
The specific gravity for having the pixel of depth information to account for the human face region of infrared depth image in domain is no more than preset threshold, then preliminary judgement
Human face region to be measured is non-living body face.If it is determined that non-living body face, then detection terminates, and does not need to carry out subsequent judgement,
Directly exporting the judgement result of non-living body face is non-living body face.
S133, if so, judging in human face region specified range to be detected with the presence or absence of frame.
In the present embodiment, nearby it whether there is frame particular by scene analysis human face region, in other embodiments
In, pixel can be used and determine whether, to carry out the judgement of face living body attack protection, to improve the accurate of recognition of face there are frame
Property.
S134, if it is not, then analyzing the screen pixels texture of human face region to be measured.
In the present embodiment, the screen pixels line of human face region to be measured is specifically analyzed based on tamura (textural characteristics)
Reason specifically calculates roughness and contrast using tamura (textural characteristics) algorithm.Roughness is granularity in reflection texture
One amount, is most basic textural characteristics.When two kinds of textural characteristics mode knowledge cell sizes differences, there is larger primitive ruler
Very little mode feels rougher to people.
Firstly, calculating size in color image is 2k×2kThe active window of a pixel, the average intensity value of pixel are as follows:
Wherein, k=0,1 ..., 5, g (i, j) are located at (i, j)
Grey scale pixel value.The mean intensity between window not overlapped in the horizontal and vertical directions to the calculating of each pixel is poor, water
Average equal intensity difference is EK, h(x, y)=| Ak(x+2k-1,y)-Ak(x-2k-1,y)|；Vertical mean intensity difference is EK, v(x, y)=|
Ak(x,y+2k-1)-Ak(x,y-2k-1)|；Wherein for each pixel, so that E value reaches maximum k value and is used to that optimum size is arranged
Sbest(x, y)=2k.Roughness is obtained by calculating average value in entire image, which is
Here m and n refers to the length and width of entire image.
Contrast size is determined by four factors: produce a polarization degree, side for black and white part in gray scale dynamic range, histogram
The period of edge acutance and repeat pattern.Under normal circumstances, contrast refers to the factor of front two, and the formula for obtaining contrast isWherein,μ4It is four squares, σ4It is variance, contrast gives the global measurement of entire image.
In other embodiments, photos all in image library can also successively be denoised, histogram equalization, photo consolidation
Change processing, extracts the HSV histogram feature of each sample.Using the face characteristic directly acquired from camera as positive sample, mark
It signs and is labeled as+1, using the counterfeit face to get off from papery photo or display reproduction as negative sample, label is labeled as -1.It will
All samples are put into support vector machines and are learnt, and such supporting vector chance adjusts inner parameter, are optimal.Work as progress
When detection, whether it is real human face that support vector machines is judged automatically according to the feature of sample.
S135, judged human face region to be measured with the presence or absence of predetermined condition according to screen pixels texture analysis result；
Specifically, from the roughness of texture analysis and contrast can be concluded that the human face region to be measured with the presence or absence of mole
The features such as line, color exception and Facial metamorphosis, fuzzy, so as to form analysis as a result, according to whether have moire fringes, color abnormal and
Whether the features such as Facial metamorphosis, fuzzy determine before camera lens to be true man, to effectively prevent to crack recognition of face with screen reproduction
The phenomenon that occur.
S136, if it is not, determining whether human face region to be measured meets preset condition using Surf algorithm.
In the present embodiment, determined using Surf algorithm face three-dimensional mask attack protection.
In one embodiment, as shown in figure 5, above-mentioned step S136 may include step S136a~S136e.
S136a, the human face region Surf characteristic point for obtaining several color images.
Specifically, by constructing Hessian matrix, all points of interest are generated, the extraction for feature；It is empty to construct scale
Between；Location feature point；The principal direction of assigned characteristics point；Generate feature point description.
S136b, matching Surf characteristic point, to obtain matching result；
In the present embodiment, matching degree is determined by calculating the Euclidean distance between two characteristic points, Euclidean distance is shorter,
The matching degree for representing two characteristic points is better.Matching is additionally added the judgement of Hessian (trace of a matrix) simultaneously, if two characteristic points
Trace of a matrix sign it is identical, the two features contrast change direction having the same is represented, if it is different, illustrating the two
The contrast change direction of characteristic point be it is opposite, even if Euclidean distance be 0, also directly excluded.
Specifically color image 1 and 4, color image 2 and 5, color image 3 and 6 successively carry out human face region
Surf characteristic point is matched.
S136c, judge whether the matching number in the matching result is greater than matching threshold.
In the present embodiment, further determine whether the test object is living body faces according to Feature Points Matching result.Such as
The number of three groups of human face region Corresponding matching characteristic points of fruit is greater than matching threshold, then is determined as non-living body face, the matching threshold
It is 5, certainly, in other embodiments, above-mentioned matching threshold may be other numerical value, according to depending on actual conditions.
S136d, if it is not, then human face region to be measured meets preset condition；
S136e, if so, human face region to be measured is unsatisfactory for preset condition.
S137, if so, human face region to be measured object be living body faces, to form judgement result.
S140, output determine result.
In the present embodiment, will determine that result is exported to user terminal 10 to show.
In one embodiment, after above-mentioned step S133, further includes:
If so, returning to the S132.
In one embodiment, after step S137, further include
If it is not, then returning to the S132.
Above-mentioned biopsy method, by obtaining color image and infrared depth image, by color image into
Row deep learning model inspection face, the screen pixels texture of binding analysis human face region to be measured, and sentenced using Surf algorithm
Whether fixed human face region to be measured meets preset condition, carries out living body faces judgement and face living body, face three to human face region
The attack protection for tieing up mask determines, greatly improves the anti-attack ability of three-dimensional artificial mask, video and general picture, effectively defends
Mask, three-dimensional artificial face, the attack of video non-living body, greatly improve the accuracy of recognition of face.
Referring to Fig. 6, Fig. 6 is the schematic block diagram of living body detection device 200 provided in an embodiment of the present invention, such as Fig. 6 institute
Show, the living body detection device 200, comprising:
Image acquisition unit 201, for obtaining facial image；
Area acquisition unit 202, for being detected to facial image to obtain human face region to be measured；
It is anti-to carry out living body faces, face living body for analyzing human face region to be measured based on the analysis results for judging unit 203
Attack and the judgement of face three-dimensional mask attack protection, obtain and determine result；
Output unit 204 determines result for exporting.
In one embodiment, as shown in fig. 7, above-mentioned area acquisition unit 202 includes:
Image Acquisition subelement 2021 is used for several color images of continuous acquisition；
Detection sub-unit 2022, for passing sequentially through deep learning model inspection face to several color images, to obtain
Take the human face region in color image；
It determines subelement 2023, determines corresponding face in infrared depth image for the human face region according to color image
Region, to obtain human face region to be measured.
In one embodiment, as shown in figure 8, above-mentioned judging unit 203 includes:
Accounting judgment sub-unit 2031 has the pixel of depth information in the human face region for judging infrared depth image
Whether the specific gravity for accounting for the human face region of infrared depth image is more than preset threshold.
Frame determines subelement 2032, for if so, judging in human face region specified range to be detected with the presence or absence of side
Frame.
Texture analysis subelement 2033, for if it is not, then analyzing the screen pixels texture of human face region to be measured.
Texture determines subelement 2034, for judging whether human face region to be measured is deposited according to screen pixels texture analysis result
In predetermined condition.
Three-dimensional mask determines subelement 2035, for if it is not, determining whether human face region to be measured meets using Surf algorithm
Preset condition.
Living body result forms subelement 2036, for if so, the object of human face region to be measured is living body faces, to be formed
Determine result.
Non-living body result formed subelement 2037, for if so, human face region to be measured object be non-living body face, with
It is formed and determines result.
In one embodiment, as shown in figure 9, above-mentioned three-dimensional mask determines that subelement 2035 includes:
Characteristic point obtains module 2035a, for obtaining the human face region Surf characteristic point of several color images
Matching module 2035b, for matching Surf characteristic point, to obtain matching result.
Whether number judgment module 2035c, the matching number for judging in the matching result are greater than matching threshold；If
No, then human face region to be measured meets preset condition；If so, human face region to be measured is unsatisfactory for preset condition.
It should be noted that it is apparent to those skilled in the art that, above-mentioned 400 He of living body detection device
The specific implementation process of each unit can refer to the corresponding description in preceding method embodiment, for convenience of description and succinctly,
Details are not described herein.
Above-mentioned living body detection device 200 can be implemented as a kind of form of computer program, which can be
It is run in computer equipment as shown in Figure 10.
Referring to Fig. 10, Figure 10 is a kind of schematic block diagram of computer equipment provided by the embodiments of the present application.The calculating
Machine equipment 500 can be terminal, be also possible to server, wherein terminal can be smart phone, tablet computer, notebook electricity
Brain, desktop computer, personal digital assistant and wearable device etc. have the electronic equipment of communication function.Server can be independence
Server, be also possible to the server cluster of multiple servers composition.
Refering to fig. 10, which includes processor 302, memory and the net connected by system bus 301
Network interface 305, wherein memory may include non-volatile memory medium 503 and built-in storage 304.
The non-volatile memory medium 303 can storage program area 3031 and computer program 3032.The computer program
3032 include program instruction, which is performed, and processor 302 may make to execute a kind of biopsy method.
The processor 302 is for providing calculating and control ability, to support the operation of entire computer equipment 300.
The built-in storage 304 provides environment for the operation of the computer program 3032 in non-volatile memory medium 303, should
When computer program 3032 is executed by processor 302, processor 302 may make to execute a kind of biopsy method.
The network interface 305 is used to carry out network communication with other equipment.It will be understood by those skilled in the art that in Figure 10
The structure shown, only the block diagram of part-structure relevant to application scheme, does not constitute and is applied to application scheme
The restriction of computer equipment 300 thereon, specific computer equipment 300 may include more more or fewer than as shown in the figure
Component perhaps combines certain components or with different component layouts.
Wherein, the processor 302 is for running computer program 3032 stored in memory, to realize following step
It is rapid:
Obtain facial image；
Facial image is detected to obtain human face region to be measured；
Human face region to be measured is analyzed, it is three-dimensional to carry out living body faces, face living body attack protection and face based on the analysis results
The judgement of mask attack protection obtains and determines result；
Output determines result.
In one embodiment, processor 302 is implemented as follows step when realizing the acquisition facial image step:
Color image and infrared depth image are obtained, to obtain facial image.
In one embodiment, processor 302 is realizing described detected to facial image to obtain human face region to be measured
When step, it is implemented as follows step:
Several color images of continuous acquisition；
Deep learning model inspection face is passed sequentially through to several color images, to obtain the face area in color image
Domain；
Corresponding human face region in infrared depth image is determined according to the human face region of color image, to obtain face to be measured
Region.
In one embodiment, processor 302 is realizing the analysis human face region to be measured, carries out living body based on the analysis results
The judgement of face, face living body attack protection and face three-dimensional mask attack protection, when obtaining judgement result step, specific implementation is such as
Lower step:
Judge the face area for thering is the pixel of depth information to account for infrared depth image in the human face region of infrared depth image
Whether the specific gravity in domain is more than preset threshold；
If so, judging in human face region specified range to be detected with the presence or absence of frame；
If it is not, then analyzing the screen pixels texture of human face region to be measured；
Judge human face region to be measured with the presence or absence of predetermined condition according to screen pixels texture analysis result；
If it is not, determining whether human face region to be measured meets preset condition using Surf algorithm；
If so, the object of human face region to be measured is living body faces, to form judgement result.
In one embodiment, processor 302 determines whether human face region to be measured meets in the realization use Surf algorithm
When preset condition step, it is implemented as follows step:
Obtain the human face region Surf characteristic point of several color images；
Surf characteristic point is matched, to obtain matching result；
Judge whether the matching number in the matching result is greater than matching threshold；
If it is not, then human face region to be measured meets preset condition；
If so, human face region to be measured is unsatisfactory for preset condition.
In one embodiment, processor 302 is realizing the pixel for having depth information in the infrared depth image of judgement
Account for human face region to be measured specific gravity whether be more than preset threshold step after, also realization following steps:
If it is not, then the object of human face region to be measured is non-living body face, to form judgement result.
In one embodiment, processor 302 whether there is in the realization judgement human face region specified range to be detected
After frame step, following steps are also realized:
If so, the object of human face region to be measured is non-living body face, to form judgement result.
It should be appreciated that in the embodiment of the present application, processor 302 can be central processing unit (Central
Processing Unit, CPU), which 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) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
Person's processor is also possible to any conventional processor etc..
Those of ordinary skill in the art will appreciate that be realize above-described embodiment method in all or part of the process,
It is that relevant hardware can be instructed to complete by computer program.The computer program includes program instruction, computer journey
Sequence can be stored in a storage medium, which is computer readable storage medium.The program instruction is by the department of computer science
At least one processor in system executes, to realize the process step of the embodiment of the above method.
Therefore, the present invention also provides a kind of storage mediums.The storage medium can be computer readable storage medium.This is deposited
Storage media is stored with computer program, and wherein computer program includes program instruction.The program instruction makes when being executed by processor
Processor executes following steps:
Obtain facial image；
Facial image is detected to obtain human face region to be measured；
Human face region to be measured is analyzed, it is three-dimensional to carry out living body faces, face living body attack protection and face based on the analysis results
The judgement of mask attack protection obtains and determines result；
Output determines result.
In one embodiment, the processor realizes the acquisition facial image step executing described program instruction
When, it is implemented as follows step: color image and infrared depth image is obtained, to obtain facial image.
In one embodiment, the processor is realized and described is detected to facial image executing described program instruction
When obtaining human face region step to be measured, it is implemented as follows step:
Several color images of continuous acquisition；
Deep learning model inspection face is passed sequentially through to several color images, to obtain the face area in color image
Domain；
Corresponding human face region in infrared depth image is determined according to the human face region of color image, to obtain face to be measured
Region.
In one embodiment, the processor realizes the analysis human face region to be measured executing described program instruction,
The judgement for carrying out living body faces, face living body attack protection and face three-dimensional mask attack protection based on the analysis results, obtains and determines
When result step, it is implemented as follows step:
Judge the face area for thering is the pixel of depth information to account for infrared depth image in the human face region of infrared depth image
Whether the specific gravity in domain is more than preset threshold；
If so, judging in human face region specified range to be detected with the presence or absence of frame；
If it is not, then analyzing the screen pixels texture of human face region to be measured；
Judge human face region to be measured with the presence or absence of predetermined condition according to screen pixels texture analysis result；
If it is not, determining whether human face region to be measured meets preset condition using Surf algorithm；
If so, the object of human face region to be measured is living body faces, to form judgement result.
In one embodiment, the processor execute described program instruction and realize it is described using Surf algorithm determine to
When whether survey human face region meets preset condition step, it is implemented as follows step:
Obtain the human face region Surf characteristic point of several color images；
Surf characteristic point is matched, to obtain matching result；
Judge whether the matching number in the matching result is greater than matching threshold；
If it is not, then human face region to be measured meets preset condition；
If so, human face region to be measured is unsatisfactory for preset condition.
In one embodiment, the processor is realized in the instruction of execution described program in the infrared depth image of judgement
Have the pixel of depth information account for human face region to be measured specific gravity whether be more than preset threshold step after, also realize following step
It is rapid:
If it is not, then the object of human face region to be measured is non-living body face, to form judgement result.
In one embodiment, the processor realizes the judgement human face region to be detected executing described program instruction
With the presence or absence of after frame step in specified range, following steps are also realized:
If so, the object of human face region to be measured is non-living body face, to form judgement result.
The storage medium can be USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), magnetic disk
Or the various computer readable storage mediums that can store program code such as CD.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary.For example, the division of each unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation.Such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.
The steps in the embodiment of the present invention can be sequentially adjusted, merged and deleted according to actual needs.This hair
Unit in bright embodiment device can be combined, divided and deleted according to actual needs.In addition, in each implementation of the present invention
Each functional unit in example can integrate in one processing unit, is also possible to each unit and physically exists alone, can also be with
It is that two or more units are integrated in one unit.
If the integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in one storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing skill
The all or part of part or the technical solution that art contributes can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, terminal or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
It is above-mentioned that technology contents of the invention are only further illustrated with embodiment, in order to which reader is easier to understand, but not
It represents embodiments of the present invention and is only limitted to this, any technology done according to the present invention extends or recreation, by of the invention
Protection.Protection scope of the present invention is subject to claims.
Claims (10)
1. biopsy method characterized by comprising
Obtain facial image；
Facial image is detected to obtain human face region to be measured；
Human face region to be measured is analyzed, carries out living body faces, face living body attack protection and face three-dimensional mask based on the analysis results
The judgement of attack protection obtains and determines result；
Output determines result.
2. biopsy method according to claim 1, which is characterized in that the acquisition facial image, comprising:
Color image and infrared depth image are obtained, to obtain facial image.
3. biopsy method according to claim 2, which is characterized in that described to be detected facial image to obtain
Human face region to be measured, comprising:
Several color images of continuous acquisition；
Deep learning model inspection face is passed sequentially through to several color images, to obtain the human face region in color image；
Corresponding human face region in infrared depth image is determined according to the human face region of color image, to obtain face area to be measured
Domain.
4. biopsy method according to claim 3, which is characterized in that analysis human face region to be measured, according to point
The judgement that result carries out living body faces, face living body attack protection and face three-dimensional mask attack protection is analysed, obtains and determines as a result, packet
It includes:
Judge the human face region for thering is the pixel of depth information to account for infrared depth image in the human face region of infrared depth image
Whether specific gravity is more than preset threshold；
If so, judging in human face region specified range to be detected with the presence or absence of frame；
If it is not, then analyzing the screen pixels texture of human face region to be measured；
Judge human face region to be measured with the presence or absence of predetermined condition according to screen pixels texture analysis result；
If it is not, determining whether human face region to be measured meets preset condition using Surf algorithm；
If so, the object of human face region to be measured is living body faces, to form judgement result.
5. biopsy method according to claim 4, which is characterized in that described to determine face to be measured using Surf algorithm
Whether region meets preset condition, comprising:
Obtain the human face region Surf characteristic point of several color images；
Surf characteristic point is matched, to obtain matching result；
Judge whether the matching number in the matching result is greater than matching threshold；
If it is not, then human face region to be measured meets preset condition；
If so, human face region to be measured is unsatisfactory for preset condition.
6. biopsy method according to claim 4, which is characterized in that have depth in the infrared depth image of judgement
After whether the specific gravity that the pixel of information accounts for human face region to be measured is more than preset threshold, further includes:
If it is not, then the object of human face region to be measured is non-living body face, to form judgement result.
7. biopsy method according to claim 4, which is characterized in that the judgement human face region to be detected specifies model
With the presence or absence of after frame in enclosing, further includes:
If so, the object of human face region to be measured is non-living body face, to form judgement result.
8. living body detection device characterized by comprising
Image acquisition unit, for obtaining facial image；
Area acquisition unit, for being detected to facial image to obtain human face region to be measured；
Judging unit, for analyzing human face region to be measured, based on the analysis results carry out living body faces, face living body attack protection and
The judgement of face three-dimensional mask attack protection obtains and determines result；
Output unit determines result for exporting.
9. a kind of computer equipment, which is characterized in that including memory, processor and be stored on the memory and can be in institute
The computer program run on processor is stated, the processor is realized when executing the computer program as in claim 1 to 7
Biopsy method described in any one.
10. a kind of storage medium, which is characterized in that the storage medium is stored with computer program, the computer program packet
Program instruction is included, described program instruction makes the processor execute such as claim 1 to 7 any one when being executed by a processor
The biopsy method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810869464.4A CN109086718A (en) | 2018-08-02 | 2018-08-02 | Biopsy method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810869464.4A CN109086718A (en) | 2018-08-02 | 2018-08-02 | Biopsy method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109086718A true CN109086718A (en) | 2018-12-25 |
Family
ID=64833790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810869464.4A Pending CN109086718A (en) | 2018-08-02 | 2018-08-02 | Biopsy method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086718A (en) |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109508706A (en) * | 2019-01-04 | 2019-03-22 | 江苏正赫通信息科技有限公司 | A kind of silent biopsy method based on micro- Expression Recognition and noninductive recognition of face |
| CN109685018A (en) * | 2018-12-26 | 2019-04-26 | 深圳市捷顺科技实业股份有限公司 | A kind of testimony of a witness method of calibration, system and relevant device |
| CN109858471A (en) * | 2019-04-03 | 2019-06-07 | 深圳市华付信息技术有限公司 | Biopsy method, device and computer equipment based on picture quality |
| CN109961062A (en) * | 2019-04-16 | 2019-07-02 | 北京迈格威科技有限公司 | Image-recognizing method, device, terminal and readable storage medium storing program for executing |
| CN109977929A (en) * | 2019-04-28 | 2019-07-05 | 北京超维度计算科技有限公司 | A kind of face identification system and method based on TOF |
| CN110059607A (en) * | 2019-04-11 | 2019-07-26 | 深圳市华付信息技术有限公司 | Living body multiple detection method, device, computer equipment and storage medium |
| CN110070062A (en) * | 2019-04-28 | 2019-07-30 | 北京超维度计算科技有限公司 | A kind of system and method for the recognition of face based on binocular active infrared |
| CN110084135A (en) * | 2019-04-03 | 2019-08-02 | 平安科技（深圳）有限公司 | Face identification method, device, computer equipment and storage medium |
| CN110222573A (en) * | 2019-05-07 | 2019-09-10 | 平安科技（深圳）有限公司 | Face identification method, device, computer equipment and storage medium |
| CN110659617A (en) * | 2019-09-26 | 2020-01-07 | 杭州艾芯智能科技有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN110688967A (en) * | 2019-09-30 | 2020-01-14 | 上海依图信息技术有限公司 | System and method for static human face living body detection |
| CN111046845A (en) * | 2019-12-25 | 2020-04-21 | 上海骏聿数码科技有限公司 | Living body detection method, device and system |
| CN111079576A (en) * | 2019-11-30 | 2020-04-28 | 腾讯科技（深圳）有限公司 | Living body detection method, living body detection device, living body detection equipment and storage medium |
| CN111160233A (en) * | 2019-12-27 | 2020-05-15 | 中国科学院苏州纳米技术与纳米仿生研究所 | Human face in-vivo detection method, medium and system based on three-dimensional imaging assistance |
| CN111241949A (en) * | 2020-01-03 | 2020-06-05 | 中科智云科技有限公司 | Image recognition method and device, electronic equipment and readable storage medium |
| CN111582155A (en) * | 2020-05-07 | 2020-08-25 | 腾讯科技（深圳）有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN111666884A (en) * | 2020-06-08 | 2020-09-15 | 睿云联(厦门)网络通讯技术有限公司 | Living body detection method, living body detection device, computer-readable medium, and electronic apparatus |
| CN111699678A (en) * | 2019-01-16 | 2020-09-22 | 深圳市汇顶科技股份有限公司 | Anti-spoof facial ID sensing using two cameras |
| CN111767845A (en) * | 2020-06-29 | 2020-10-13 | 京东数字科技控股有限公司 | Certificate identification method and device |
| CN111767760A (en) * | 2019-04-01 | 2020-10-13 | 北京市商汤科技开发有限公司 | Living body detection method and apparatus, electronic device, and storage medium |
| CN111879724A (en) * | 2020-08-05 | 2020-11-03 | 中国工程物理研究院流体物理研究所 | Human skin mask identification method and system based on near infrared spectrum imaging |
| CN112036376A (en) * | 2020-10-01 | 2020-12-04 | 深圳奥比中光科技有限公司 | Method and device for detecting infrared image and depth image and face recognition system |
| CN112052729A (en) * | 2020-07-30 | 2020-12-08 | 广州市标准化研究院 | Intelligent dynamic high-definition video detection method and system based on face recognition |
| CN112084915A (en) * | 2020-08-31 | 2020-12-15 | 支付宝(杭州)信息技术有限公司 | Model training method, living body detection method, device and electronic equipment |
| CN112183454A (en) * | 2020-10-15 | 2021-01-05 | 北京紫光展锐通信技术有限公司 | Image detection method and device, storage medium and terminal |
| CN112215045A (en) * | 2019-07-12 | 2021-01-12 | 普天信息技术有限公司 | Living body detection method and device |
| CN112434547A (en) * | 2019-08-26 | 2021-03-02 | 中国移动通信集团广东有限公司 | User identity auditing method and device |
| CN112651311A (en) * | 2020-12-15 | 2021-04-13 | 展讯通信(天津)有限公司 | Face recognition method and related equipment |
| CN112883918A (en) * | 2021-03-22 | 2021-06-01 | 深圳市百富智能新技术有限公司 | Face detection method and device, terminal equipment and computer readable storage medium |
| CN112883762A (en) * | 2019-11-29 | 2021-06-01 | 广州慧睿思通科技股份有限公司 | Living body detection method, device, system and storage medium |
| CN113343889A (en) * | 2021-06-23 | 2021-09-03 | 的卢技术有限公司 | Face recognition system based on silence live body detection |
| CN113642428A (en) * | 2021-07-29 | 2021-11-12 | 北京百度网讯科技有限公司 | Face living body detection method and device, electronic equipment and storage medium |
| CN113723243A (en) * | 2021-08-20 | 2021-11-30 | 南京华图信息技术有限公司 | Thermal infrared image face recognition method for wearing mask and application |
| WO2022120532A1 (en) * | 2020-12-07 | 2022-06-16 | Huawei Technologies Co., Ltd. | Presentation attack detection |
| CN112036376B (en) * | 2020-10-01 | 2024-05-31 | 奥比中光科技集团股份有限公司 | Method, device and face recognition system for detecting infrared image and depth image |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385578A (en) * | 2010-08-27 | 2012-03-21 | 腾讯科技（深圳）有限公司 | Picture searching method and device |
| CN102622588A (en) * | 2012-03-08 | 2012-08-01 | 无锡数字奥森科技有限公司 | Dual-certification face anti-counterfeit method and device |
| CN103310460A (en) * | 2013-06-24 | 2013-09-18 | 安科智慧城市技术（中国）有限公司 | Image characteristic extraction method and system |
| CN103426186A (en) * | 2013-09-05 | 2013-12-04 | 山东大学 | Improved SURF fast matching method |
| CN103942540A (en) * | 2014-04-10 | 2014-07-23 | 杭州景联文科技有限公司 | False fingerprint detection algorithm based on curvelet texture analysis and SVM-KNN classification |
| CN105023010A (en) * | 2015-08-17 | 2015-11-04 | 中国科学院半导体研究所 | Face living body detection method and system |
| CN105354558A (en) * | 2015-11-23 | 2016-02-24 | 河北工业大学 | Face image matching method |
| CN105512632A (en) * | 2015-12-09 | 2016-04-20 | 北京旷视科技有限公司 | In vivo detection method and device |
| CN105518711A (en) * | 2015-06-29 | 2016-04-20 | 北京旷视科技有限公司 | In-vivo detection method, in-vivo detection system, and computer program product |
| CN107590430A (en) * | 2017-07-26 | 2018-01-16 | 百度在线网络技术（北京）有限公司 | Biopsy method, device, equipment and storage medium |
| CN107688775A (en) * | 2017-07-11 | 2018-02-13 | 浙江新再灵科技股份有限公司 | Binocular camera recognition of face right discriminating system and method based on elevator scene |
| KR20180039885A (en) * | 2016-10-11 | 2018-04-19 | 인하대학교 산학협력단 | Complexity Reduction Method of SURF algorithm based on Frame Difference in the Mobile GPU environment |
-
2018
- 2018-08-02 CN CN201810869464.4A patent/CN109086718A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385578A (en) * | 2010-08-27 | 2012-03-21 | 腾讯科技（深圳）有限公司 | Picture searching method and device |
| CN102622588A (en) * | 2012-03-08 | 2012-08-01 | 无锡数字奥森科技有限公司 | Dual-certification face anti-counterfeit method and device |
| CN103310460A (en) * | 2013-06-24 | 2013-09-18 | 安科智慧城市技术（中国）有限公司 | Image characteristic extraction method and system |
| CN103426186A (en) * | 2013-09-05 | 2013-12-04 | 山东大学 | Improved SURF fast matching method |
| CN103942540A (en) * | 2014-04-10 | 2014-07-23 | 杭州景联文科技有限公司 | False fingerprint detection algorithm based on curvelet texture analysis and SVM-KNN classification |
| CN105518711A (en) * | 2015-06-29 | 2016-04-20 | 北京旷视科技有限公司 | In-vivo detection method, in-vivo detection system, and computer program product |
| CN105023010A (en) * | 2015-08-17 | 2015-11-04 | 中国科学院半导体研究所 | Face living body detection method and system |
| CN105354558A (en) * | 2015-11-23 | 2016-02-24 | 河北工业大学 | Face image matching method |
| CN105512632A (en) * | 2015-12-09 | 2016-04-20 | 北京旷视科技有限公司 | In vivo detection method and device |
| KR20180039885A (en) * | 2016-10-11 | 2018-04-19 | 인하대학교 산학협력단 | Complexity Reduction Method of SURF algorithm based on Frame Difference in the Mobile GPU environment |
| CN107688775A (en) * | 2017-07-11 | 2018-02-13 | 浙江新再灵科技股份有限公司 | Binocular camera recognition of face right discriminating system and method based on elevator scene |
| CN107590430A (en) * | 2017-07-26 | 2018-01-16 | 百度在线网络技术（北京）有限公司 | Biopsy method, device, equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| ZINELABIDINE BOULKENAFET等: "Face Antispoofing Using Speeded-Up Robust Features and Fisher Vector Encoding", 《IEEE SIGNAL PROCESSING LETTERS》 * |
| 刘华成: "人脸活体检测关键技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 栾悉道 等: "《多媒体情报处理技术》", 31 May 2016 * |
Cited By (52)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109685018A (en) * | 2018-12-26 | 2019-04-26 | 深圳市捷顺科技实业股份有限公司 | A kind of testimony of a witness method of calibration, system and relevant device |
| CN109508706A (en) * | 2019-01-04 | 2019-03-22 | 江苏正赫通信息科技有限公司 | A kind of silent biopsy method based on micro- Expression Recognition and noninductive recognition of face |
| CN109508706B (en) * | 2019-01-04 | 2020-05-05 | 江苏正赫通信息科技有限公司 | Silence living body detection method based on micro-expression recognition and non-sensory face recognition |
| US11367314B2 (en) | 2019-01-16 | 2022-06-21 | Shenzhen GOODIX Technology Co., Ltd. | Anti-spoofing face ID sensing based on retro-reflection |
| US11403884B2 (en) | 2019-01-16 | 2022-08-02 | Shenzhen GOODIX Technology Co., Ltd. | Anti-spoofing face ID sensing |
| CN111699678A (en) * | 2019-01-16 | 2020-09-22 | 深圳市汇顶科技股份有限公司 | Anti-spoof facial ID sensing using two cameras |
| CN111767760A (en) * | 2019-04-01 | 2020-10-13 | 北京市商汤科技开发有限公司 | Living body detection method and apparatus, electronic device, and storage medium |
| CN109858471A (en) * | 2019-04-03 | 2019-06-07 | 深圳市华付信息技术有限公司 | Biopsy method, device and computer equipment based on picture quality |
| CN110084135A (en) * | 2019-04-03 | 2019-08-02 | 平安科技（深圳）有限公司 | Face identification method, device, computer equipment and storage medium |
| CN110084135B (en) * | 2019-04-03 | 2024-04-23 | 平安科技（深圳）有限公司 | Face recognition method, device, computer equipment and storage medium |
| CN110059607A (en) * | 2019-04-11 | 2019-07-26 | 深圳市华付信息技术有限公司 | Living body multiple detection method, device, computer equipment and storage medium |
| CN109961062A (en) * | 2019-04-16 | 2019-07-02 | 北京迈格威科技有限公司 | Image-recognizing method, device, terminal and readable storage medium storing program for executing |
| CN109977929A (en) * | 2019-04-28 | 2019-07-05 | 北京超维度计算科技有限公司 | A kind of face identification system and method based on TOF |
| CN110070062A (en) * | 2019-04-28 | 2019-07-30 | 北京超维度计算科技有限公司 | A kind of system and method for the recognition of face based on binocular active infrared |
| CN110222573B (en) * | 2019-05-07 | 2024-05-28 | 平安科技（深圳）有限公司 | Face recognition method, device, computer equipment and storage medium |
| CN110222573A (en) * | 2019-05-07 | 2019-09-10 | 平安科技（深圳）有限公司 | Face identification method, device, computer equipment and storage medium |
| CN112215045A (en) * | 2019-07-12 | 2021-01-12 | 普天信息技术有限公司 | Living body detection method and device |
| CN112434547B (en) * | 2019-08-26 | 2023-11-14 | 中国移动通信集团广东有限公司 | User identity auditing method and device |
| CN112434547A (en) * | 2019-08-26 | 2021-03-02 | 中国移动通信集团广东有限公司 | User identity auditing method and device |
| CN110659617A (en) * | 2019-09-26 | 2020-01-07 | 杭州艾芯智能科技有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN110688967A (en) * | 2019-09-30 | 2020-01-14 | 上海依图信息技术有限公司 | System and method for static human face living body detection |
| CN112883762A (en) * | 2019-11-29 | 2021-06-01 | 广州慧睿思通科技股份有限公司 | Living body detection method, device, system and storage medium |
| CN111079576A (en) * | 2019-11-30 | 2020-04-28 | 腾讯科技（深圳）有限公司 | Living body detection method, living body detection device, living body detection equipment and storage medium |
| CN111079576B (en) * | 2019-11-30 | 2023-07-28 | 腾讯科技（深圳）有限公司 | Living body detection method, living body detection device, living body detection equipment and storage medium |
| CN111046845A (en) * | 2019-12-25 | 2020-04-21 | 上海骏聿数码科技有限公司 | Living body detection method, device and system |
| CN111160233A (en) * | 2019-12-27 | 2020-05-15 | 中国科学院苏州纳米技术与纳米仿生研究所 | Human face in-vivo detection method, medium and system based on three-dimensional imaging assistance |
| CN111160233B (en) * | 2019-12-27 | 2023-04-18 | 中国科学院苏州纳米技术与纳米仿生研究所 | Human face in-vivo detection method, medium and system based on three-dimensional imaging assistance |
| CN111241949B (en) * | 2020-01-03 | 2021-12-14 | 中科智云科技有限公司 | Image recognition method and device, electronic equipment and readable storage medium |
| CN111241949A (en) * | 2020-01-03 | 2020-06-05 | 中科智云科技有限公司 | Image recognition method and device, electronic equipment and readable storage medium |
| CN111582155B (en) * | 2020-05-07 | 2024-02-09 | 腾讯科技（深圳）有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN111582155A (en) * | 2020-05-07 | 2020-08-25 | 腾讯科技（深圳）有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN111666884B (en) * | 2020-06-08 | 2023-08-25 | 睿云联(厦门)网络通讯技术有限公司 | Living body detection method, living body detection device, computer readable medium and electronic equipment |
| CN111666884A (en) * | 2020-06-08 | 2020-09-15 | 睿云联(厦门)网络通讯技术有限公司 | Living body detection method, living body detection device, computer-readable medium, and electronic apparatus |
| CN111767845A (en) * | 2020-06-29 | 2020-10-13 | 京东数字科技控股有限公司 | Certificate identification method and device |
| CN111767845B (en) * | 2020-06-29 | 2024-03-05 | 京东科技控股股份有限公司 | Certificate identification method and device |
| CN112052729A (en) * | 2020-07-30 | 2020-12-08 | 广州市标准化研究院 | Intelligent dynamic high-definition video detection method and system based on face recognition |
| CN112052729B (en) * | 2020-07-30 | 2024-04-16 | 广州市标准化研究院 | Intelligent dynamic high-definition video detection method and system based on face recognition |
| CN111879724A (en) * | 2020-08-05 | 2020-11-03 | 中国工程物理研究院流体物理研究所 | Human skin mask identification method and system based on near infrared spectrum imaging |
| CN112084915A (en) * | 2020-08-31 | 2020-12-15 | 支付宝(杭州)信息技术有限公司 | Model training method, living body detection method, device and electronic equipment |
| CN112036376B (en) * | 2020-10-01 | 2024-05-31 | 奥比中光科技集团股份有限公司 | Method, device and face recognition system for detecting infrared image and depth image |
| CN112036376A (en) * | 2020-10-01 | 2020-12-04 | 深圳奥比中光科技有限公司 | Method and device for detecting infrared image and depth image and face recognition system |
| CN112183454A (en) * | 2020-10-15 | 2021-01-05 | 北京紫光展锐通信技术有限公司 | Image detection method and device, storage medium and terminal |
| WO2022120532A1 (en) * | 2020-12-07 | 2022-06-16 | Huawei Technologies Co., Ltd. | Presentation attack detection |
| WO2022127480A1 (en) * | 2020-12-15 | 2022-06-23 | 展讯通信(天津)有限公司 | Facial recognition method and related device |
| CN112651311A (en) * | 2020-12-15 | 2021-04-13 | 展讯通信(天津)有限公司 | Face recognition method and related equipment |
| CN112883918B (en) * | 2021-03-22 | 2024-03-19 | 深圳市百富智能新技术有限公司 | Face detection method, face detection device, terminal equipment and computer readable storage medium |
| CN112883918A (en) * | 2021-03-22 | 2021-06-01 | 深圳市百富智能新技术有限公司 | Face detection method and device, terminal equipment and computer readable storage medium |
| CN113343889A (en) * | 2021-06-23 | 2021-09-03 | 的卢技术有限公司 | Face recognition system based on silence live body detection |
| CN113642428B (en) * | 2021-07-29 | 2022-09-27 | 北京百度网讯科技有限公司 | Face living body detection method and device, electronic equipment and storage medium |
| CN113642428A (en) * | 2021-07-29 | 2021-11-12 | 北京百度网讯科技有限公司 | Face living body detection method and device, electronic equipment and storage medium |
| CN113723243A (en) * | 2021-08-20 | 2021-11-30 | 南京华图信息技术有限公司 | Thermal infrared image face recognition method for wearing mask and application |
| CN113723243B (en) * | 2021-08-20 | 2024-05-17 | 南京华图信息技术有限公司 | Face recognition method of thermal infrared image of wearing mask and application |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086718A (en) | Biopsy method, device, computer equipment and storage medium | |
| CN105518709B (en) | The method, system and computer program product of face for identification | |
| CN108416336B (en) | A kind of method and system of intelligence community recognition of face | |
| CN108319953B (en) | Occlusion detection method and device, electronic equipment and the storage medium of target object | |
| Kim et al. | Salient region detection via high-dimensional color transform | |
| EP1693782B1 (en) | Method for facial features detection | |
| Jian et al. | Visual-patch-attention-aware saliency detection | |
| CN108549886A (en) | A kind of human face in-vivo detection method and device | |
| Li et al. | Finding the secret of image saliency in the frequency domain | |
| CN103914676B (en) | A kind of method and apparatus used in recognition of face | |
| US7715596B2 (en) | Method for controlling photographs of people | |
| CN103902977B (en) | Face identification method and device based on Gabor binary patterns | |
| CN111626163B (en) | Human face living body detection method and device and computer equipment | |
| US20180034852A1 (en) | Anti-spoofing system and methods useful in conjunction therewith | |
| CN112052831B (en) | Method, device and computer storage medium for face detection | |
| WO2019061658A1 (en) | Method and device for positioning eyeglass, and storage medium | |
| CN108171158A (en) | Biopsy method, device, electronic equipment and storage medium | |
| CN109284673A (en) | Method for tracing object and device, electronic equipment and storage medium | |
| JP2015106197A (en) | Image processing device and image processing method | |
| Feng et al. | Image shadow detection and removal based on region matching of intelligent computing | |
| Feng et al. | HOSO: Histogram of surface orientation for RGB-D salient object detection | |
| Datta | Credit Card Processing Using Cell Phone Images | |
| Thomas et al. | Real Time Face Mask Detection and Recognition using Python | |
| CN112766175B (en) | Living body detection method, living body detection device and nonvolatile storage medium | |
| Oh et al. | Saliency detection using centroid weight map |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181225 |
|
| RJ01 | Rejection of invention patent application after publication |