CN105184277A - Living body human face recognition method and device - Google Patents
Living body human face recognition method and device Download PDFInfo
- Publication number
- CN105184277A CN105184277A CN201510629903.0A CN201510629903A CN105184277A CN 105184277 A CN105184277 A CN 105184277A CN 201510629903 A CN201510629903 A CN 201510629903A CN 105184277 A CN105184277 A CN 105184277A
- Authority
- CN
- China
- Prior art keywords
- eyes
- image
- blinkpunkt
- facial image
- iris
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/167—Detection; Localisation; Normalisation using comparisons between temporally consecutive images
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General 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)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the technical field of identity verification, and particularly relates to a living body human face recognition method, a device and a system. The method comprises steps: multiple human face images are acquired instantly; according to the human face images, a fixation point of at least one eye in each human face image or a motion track of the fixation point is acquired; according to the fixation point of the eye or the motion track of the fixation point, whether the eye moves according to a hint is judged; if yes, living body verification is passed. According to the method, when a user carries out facial feature verification, the eye moves according to the hint; as facial features and eye moving data are extracted from the same picture or one group of pictures or video, an illegal logon person can not cheat the verification device by using a face image or video prepared in advance, and thus, the method can judge that the user agrees to the face features, and the face information is from the living body in reality.
Description
Technical field
The present invention relates to identity validation technology field, in particular to a kind of living body faces recognition methods and device.
Background technology
At present, facial recognition techniques is widely used in the authentication in Security Login System.Current facial recognition techniques is generally the mug shot by image capture device Real-time Obtaining active user, the mug shot of Real-time Obtaining and the mug shot prestored before are carried out the comparison distributed based on the characteristic sum of face, if comparison is consistent, then authentication is passed through.
But in the process of carrying out face recognition, illegal registrant can by forging face " deception " camera or other image capture devices, and the photo making image capture device obtain is not living body faces photo.Such as use before the human face photo of registrant or face video fragment be placed in image capture device, the mug shot of the active user that image capture device obtains is come from photo or video segment actually, or, illegal registrant can also forge three-dimensional face model, before this three-dimensional face model is placed in image capture device, the human face photo that now image capture device obtains is the photo of three-dimensional face model, but when carrying out the comparison distributed based on the characteristic sum of face, this point cannot be discovered, this anti-counterfeit capability just causing identification system is weak, the problem that security is low.
Summary of the invention
In view of this, the object of the embodiment of the present invention is to provide a kind of personal identification method and device, can identify whether the human face photo obtained from image capture device comes from the live body people reality, increase the anti-counterfeit capability of identification system, improve the security of system.
First aspect, embodiments provides a kind of living body faces recognition methods, comprising:
Multiple facial images of instant acquisition;
According to described facial image, obtain the blinkpunkt of at least one eyes or the movement locus of blinkpunkt in each facial image;
According to the blinkpunkt of described eyes or the movement locus of blinkpunkt, judge that whether described eyes are according to prompting campaign;
If judged result is yes, then verified by live body.
In conjunction with first aspect, embodiments provide the first possible embodiment of first aspect,
Judge whether described eyes carry out motion according to prompting and comprise following at least one:
That points out eyes to watch attentively to user in advance is positioned at extraneous target fiducials object, and in the process of taking pictures, whether the blinkpunkt of eyes aims at described target fiducials object respectively in multiple facial images;
In the process of taking pictures, shown the reference body of movement locus random variation by display screen to user, whether the movement locus of the blinkpunkt that described eyes are formed in multiple facial images is consistent with the movement locus of described target fiducials object;
In the process of taking pictures, be presented at multiple random site by display screen to user to occur successively, and the target fiducials object disappeared after Preset Time after each appearance, the blinkpunkt described target fiducials object that whether aligned position is random respectively in multiple facial images of described eyes;
In the process of taking pictures, show multiple reference body to user, the part in multiple described reference body pointed out to user as target fiducials object, whether the blinkpunkt of described eyes aims at described target fiducials object respectively in multiple facial images;
In the process of taking pictures, show Password Input panel to user, whether the blinkpunkt of eyes aims at default password successively in multiple facial images is being watched the correspondence position on Password Input panel attentively.
In conjunction with first aspect, embodiments provide the embodiment that the second of first aspect is possible, described instant acquisition at least one facial image, specifically comprises:
Obtain the original image that individual or multiple include face;
According to described original image, carry out Face datection, obtain face location;
According to described face location, the described original image including face is intercepted, thus obtain facial image.
In conjunction with first aspect, embodiments provide the third possible embodiment of first aspect, described according to described facial image, obtain the blinkpunkt of at least one eyes in each facial image, specifically comprise:
According to described facial image, carry out eyes location, and described facial image is intercepted, obtain the image of at least one eyes;
Iris image and/or the pupil image of eyes is extracted from the image of described eyes;
According to described iris image and/or described pupil image, calculate oculogyral relative displacement, according to described relative displacement, obtain the movement locus of the blinkpunkt of described eyes.
In conjunction with first aspect, embodiments provide the 4th kind of possible embodiment of first aspect, before described instant acquisition at least one facial image, also comprise: launch at least a branch of infrared light, make every Shu Suoshu infrared light can both form an iris reflex point in human eyeball;
Multiple calibration point is shown in advance to user, and the calibration facial image when blinkpunkt obtaining described eyes aims at described calibration point;
According to described calibration facial image, carry out eyes location, and described calibration facial image is intercepted, obtain the image of at least one eyes;
From the image of described eyes, extract pupil position and/or the iris position of eyes, and obtain the position of described iris reflex point;
According to described pupil position and/or iris position, and the relative position of eye pupil and/or iris and described iris reflex point described in the position acquisition of described iris reflex point;
According to relative position, the coordinate of reference point in display screen of described eye pupil and/or iris and described iris reflex point, the position corresponding relation of calibration eyes blinkpunkt and described calibration point in real space;
Described according to described facial image, the blinkpunkt obtaining at least one eyes in each facial image specifically comprises:
According to described eyes the position corresponding relation of reference point and facial image in blinkpunkt and display screen in real space, obtain the concrete coordinate of position in display screen that eyes are watched attentively; The concrete coordinate of the position watched attentively by eyes in display screen is as blinkpunkt;
And/or,
After described multiple facial images of instant acquisition, also comprise:
According to described facial image, extract the face feature of facial image, and the face feature of described facial image and the registration facial image prestored are compared;
As comparison result is consistent, then pass through face verification;
Also comprise: if face verification and live body checking are all passed through, then pass through user rs authentication.
Second aspect, the embodiment of the present invention also provides a kind of living body faces recognition device, comprising:
Facial image acquiring unit, for immediately obtaining multiple facial images;
Eye gaze point acquiring unit, for according to described facial image, obtains the blinkpunkt of at least one eyes or the movement locus of blinkpunkt in each facial image;
Eye gaze point position judgment unit, according to the blinkpunkt of described eyes or the movement locus of blinkpunkt, judges that whether described eyes are according to prompting campaign;
Live body is verified unit, for when judged result is for being, is verified by live body.
In conjunction with second aspect, embodiments provide the first possible embodiment of second aspect, judge whether described eyes carry out motion according to prompting and comprise following at least one:
That points out eyes to watch attentively to user in advance is positioned at extraneous target fiducials object, and in the process of taking pictures, whether the blinkpunkt of eyes aims at described target fiducials object respectively in multiple facial images;
In the process of taking pictures, shown the reference body of movement locus random variation by display screen to user, whether the movement locus of the blinkpunkt that described eyes are formed in multiple facial images is consistent with the movement locus of described target fiducials object;
In the process of taking pictures, be presented at multiple random site by display screen to user to occur successively, and the target fiducials object disappeared after Preset Time after each appearance, the blinkpunkt described target fiducials object that whether aligned position is random respectively in multiple facial images of described eyes;
In the process of taking pictures, show multiple reference body to user, the part in multiple described reference body pointed out to user as target fiducials object, whether the blinkpunkt of described eyes aims at described target fiducials object respectively in multiple facial images;
In the process of taking pictures, show Password Input panel to user, whether the blinkpunkt of eyes aims at default password successively in multiple facial images is being watched the correspondence position on Password Input panel attentively.
In conjunction with second aspect, embodiments provide the embodiment that the second of second aspect is possible, described facial image acquiring unit, specifically comprises:
Original image acquisition module, for obtaining the original image that multiple include face;
Face location acquisition module, for according to described original image, carries out Face datection, obtains face location;
Facial image acquisition module, for according to described face location, intercepts the described original image including face, thus obtains facial image.
In conjunction with second aspect, embodiments provide the third possible embodiment of second aspect, described eye gaze point acquiring unit, specifically comprises:
First eyes image collection module, for according to described facial image, carries out eyes location, and intercepts described facial image, obtain the image of at least one eyes;
First eyes image zooming-out module, for extracting iris image and/or the pupil image of eyes in the image from described eyes;
Blinkpunkt acquisition module, for according to described iris image and/or described pupil image, calculates oculogyral relative displacement, according to described relative displacement, obtains the movement locus of the blinkpunkt of described eyes.
In conjunction with second aspect, embodiments provide the 4th kind of possible embodiment of second aspect, also comprise:
Infrared light transmitter elements, for launching at least a branch of infrared light, makes every Shu Suoshu infrared light can both form an iris reflex point in human eyeball;
Calibration facial image acquisition module, for showing multiple calibration point to user in advance, and the calibration facial image when blinkpunkt obtaining described eyes aims at described calibration point;
Second eyes image collection module, for according to described calibration facial image, carries out eyes location, and intercepts described calibration facial image, obtains the image of at least one eyes;
Second eye position extraction module, for extracting pupil position and/or the iris position of eyes in the image from described eyes, and obtain the position of described iris reflex point, and according to described pupil position and/or iris position, and the relative position of eye pupil and/or iris and described iris reflex point described in the position acquisition of described iris reflex point;
Calibration module, for the relative position according to described eye pupil and/or iris and described iris reflex point, the coordinate of reference point in display screen, the position corresponding relation of calibration eyes blinkpunkt and described calibration point in real space;
Described eye gaze point acquiring unit specifically comprises:
Blinkpunkt coordinate obtains submodule, for according to described eyes the position corresponding relation of reference point and facial image in blinkpunkt and display screen in real space, and the concrete coordinate of position in display screen that acquisition eyes are watched attentively; The concrete coordinate of the position watched attentively by eyes in display screen is as blinkpunkt;
And/or,
Also comprising: face characteristic extraction unit, for extracting the face feature of facial image, and the face feature of described facial image and the registration facial image prestored being compared;
Face verification, by unit, for when comparison result is consistent, passes through face verification;
User rs authentication by unit, for face verification and live body checking all by time, pass through user rs authentication.
The living body faces recognition methods that the embodiment of the present invention provides and device, after obtaining facial image, according to facial image, obtain the blinkpunkt of at least one eyes or the movement locus of blinkpunkt in each facial image, then according to the movement locus of blinkpunkt or blinkpunkt, judge that whether the eyes of people are according to prompting campaign, prompting is then in the process of taking pictures, the prompting that device is sent to user by display screen, thus be ready for user and take pictures or when recorded video, eyes must according to prompting campaign, because the data that the extraction of facial characteristics and eye move extract from same/same group photo or video, illegal registrant cannot with realizing ready facial image or next " deception " demo plant of video, thus the method can judge that user meets while facial characteristics meets, facial information is from for the live body people in reality, increase the anti-counterfeit capability of identification system, the security of raising system.
For making above-mentioned purpose of the present invention, feature and advantage become apparent, preferred embodiment cited below particularly, and coordinate appended accompanying drawing, be described in detail below.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment below, be to be understood that, the following drawings illustrate only some embodiment of the present invention, therefore the restriction to scope should be counted as, for those of ordinary skill in the art, under the prerequisite not paying creative work, other relevant accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 shows the process flow diagram of a kind of living body faces recognition methods that the embodiment of the present invention provides;
Fig. 2 shows in the living body faces recognition methods that the embodiment of the present invention provides, and obtains the process flow diagram of the concrete grammar of multiple facial images;
Fig. 3 shows in the living body faces recognition methods that the embodiment of the present invention provides, and obtains the process flow diagram of the concrete grammar of the movement locus of blinkpunkt;
Fig. 4 shows in the living body faces recognition methods that the embodiment of the present invention provides, and obtains the process flow diagram of the concrete grammar of blinkpunkt;
Fig. 5 shows the process flow diagram of the another kind of living body faces recognition methods that the embodiment of the present invention provides;
Fig. 6 shows the structural representation of the living body faces recognition device that the embodiment of the present invention provides;
Fig. 7 shows the concrete structure schematic diagram of the facial image acquiring unit that the embodiment of the present invention provides;
Fig. 8 shows the concrete structure schematic diagram of the eye gaze point acquiring unit that the embodiment of the present invention provides;
Fig. 9 shows the concrete structure schematic diagram of the another kind of eye gaze point acquiring unit that the embodiment of the present invention provides;
Figure 10 shows the structural representation of the another kind of living body faces identification that the embodiment of the present invention provides;
Figure 11 shows the structural representation of the living body faces recognition system that the embodiment of the present invention provides.
Illustrate:
10-facial image acquiring unit; 20-eye gaze point acquiring unit; 30-eye gaze point position judgment unit; 40-live body is verified unit; 50-infrared light transmitter elements; 60-calibrates facial image acquisition module; 70-second eyes image collection module; 80-second eye position extraction module; 90-calibration module; 100-face characteristic extraction unit; 110-face verification passes through unit; Unit is passed through in 120-user rs authentication; 130-display screen; 140-image capture device; 150-lighting device all with 160-living body faces recognition device;
101-original image acquisition module; 102-face location acquisition module; 103-facial image acquisition module;
201-first eyes image collection module; 202-first eyes image zooming-out module; 203-blinkpunkt acquisition module; 204-blinkpunkt coordinate obtaining module.
Embodiment
Below in conjunction with accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.The assembly of the embodiment of the present invention describing and illustrate in usual accompanying drawing herein can be arranged with various different configuration and design.Therefore, below to the detailed description of the embodiments of the invention provided in the accompanying drawings and the claimed scope of the present invention of not intended to be limiting, but selected embodiment of the present invention is only represented.Based on embodiments of the invention, the every other embodiment that those skilled in the art obtain under the prerequisite not making creative work, all belongs to the scope of protection of the invention.
Current living body faces recognition methods, it is generally the collection directly being carried out human body face photo by image capture device, then according to the human body face feature in photo, compare with the human body face feature in the registration photo prestored before, if comparison is consistent, then authentication is passed through, but once there be illegal registrant to cheat image capture device by forging face, make it collected photo and the photo of the people of non-living body, this point cannot to be discovered constantly in follow-up comparison, thus the anti-counterfeit capability causing identification system is weak, the problem that security is low.Based on this, a kind of living body faces recognition methods that the application provides, device and system, can identify whether the human face photo obtained from image capture device comes from the live body people reality, increase the anti-counterfeit capability of identification system, improve the security of system.It should be noted that the method can be applied to panel computer, mobile phone or other mobile terminal equipment.Such as, can mobile phone, the camera of panel computer or other mobile devices is used for picture collection.In addition, can also with the form of mobile phone or mobile device APP, for logining of mobile terminal hardware itself, online game, Web bank, electronics businessman etc. needs authentication to log in.
For ease of understanding the present embodiment, first a kind of living body faces recognition methods disclosed in the embodiment of the present invention is described in detail,
Shown in Figure 1, the living body faces recognition methods that the embodiment of the present invention provides comprises the following steps:
S101: instant multiple facial images of acquisition;
When specific implementation, need the acquisition being carried out facial image by relevant image capture device.And immediately obtained by image capture device, like this, can ensure that obtained image is the current image being in the people of the image acquisition region of image capture device, instead of photo, the video having taken before or forged.Usually, when gathering facial image by image capture device, multiple facial images can be obtained continuously according to certain frequency.This just makes when user needs to see to multiple target fiducials object time, eyes are seen to during each target fiducials object all can obtain multiple images, therefore will screen wherein one in these multiple images, the blinkpunkt as eyes watches the image of this target fiducials object attentively.
After acquisition facial image, also comprise:
S102: according to described facial image, obtains the blinkpunkt of at least one eyes or the movement locus of blinkpunkt in each facial image;
When specific implementation, owing to obtaining facial image, and the feature at each position all can extract from facial image in face, thus can first eye feature be extracted from facial image, then according to eye feature, the blinkpunkt of at least one eyes in facial image is obtained.It should be noted that, certain distance is there is between two of people, because two eyes of this person are when watching same target attentively, the anglec of rotation of eyeball is different, therefore, during the blinkpunkt of eyes when certain obtaining same user logs in, what should obtain is the blinkpunkt of same eyes.
S103: according to the blinkpunkt of described eyes or the movement locus of blinkpunkt, judges that whether described eyes are according to prompting campaign;
When specific implementation:
1, system can point out it to need the target fiducials object being positioned at the external world watched attentively to user, be positioned at the external world relative to display screen, using the external object outside display screen as target fiducials object, and when image acquisition equipment is installed, have already been made the location of external object, such as in ATM withdrawal machine, after camera is installed, extraneous object, the such as cash dispensing port of ATM withdrawal machine, ticket outlet, card reader, corner, camera etc. is all fixing relative to camera, even can draw various reference body in advance on ATM withdrawal machine, or directly on ATM withdrawal machine, some reference body is installed, can also be attached to specially or be placed on display or with the wall towards face, some paster on object, ornaments etc.Like this, system directly needs the target fiducials object being specifically positioned at the external world watched attentively by display screen prompting user, the eyes simultaneously obtaining people are seen to facial image during target fiducials object, and judge whether the blinkpunkt of eyes targeted by this target fiducials object in an image.It should be noted that can repeatedly to user's prompting, and indicating user sees the target fiducials object different to position, improves security.
2, system shows movement locus random variation target fiducials object to user, and point out user to see to this target fiducials object, when the position of target fiducials object is when change, eyeball can rotate along with the change of target fiducials object space, during final Rotation of eyeball, the movement locus of eye gaze point should match with the movement locus of target fiducials object.Such as show a conglobate target fiducials object of movement locus to user, when eyes are seen to this target fiducials object, the track of eye gaze point also should be conglobate.When judgement, as long as the matching degree of the movement locus of eye gaze point and the movement locus of reference body is more than the threshold value preset, just think that eye gaze is to this target fiducials object.
It should be noted that, in the process of target fiducials object movement, image acquisition equipment is taken pictures to face simultaneously.Be carry out according to a certain default frequency owing to taking pictures, therefore obtained human face photo is multiple, and finally in these multiple human face photos, the continuous movement locus of eye gaze point should be consistent with the movement locus of target fiducials object.
3, system can need the reference body watched attentively in advance when user is presented at and takes pictures.This reference body can be system by display to the position that user shows the reference body of random (namely coordinate is random), after this reference body display Preset Time, disappear and again appear at other random site with original form or other form, so repeat preset times, in this process, the eyes of user will see the position occurred to reference body.More accurate in order to judge, procedure for displaying as above can repeat for several times, and what occur on a display screen is a mode position combination, and user needs the order occurred according to reference body to watch the position at its place successively attentively.When user watches these position groupings in order attentively time, the blinkpunkt of eyes can change thereupon.Therefore according to the picture of multiple eyes, the location point that a series of eye gaze point is formed can be obtained.The mode position of the point formed by eye gaze point contrasts with the mode position of the actual point occurred, if similarity is on the threshold value preset, then thinks that the blinkpunkt of eyes is consistent with the position grouping shown to user in advance.Namely, in each facial image, the blinkpunkt of eyes is aligned in the target fiducials object of diverse location appearance respectively.Concrete judge in, according to the position of blinkpunkt and the random reference body occurred, can judge whether the eyes of people are the random objects watching this position random variation attentively.
4, system can show the combination of multiple reference body over the display in advance to user, a such as alphabetic keypad, numeric keypad, or figure combination or other guide combination, then require that user watches part reference body wherein attentively, by the part in reference body as target fiducials object, and user is pointed out to watch these target fiducials objects attentively.Such as require that user watches the monogram Q on alphabetic keypad attentively, P, Z, M, or combination of numbers 3,7,4,2, then or combination of shapes in the object (circular to star) of some shape.This process of watching attentively can require that user is in strict accordance with appointment order, also a reference content whether can unanimously and not consider the order that user watches attentively.
5, system can show a Password Input panel to user over the display in advance, this Password Input panel can be alphabetic keypad, a numeric keypad or figure combination or other guide combination, then require mode that eyes of user is watched attentively input user before the password that sets or combination of shapes, namely whether the blinkpunkt of eyes is aimed at default password successively and is being watched the correspondence position on Password Input panel attentively in multiple facial images.Its process is similar on screen and occurs dummy keyboard or input point, requires the password that the way selection oneself of user's eye gaze is preset, or mobile eyeball, causes the activity of eyeball to be preset shape according to drawing before.It should be noted that default shape is also the one of Password Input.
S104: if judged result is yes, then verified by live body.
When specific implementation, the result judged if above-mentioned is yes, then think that image that system obtains is the image of the people of live body, thus verified by live body.
Living body faces recognition methods provided by the present invention, after obtaining facial image, according to facial image, obtain the blinkpunkt of at least one eyes in each facial image, then according to blinkpunkt, judge the eyes whether fixation object reference body of people, thus user taking pictures or when recorded video, eyes must rotate as indicated, in this process, illegal lander is difficult at short notice by forging face " deception " image capture device, thus living body faces recognition methods provided by the present invention can identify whether the human face photo obtained from image capture device comes from the live body people reality, increase the anti-counterfeit capability of identification system, the security of raising system.
For above-mentioned facial image, shown in Figure 2, the embodiment of the present invention also provides a kind of concrete grammar obtaining facial image, and the method comprises:
S201: obtain the original image that individual or multiple include face;
When specific implementation, obtaining individual or multiple has the original image of face to be the image without any process directly collected by image capture device.
When acquisition, shooting button can be provided to user, see to reference body client, or the blinkpunkt of eyes is turned to certain angle by user as requested, namely time eye gaze point arrives indicating positions, just can press shooting button, now, the image that image capture device collects is namely as original image.Or, display screen is set to touch-screen, user can by touching, touch, the mode such as slip, to system sending controling instruction, system controls image capture device according to the steering order that user inputs and carries out work, user in the face of the camera lens of image capture device, and can realize the interaction with camera lens by touch-screen.In addition, image collecting device can also under the control of system, automatic acquisition original image.
S202: according to described original image, carries out Face datection, obtains face location;
When specific implementation, Face datection is carried out according to original image, namely from original image, pick out and whether have face, general, all face can be included in original image, but also may at image collecting device under Systematical control, during automatic acquisition original image, the image obtained is the image of user when not being ready to, now may not include face in original image, therefore this part do not contain face image need give it up after identification does not have face.And after carrying out Face datection, the position of face in original image be obtained.
S203: according to described face location, intercepts the described original image including face, thus obtains facial image.
When specific implementation, owing to obtaining face location in S202, when acquisition face location, what obtained is face edge coordinate point in the picture or has predeterminable range with face edge, and the coordinate points be positioned at outside face, now, facial image can be intercepted out according to this coordinate points, namely obtain facial image.
In addition, shown in Figure 3, the embodiment of the present invention also provides a kind of according to described facial image, and obtain the concrete grammar of the movement locus of the blinkpunkt of at least one eyes in each facial image, the method comprises:
S301: according to described facial image, carries out eyes location, and intercepts described facial image, obtains the image of at least one eyes;
When specific implementation, the feature at each position of face can obtain from facial image, therefore when positioning eyes, only according to the feature of eyes, can carry out eyes location.When eyes location, what obtain is the coordinate of eye contour in facial image actually, therefore now, can intercept, obtain the image of at least one eyes according to obtained coordinate in facial image.
S302: iris image and/or the pupil image of extracting eyes from the image of described eyes;
When specifically realizing, under various light conditions, such as under visible ray or infrared radiation, the iris image of the eyes of people and pupil image are all can observe directly from the image of eyes, thus eyes image is being processed, such as in removal noise jamming, according to the feature of iris or pupil, only retain final iris image or pupil image.
S303: according to described iris image and/or described pupil image, calculate oculogyral relative displacement, according to described relative displacement, obtains the movement locus of the blinkpunkt of described eyes.
When specific implementation, because people is seeing that eyeball can rotate, and then produces corresponding displacement to when certain target fiducials object.Usually, during dead ahead that eyes are visual, the axis of pupil or iris is as datum axis, so when eyes are seen to certain target fiducials object, even if the iris image that can obtain or pupil image, obtain the axis of iris or pupil at that time, the axis of iris or pupil at that time and datum axis are contrasted, just can calculate oculogyral relative displacement.And oculogyral relative displacement combines in multiple face picture, the movement locus of the blinkpunkt of eyes just can be formed.The mode of the blinkpunkt of this acquisition eyes does not need to carry out eyes location, and only rely on eyeball watching attentively to when diverse location, the change in location of pupil or iris judges.
In addition, shown in Figure 4, the embodiment of the present invention also provides another kind of living body faces recognition methods, and on the basis of above-mentioned several embodiment, the method comprises:
Before acquisition at least one facial image, namely before S101, at least a branch of infrared light can also be launched by light fixture, make every Shu Suoshu infrared light can both form an iris reflex point in human eyeball.The infrared light sent when single or multiple infrared light supply forms single or multiple iris reflex point on iris, and according to iris reflex point and oculogyral relative position and angle, the change in location of the blinkpunkt in the realistic space corresponding to the relative movement of eyes in imaging picture can be calculated, namely the change of eye gaze point can be known, thus, calculate the described blinkpunkt of eyes in realistic space according to the iris reflex point on the iris of described eyes and pupil image.
Particularly, the tracking of eye position can be the position of a certain the eyes in left and right, also can be that two eyes in left and right are all followed the trail of respectively.
Under comparatively stable visible ray illumination condition, the method for face recognition can determine the position of eyes of user.Pupil and iris are all the intrinsic physiologic result of eyes, because color and surrounding structure differ greatly, and shape is fixed, and move so be all widely used in following the trail of eye.
Pupil is positioned at the center of iris, usually in dark, if it is rounded not go up blocking of palpebra inferior, or has partial occlusion to be then part circular.Controlled by the pattern identification of shape and the threshold value of color, the center of pupil can be obtained on image.Iris presents circle under the situation that palpebra inferior blocks or the blocking of palpebra inferior on having not going up usually, is the circle of part, can be made a distinction by colour contrast with eyeball white portion.
The motion of pupil or iris, can be approximated to be the change of eyes relative position on image.Only use visible ray just can obtain the position data of eyes in the picture gathered, therefore, also comprise:
S401: show multiple calibration point to user in advance, and the calibration facial image when blinkpunkt obtaining described eyes aims at described calibration point;
Its process and S301 similar, do not repeat them here.
S402: according to described calibration facial image, carry out eyes location, and described calibration facial image is intercepted, obtain the image of at least one eyes;
Its process and S302 similar, do not repeat them here.
S403: pupil position and/or the iris position of extracting eyes from the image of described eyes, and obtain the position of described iris reflex point;
When specific implementation, when entering human eye when there being infrared radiation and form iris reflex point, this iris reflex point by eyeball observes directly, equally also can acquire from the image of eyes.And eyes are when rotation, the position of pupil position and iris can change along with the rotation of eyeball, but because ultrared incident angle is constant, so when oculogyral time, the hot spot that infrared ray is formed in eyes with pupil or iris for object of reference, position is change, and its change is just in time contrary with the change of pupil or iris.Thus can intuitively from the image of eyes by pupil position and/or iris position, and the position of iris reflex point extracts.
S404: according to described pupil position and/or iris position, and the relative position of eye pupil and/or iris and described iris reflex point described in the position acquisition of described iris reflex point;
S405: according to relative position, the coordinate of reference point in display screen of described eye pupil and/or iris and described iris reflex point, the position corresponding relation of calibration eyes blinkpunkt and described calibration point in real space.
When from the image of eyes from pupil position and/or iris position, and after the position of iris reflex point extracts, can directly by measuring or calculate the position relationship of above-mentioned a few person in the image of eyes, obtain the relative position of eye pupil and/or iris and described iris reflex point, then according to the relative position of eye pupil and/or iris and described iris reflex point, and the coordinate of reference point in display screen, the position corresponding relation of calibration eyes blinkpunkt and calibration point in real space.
When display screen shows reference body to user again time, can according to the coordinate of reference body and eyes the position corresponding relation of blinkpunkt and calibration point in real space, and the facial image that user is captured when watching reference body attentively, just can obtain the concrete coordinate of position in display screen of eyes, this coordinate is the blinkpunkt of eyes.
Thus, described according to described facial image, the blinkpunkt obtaining at least one eyes in each facial image specifically comprises:
According to described eyes the position corresponding relation of reference point and facial image in blinkpunkt and display screen in real space, obtain the concrete coordinate of position in display screen that eyes are watched attentively; The concrete coordinate of the position watched attentively by eyes in display screen is as blinkpunkt;
When specific implementation, system can show several calibration point at diverse location to user over the display successively, requires that eyes of user watches these points attentively.Position due to this reference body is that system is shown by display, and therefore system directly can obtain the position of this calibration point, and then system also obtains the data of eyes in photo coordinate at the corresponding time by above-mentioned method.The relative motion in photo coordinate by the relative position between several calibration point and eyes, can be calibrated to the coordinate of screen or the physical coordinates of reality the motion of eyes in photo coordinate conversion.
Under infrared light supply irradiates, the dynamic tracking of eye can be carried out with similar under the condition of visible ray.In addition, infrared light supply can be formed strongly and specular reflection point clearly more on the iris of people, and be called iris reflex point, iris reflex point can form obvious hot spot on eyeball, and this iris reflex point can clearly be seen from eyeball.
When eye motion, the location following of pupil or iris eye motion and moves.But when infrared light supply position is constant, the position of iris reflex point can't change.By the difference of the position of pupil (or iris) and iris reflex point, the change of position coordinates that eyes watch attentively in realistic space or in actual screen and position can be calculated.
One or more infrared light supply can be used, thus form one or more iris reflex point.When light source position is known, eyes, relative to the motion of light source position, may be used for the position that calibration eyes are watched attentively in real space.
In addition, another embodiment of the present invention also provides another kind of living body faces recognition methods, on the basis of above-described embodiment, shown in Figure 5, before described instant acquisition at least one facial image, also comprises:
S501: according to described facial image, extracts the face feature of facial image, and the face feature of described facial image and the registration facial image prestored is compared;
S502: as comparison result is consistent, then pass through face verification;
When specific implementation, owing to being in the embodiment corresponding to Fig. 1, whether the image only having carried out obtaining comes from the checking of living body faces, therefore, also need for facial image, carry out the comparison based on face feature with the registration facial image prestored, only have when comparison is passed through time, just can think that the people that will log in is user, and be not other illegal landers.According to described facial image, extract the face feature of facial image, and compared with the registration facial image prestored by the face feature of described facial image and use existing living body faces recognition methods, therefore detailed process does not repeat them here.
It should be noted that the embodiment corresponding to Fig. 1 and the embodiment corresponding to Fig. 5 should synchronously be carried out, namely after obtaining facial image, carry out live body checking and face verification simultaneously to only have when both passing through, just can make user's Successful login.If wherein there is a checking to pass through, then cannot log in.Therefore, embodiment provided by the present invention also comprises: if face verification and live body checking are all passed through, then pass through user rs authentication.
Further embodiment of this invention also provides a kind of living body faces recognition device, shown in Figure 6, and the living body faces recognition device that the embodiment of the present invention provides comprises:
Facial image acquiring unit 10, for immediately obtaining at least one facial image;
Eye gaze point acquiring unit 20, for according to described facial image, obtains the blinkpunkt of at least one eyes or the movement locus of blinkpunkt in each facial image;
Eye gaze point position judgment unit 30, according to the blinkpunkt of described eyes or the movement locus of blinkpunkt, judges that whether described eyes are according to prompting campaign;
Live body is verified unit 40, for when judged result is for being, is verified by live body.
Wherein, judge whether described eyes carry out motion according to prompting and comprise following at least one:
That points out eyes to watch attentively to user in advance is positioned at extraneous target fiducials object, and in the process of taking pictures, whether the blinkpunkt of eyes aims at described target fiducials object respectively in multiple facial images;
In the process of taking pictures, shown the reference body of movement locus random variation by display screen to user, whether the movement locus of the blinkpunkt that described eyes are formed in multiple facial images is consistent with the movement locus of described target fiducials object;
In the process of taking pictures, be presented at multiple random site by display screen to user to occur successively, and the target fiducials object disappeared after Preset Time after each appearance, the blinkpunkt described target fiducials object that whether aligned position is random respectively in multiple facial images of described eyes;
In the process of taking pictures, show multiple reference body to user, the part in multiple described reference body pointed out to user as target fiducials object, whether the blinkpunkt of described eyes aims at described target fiducials object respectively in multiple facial images;
In the process of taking pictures, show Password Input panel to user, whether the blinkpunkt of eyes aims at default password successively in multiple facial images is being watched the correspondence position on Password Input panel attentively.
In the present embodiment, facial image acquiring unit 10, eye gaze point acquiring unit 20, eye gaze point position judgment unit 30 and live body are verified concrete function and the interactive mode of unit 40, see the record of embodiment corresponding to Fig. 1, can not repeat them here.
The living body faces recognition device that the embodiment of the present invention provides, after obtaining at least one facial image by facial image acquiring unit 10, re-use eye gaze point acquiring unit 20 according to above-mentioned facial image, obtain the blinkpunkt of at least one eyes in each facial image, and judge whether the image collected by image capture device comes from the people of live body by eye gaze point position judgment unit 30 according to the blinkpunkt of eyes.Reference body movement locus used in the process, obtaining the random object of reference in the position that is shown to client before facial image in advance, thus be ready for user and take pictures or when recorded video, eyes must rotate according to instruction in advance, in this process, illegal lander is difficult at short notice by forging face " deception " image capture device, thus living body faces recognition methods provided by the present invention can identify whether the human face photo obtained from image capture device comes from the live body people reality, increase the anti-counterfeit capability of identification system, the security of raising system.
Further embodiment of this invention also provides the concrete device of facial image acquiring unit, shown in Figure 7, and facial image acquiring unit 10 specifically comprises:
Original image acquisition module 101, includes the original image of face for obtaining individual or multiple;
Face location acquisition module 102, for according to described original image, carries out Face datection, obtains face location;
Facial image acquisition module 103, for according to described face location, intercepts the described original image including face, thus obtains facial image.
In the present embodiment, the concrete function of original image acquisition module 101, face location acquisition module 102 and facial image acquisition module 103 and interactive mode, see the record of embodiment corresponding to Fig. 2, can not repeat them here.
Further embodiment of this invention also provides the concrete structure of another kind of eye gaze point acquiring unit, shown in Figure 8, and described eye gaze point acquiring unit 20, specifically comprises:
First eyes image collection module 201, for according to described facial image, carries out eyes location, and intercepts described facial image, obtain the image of at least one eyes;
First eyes image zooming-out module 202, for extracting iris image and/or the pupil image of eyes in the image from described eyes;
Blinkpunkt acquisition module 203, for according to described iris image and/or described pupil image, calculates oculogyral relative displacement, according to described relative displacement, obtains the movement locus of the blinkpunkt of described eyes.
In the present embodiment, the concrete function of the first eyes image collection module 201, first eyes image zooming-out module 202 and blinkpunkt acquisition module 203 and interactive mode, see the record of embodiment corresponding to Fig. 3, can not repeat them here.
It should be noted that in addition in each embodiment of the present invention, shown in Figure 9, can also comprising: infrared light transmitter elements 50, for launching at least a branch of infrared light, making every Shu Suoshu infrared light can both form an iris reflex point in human eyeball;
Calibration facial image acquisition module 60, for showing multiple calibration point to user in advance, and the calibration facial image when blinkpunkt obtaining described eyes aims at described calibration point;
Second eyes image collection module 70, for according to described calibration facial image, carries out eyes location, and intercepts described calibration facial image, obtains the image of at least one eyes;
Second eye position extraction module 80, for extracting pupil position and/or the iris position of eyes in the image from described eyes, and obtain the position of described iris reflex point, and according to described pupil position and/or iris position, and the relative position of eye pupil and/or iris and described iris reflex point described in the position acquisition of described iris reflex point;
Calibration module 90, for the relative position according to described eye pupil and/or iris and described iris reflex point, the coordinate of reference point in display screen, the position corresponding relation of calibration eyes blinkpunkt and described calibration point in real space;
It should be noted that now, described eye gaze point acquiring unit 20 specifically comprises:
Blinkpunkt coordinate obtaining module 204, for according to described eyes the position corresponding relation of reference point and facial image in blinkpunkt and display screen in real space, obtains the concrete coordinate of position in display screen that eyes are watched attentively; The concrete coordinate of the position watched attentively by eyes in display screen is as blinkpunkt;
In the present embodiment, the concrete function of infrared light transmitter elements 50, calibration facial image acquisition module 60, second eyes image collection module 70, second eye position extraction module 80, calibration module 90 and blinkpunkt coordinate obtaining module 204 and interactive mode, see the record of embodiment corresponding to Fig. 4, can not repeat them here.
Shown in Figure 10, also comprising: face characteristic extraction unit 100, for extracting the face feature of facial image, and the face feature of described facial image and the registration facial image prestored being compared;
Face verification, by unit 110, for when comparison result is consistent, passes through face verification;
User rs authentication by unit 120, for face verification and live body checking all by time, pass through user rs authentication.
In the present embodiment, face characteristic extraction unit 100, face verification, see the record of embodiment corresponding to Fig. 4, can not repeated them here by the concrete function of unit 120 and interactive mode by unit 110 and user rs authentication.
Further embodiment of this invention additionally provides a kind of living body faces recognition system, shown in Figure 11,
Comprise: display screen 130, image capture device 140, lighting device 150, also comprise as weighed corresponding to above-mentioned Fig. 6 ~ Figure 10 embodiment in living body faces recognition device 160,
Wherein, described display screen 130, described image capture device 140, described lighting device 150 are all connected with described living body faces recognition device 160.
The living body faces recognition methods that the embodiment of the present invention provides and the computer program of device and system, comprise the computer-readable recording medium storing program code, the instruction that described program code comprises can be used for performing the method described in previous methods embodiment, specific implementation see embodiment of the method, can not repeat them here.
Those skilled in the art can be well understood to, and for convenience and simplicity of description, the system of foregoing description and the specific works process of device, with reference to the corresponding process in preceding method embodiment, can not repeat them here.
If described function using the form of SFU software functional unit realize and as independently production marketing or use time, can be stored in a computer read/write memory medium.Based on such understanding, the part of the part that technical scheme of the present invention contributes to prior art in essence in other words or this technical scheme can embody with the form of software product, this computer software product is stored in a storage medium, comprising some instructions in order to make a computer equipment (can be personal computer, server, or the network equipment etc.) perform all or part of step of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, ROM (read-only memory) (ROM, Read-OnlyMemory), random access memory (RAM, RandomAccessMemory), magnetic disc or CD etc. various can be program code stored medium.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should described be as the criterion with the protection domain of claim.
Claims (10)
1. a living body faces recognition methods, is characterized in that, comprising:
Multiple facial images of instant acquisition;
According to described facial image, obtain the blinkpunkt of at least one eyes or the movement locus of blinkpunkt in each facial image;
According to the blinkpunkt of described eyes or the movement locus of blinkpunkt, judge that whether described eyes are according to prompting campaign;
If judged result is yes, then verified by live body.
2. living body faces recognition methods according to claim 1, is characterized in that, judges whether described eyes carry out motion according to prompting and comprise following at least one:
That points out eyes to watch attentively to user in advance is positioned at extraneous target fiducials object, and in the process of taking pictures, whether the blinkpunkt of eyes aims at described target fiducials object respectively in multiple facial images;
In the process of taking pictures, shown the target fiducials object of movement locus random variation by display screen to user, whether the movement locus of the blinkpunkt that described eyes are formed in multiple facial images is consistent with the movement locus of described target fiducials object;
In the process of taking pictures, be presented at multiple random site by display screen to user to occur successively, and the target fiducials object disappeared after Preset Time after each appearance, the blinkpunkt described target fiducials object that whether aligned position is random respectively in multiple facial images of described eyes;
In the process of taking pictures, show multiple reference body to user, the part in multiple described reference body pointed out to user as target fiducials object, whether the blinkpunkt of described eyes aims at described target fiducials object respectively in multiple facial images;
In the process of taking pictures, show Password Input panel to user, whether the blinkpunkt of eyes aims at default password successively in multiple facial images is being watched the correspondence position on Password Input panel attentively.
3. living body faces recognition methods according to claim 1 and 2, is characterized in that, described multiple facial images of instant acquisition, specifically comprise:
Obtain the original image that multiple include face;
According to described original image, carry out Face datection, obtain face location;
According to described face location, the described original image including face is intercepted, thus obtain facial image.
4. living body faces recognition methods according to claim 1 and 2, is characterized in that, described according to described facial image, obtains the movement locus of the blinkpunkt of at least one eyes in each facial image, specifically comprises:
According to described facial image, carry out eyes location, and described facial image is intercepted, obtain the image of at least one eyes;
Iris image and/or the pupil image of eyes is extracted from the image of described eyes;
According to described iris image and/or described pupil image, calculate oculogyral relative displacement, according to described relative displacement, obtain the movement locus of the blinkpunkt of described eyes.
5. living body faces recognition methods according to claim 1 and 2, is characterized in that, before described instant acquisition at least one facial image, also comprises:
Launch at least a branch of infrared light, make every Shu Suoshu infrared light can both form an iris reflex point in human eyeball;
Multiple calibration point is shown in advance to user, and the calibration facial image when blinkpunkt obtaining described eyes aims at described calibration point;
According to described calibration facial image, carry out eyes location, and described calibration facial image is intercepted, obtain the image of at least one eyes;
Pupil position and/or the iris position of eyes is extracted from the image of described eyes, and obtain the position of described iris reflex point, and according to described pupil position and/or iris position, and the relative position of eye pupil and/or iris and described iris reflex point described in the position acquisition of described iris reflex point;
According to relative position, the coordinate of reference point in display screen of described eye pupil and/or iris and described iris reflex point, the position corresponding relation of calibration eyes blinkpunkt and described calibration point in real space;
Described according to described facial image, the blinkpunkt obtaining at least one eyes in each facial image specifically comprises:
According to described eyes the position corresponding relation of reference point and facial image in blinkpunkt and display screen in real space, obtain the concrete coordinate of position in display screen that eyes are watched attentively; The concrete coordinate of the position watched attentively by eyes in display screen is as blinkpunkt;
And/or,
After described multiple facial images of instant acquisition, also comprise:
According to described facial image, extract the face feature of facial image, and the face feature of described facial image and the registration facial image prestored are compared;
As comparison result is consistent, then pass through face verification;
Also comprise: if face verification and live body checking are all passed through, then pass through user rs authentication.
6. a living body faces recognition device, is characterized in that, comprising:
Facial image acquiring unit, for immediately obtaining multiple facial images;
Eye gaze point acquiring unit, for according to described facial image, obtains the blinkpunkt of at least one eyes or the movement locus of blinkpunkt in each facial image;
Eye gaze point position judgment unit, according to the blinkpunkt of described eyes or the movement locus of blinkpunkt, judges that whether described eyes are according to prompting campaign;
Live body is verified unit, for when judged result is for being, is verified by live body.
7. living body faces recognition device according to claim 6, is characterized in that, judges whether described eyes carry out motion according to prompting and comprise following at least one:
That points out eyes to watch attentively to user in advance is positioned at extraneous target fiducials object, and in the process of taking pictures, whether the blinkpunkt of eyes aims at described target fiducials object respectively in multiple facial images;
In the process of taking pictures, shown the reference body of movement locus random variation by display screen to user, whether the movement locus of the blinkpunkt that described eyes are formed in multiple facial images is consistent with the movement locus of described target fiducials object;
In the process of taking pictures, be presented at multiple random site by display screen to user to occur successively, and the target fiducials object disappeared after Preset Time after each appearance, the blinkpunkt described target fiducials object that whether aligned position is random respectively in multiple facial images of described eyes;
In the process of taking pictures, show multiple reference body to user, the part in multiple described reference body pointed out to user as target fiducials object, whether the blinkpunkt of described eyes aims at described target fiducials object respectively in multiple facial images;
In the process of taking pictures, show Password Input panel to user, whether the blinkpunkt of eyes aims at default password successively in multiple facial images is being watched the correspondence position on Password Input panel attentively.
8. the living body faces recognition device according to claim 6 or 7, is characterized in that, described facial image acquiring unit, specifically comprises:
Original image acquisition module, for obtaining the original image that multiple include face;
Face location acquisition module, for according to described original image, carries out Face datection, obtains face location;
Facial image acquisition module, for according to described face location, intercepts the described original image including face, thus obtains facial image.
9. the living body faces recognition device according to claim 6 or 7, is characterized in that, described eye gaze point acquiring unit, specifically comprises:
First eyes image collection module, for according to described facial image, carries out eyes location, and intercepts described facial image, obtain the image of at least one eyes;
First eyes image zooming-out module, for extracting iris image and/or the pupil image of eyes in the image from described eyes;
Blinkpunkt acquisition module, for according to described iris image and/or described pupil image, calculates oculogyral relative displacement, according to described relative displacement, obtains the movement locus of the blinkpunkt of described eyes.
10. the living body faces recognition device according to claim 6 or 7, is characterized in that, also comprise:
Infrared light transmitter elements, for launching at least a branch of infrared light, makes every Shu Suoshu infrared light can both form an iris reflex point in human eyeball;
Calibration facial image acquisition module, for showing multiple calibration point to user in advance, and the calibration facial image when blinkpunkt obtaining described eyes aims at described calibration point;
Second eyes image collection module, for according to described calibration facial image, carries out eyes location, and intercepts described calibration facial image, obtains the image of at least one eyes;
Second eye position extraction module, for extracting pupil position and/or the iris position of eyes in the image from described eyes, and obtain the position of described iris reflex point, and according to described pupil position and/or iris position, and the relative position of eye pupil and/or iris and described iris reflex point described in the position acquisition of described iris reflex point;
Calibration module, for the relative position according to described eye pupil and/or iris and described iris reflex point, the coordinate of reference point in display screen, the position corresponding relation of calibration eyes blinkpunkt and described calibration point in real space;
Described eye gaze point acquiring unit specifically comprises:
Blinkpunkt coordinate obtaining module, for according to described eyes the position corresponding relation of reference point and facial image in blinkpunkt and display screen in real space, obtains the concrete coordinate of position in display screen that eyes are watched attentively; The concrete coordinate of the position watched attentively by eyes in display screen is as blinkpunkt;
And/or,
Also comprising: face characteristic extraction unit, for extracting the face feature of facial image, and the face feature of described facial image and the registration facial image prestored being compared;
Face verification, by unit, for when comparison result is consistent, passes through face verification;
User rs authentication by unit, for face verification and live body checking all by time, pass through user rs authentication.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510629903.0A CN105184277B (en) | 2015-09-29 | 2015-09-29 | Living body face recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510629903.0A CN105184277B (en) | 2015-09-29 | 2015-09-29 | Living body face recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105184277A true CN105184277A (en) | 2015-12-23 |
| CN105184277B CN105184277B (en) | 2020-02-21 |
Family
ID=54906344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510629903.0A Active CN105184277B (en) | 2015-09-29 | 2015-09-29 | Living body face recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105184277B (en) |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106169075A (en) * | 2016-07-11 | 2016-11-30 | 北京小米移动软件有限公司 | Auth method and device |
| CN106203297A (en) * | 2016-06-30 | 2016-12-07 | 北京七鑫易维信息技术有限公司 | A kind of personal identification method and device |
| CN106713368A (en) * | 2017-03-08 | 2017-05-24 | 四川大学 | Identity authentication method and identity authentication device |
| CN106850685A (en) * | 2017-03-25 | 2017-06-13 | 安徽味唯网络科技有限公司 | A kind of auth method for having a sense of independence |
| CN107092818A (en) * | 2016-02-17 | 2017-08-25 | 阿里巴巴集团控股有限公司 | The implementation method and device of vivo identification |
| CN107154095A (en) * | 2017-06-06 | 2017-09-12 | 信利光电股份有限公司 | A kind of car entry system and method |
| CN107273794A (en) * | 2017-04-28 | 2017-10-20 | 北京建筑大学 | Live body discrimination method and device in a kind of face recognition process |
| CN107305629A (en) * | 2016-04-21 | 2017-10-31 | 王溯 | Sight identifying device and method |
| CN107451547A (en) * | 2017-07-17 | 2017-12-08 | 广东欧珀移动通信有限公司 | Identify the method and Related product of live body |
| CN107506696A (en) * | 2017-07-29 | 2017-12-22 | 广东欧珀移动通信有限公司 | Anti-fake processing method and related product |
| CN107590429A (en) * | 2017-07-20 | 2018-01-16 | 阿里巴巴集团控股有限公司 | The method and device verified based on eyeprint feature |
| CN107622188A (en) * | 2016-07-15 | 2018-01-23 | 阿里巴巴集团控股有限公司 | Verification method, device, system and equipment based on biological characteristic |
| CN108256406A (en) * | 2017-01-05 | 2018-07-06 | 广州市晶密电子有限公司 | It is a kind of that the data processing method of face recognition and its device are realized by eyes orientation direction |
| CN108304784A (en) * | 2018-01-15 | 2018-07-20 | 武汉神目信息技术有限公司 | A kind of blink detection method and device |
| CN108319830A (en) * | 2017-01-17 | 2018-07-24 | 中兴通讯股份有限公司 | A kind of auth method and device |
| CN108345818A (en) * | 2017-01-23 | 2018-07-31 | 北京中科奥森数据科技有限公司 | A kind of human face in-vivo detection method and device |
| CN108399365A (en) * | 2018-01-19 | 2018-08-14 | 东北电力大学 | The method and its equipment of living body faces are detected using pupil diameter |
| CN108537103A (en) * | 2018-01-19 | 2018-09-14 | 东北电力大学 | The living body faces detection method and its equipment measured based on pupil axle |
| CN108615159A (en) * | 2018-05-03 | 2018-10-02 | 百度在线网络技术（北京）有限公司 | Access control method and device based on blinkpunkt detection |
| CN108693543A (en) * | 2017-03-31 | 2018-10-23 | 法拉第未来公司 | Method and system for detecting signal deception |
| CN108701228A (en) * | 2018-04-18 | 2018-10-23 | 深圳阜时科技有限公司 | Identification authentication method, identification authentication device and electronic equipment |
| CN108900700A (en) * | 2018-06-04 | 2018-11-27 | 北京大学 | Authentication method and system based on the double verification that recognition of face and sight position |
| CN109074441A (en) * | 2016-04-29 | 2018-12-21 | 微软技术许可有限责任公司 | Based on the certification watched attentively |
| CN109271978A (en) * | 2018-11-23 | 2019-01-25 | 四川长虹电器股份有限公司 | Recognition of face anti-fraud method |
| CN109325462A (en) * | 2018-10-11 | 2019-02-12 | 深圳斐视沃德科技有限公司 | Recognition of face biopsy method and device based on iris |
| CN109753871A (en) * | 2018-11-21 | 2019-05-14 | 惠州Tcl移动通信有限公司 | A kind of method and mobile terminal of recognition of face |
| CN109871796A (en) * | 2019-01-31 | 2019-06-11 | 杭州创匠信息科技有限公司 | Method for anti-counterfeit and device based on living body iris |
| CN110114777A (en) * | 2016-12-30 | 2019-08-09 | 托比股份公司 | Use identification, certification and/or the guiding of the user for watching information progress attentively |
| CN110135370A (en) * | 2019-05-20 | 2019-08-16 | 北京百度网讯科技有限公司 | The method and device of face In vivo detection, electronic equipment, computer-readable medium |
| CN110720105A (en) * | 2019-09-11 | 2020-01-21 | 深圳市汇顶科技股份有限公司 | Face anti-counterfeiting detection method, device, chip, electronic equipment and computer readable medium |
| CN110738072A (en) * | 2018-07-18 | 2020-01-31 | 浙江宇视科技有限公司 | Living body judgment method and device |
| CN111046696A (en) * | 2018-10-12 | 2020-04-21 | 宏碁股份有限公司 | Living body identification method and electronic device |
| CN111159678A (en) * | 2019-12-26 | 2020-05-15 | 联想(北京)有限公司 | Identity recognition method, device and storage medium |
| CN111324878A (en) * | 2020-02-05 | 2020-06-23 | 重庆特斯联智慧科技股份有限公司 | Identity verification method and device based on face recognition, storage medium and terminal |
| TWI706270B (en) * | 2018-08-13 | 2020-10-01 | 香港商阿里巴巴集團服務有限公司 | Identity recognition method, device and computer readable storage medium |
| CN111967293A (en) * | 2020-06-22 | 2020-11-20 | 云知声智能科技股份有限公司 | Face authentication method and system combining voiceprint recognition and attention detection |
| CN112016482A (en) * | 2020-08-31 | 2020-12-01 | 成都新潮传媒集团有限公司 | Method and device for distinguishing false face and computer equipment |
| CN112257050A (en) * | 2020-10-26 | 2021-01-22 | 上海鹰瞳医疗科技有限公司 | Identity authentication method and equipment based on gazing action |
| CN112784655A (en) * | 2019-11-11 | 2021-05-11 | 七鑫易维(深圳)科技有限公司 | Living body detection method and device based on gazing information and detection equipment |
| CN113255529A (en) * | 2021-05-28 | 2021-08-13 | 支付宝(杭州)信息技术有限公司 | Biological feature identification method, device and equipment |
| CN113420613A (en) * | 2021-06-03 | 2021-09-21 | 中国联合网络通信集团有限公司 | Identity verification method based on face recognition, face recognition system and associated equipment |
| CN113886791A (en) * | 2021-10-19 | 2022-01-04 | 中国科学院上海微系统与信息技术研究所 | Identity information determining method and device, electronic equipment and storage medium |
| CN114677746A (en) * | 2022-04-15 | 2022-06-28 | Oppo广东移动通信有限公司 | Living body face detection method and device, storage medium and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101710383A (en) * | 2009-10-26 | 2010-05-19 | 北京中星微电子有限公司 | Method and device for identity authentication |
| CN102309366A (en) * | 2011-07-21 | 2012-01-11 | 山东科技大学 | Control system and control method for controlling upper prosthesis to move by using eye movement signals |
| CN102749991A (en) * | 2012-04-12 | 2012-10-24 | 广东百泰科技有限公司 | Non-contact free space eye-gaze tracking method suitable for man-machine interaction |
| CN102842040A (en) * | 2012-08-13 | 2012-12-26 | 高艳玲 | Living body detection method utilizing eye tracing |
| CN103186240A (en) * | 2013-03-25 | 2013-07-03 | 成都西可科技有限公司 | High-pixel camera-based method for detecting eye movement |
| CN104123543A (en) * | 2014-07-23 | 2014-10-29 | 泰亿格电子（上海）有限公司 | Eyeball movement identification method based on face identification |
| CN104158980A (en) * | 2014-08-28 | 2014-11-19 | 西安交通大学 | Intelligent equipment unlocking method based on human eye motion feature |
| CN105184246A (en) * | 2015-08-28 | 2015-12-23 | 北京旷视科技有限公司 | Living body detection method and living body detection system |
-
2015
- 2015-09-29 CN CN201510629903.0A patent/CN105184277B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101710383A (en) * | 2009-10-26 | 2010-05-19 | 北京中星微电子有限公司 | Method and device for identity authentication |
| CN102309366A (en) * | 2011-07-21 | 2012-01-11 | 山东科技大学 | Control system and control method for controlling upper prosthesis to move by using eye movement signals |
| CN102749991A (en) * | 2012-04-12 | 2012-10-24 | 广东百泰科技有限公司 | Non-contact free space eye-gaze tracking method suitable for man-machine interaction |
| CN102842040A (en) * | 2012-08-13 | 2012-12-26 | 高艳玲 | Living body detection method utilizing eye tracing |
| CN103186240A (en) * | 2013-03-25 | 2013-07-03 | 成都西可科技有限公司 | High-pixel camera-based method for detecting eye movement |
| CN104123543A (en) * | 2014-07-23 | 2014-10-29 | 泰亿格电子（上海）有限公司 | Eyeball movement identification method based on face identification |
| CN104158980A (en) * | 2014-08-28 | 2014-11-19 | 西安交通大学 | Intelligent equipment unlocking method based on human eye motion feature |
| CN105184246A (en) * | 2015-08-28 | 2015-12-23 | 北京旷视科技有限公司 | Living body detection method and living body detection system |
Cited By (62)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107092818A (en) * | 2016-02-17 | 2017-08-25 | 阿里巴巴集团控股有限公司 | The implementation method and device of vivo identification |
| CN107305629A (en) * | 2016-04-21 | 2017-10-31 | 王溯 | Sight identifying device and method |
| CN109074441A (en) * | 2016-04-29 | 2018-12-21 | 微软技术许可有限责任公司 | Based on the certification watched attentively |
| CN109074441B (en) * | 2016-04-29 | 2021-06-04 | 微软技术许可有限责任公司 | Gaze-based authentication |
| WO2018001371A1 (en) * | 2016-06-30 | 2018-01-04 | 北京七鑫易维信息技术有限公司 | Method and apparatus for identity recognition |
| CN106203297A (en) * | 2016-06-30 | 2016-12-07 | 北京七鑫易维信息技术有限公司 | A kind of personal identification method and device |
| CN106203297B (en) * | 2016-06-30 | 2019-11-08 | 北京七鑫易维信息技术有限公司 | A kind of personal identification method and device |
| US10891507B2 (en) | 2016-06-30 | 2021-01-12 | Beijing 7Invensun Technology Co., Ltd. | Method and device for recognizing identity |
| CN106169075A (en) * | 2016-07-11 | 2016-11-30 | 北京小米移动软件有限公司 | Auth method and device |
| CN107622188A (en) * | 2016-07-15 | 2018-01-23 | 阿里巴巴集团控股有限公司 | Verification method, device, system and equipment based on biological characteristic |
| CN110114777B (en) * | 2016-12-30 | 2023-10-20 | 托比股份公司 | Identification, authentication and/or guidance of a user using gaze information |
| CN110114777A (en) * | 2016-12-30 | 2019-08-09 | 托比股份公司 | Use identification, certification and/or the guiding of the user for watching information progress attentively |
| CN108256406A (en) * | 2017-01-05 | 2018-07-06 | 广州市晶密电子有限公司 | It is a kind of that the data processing method of face recognition and its device are realized by eyes orientation direction |
| CN108256406B (en) * | 2017-01-05 | 2023-11-03 | 广州市晶密电子有限公司 | Data processing method and device for realizing face recognition through eye positioning guidance |
| WO2018133584A1 (en) * | 2017-01-17 | 2018-07-26 | 中兴通讯股份有限公司 | Identity authentication method and device |
| CN108319830A (en) * | 2017-01-17 | 2018-07-24 | 中兴通讯股份有限公司 | A kind of auth method and device |
| CN108345818A (en) * | 2017-01-23 | 2018-07-31 | 北京中科奥森数据科技有限公司 | A kind of human face in-vivo detection method and device |
| CN108345818B (en) * | 2017-01-23 | 2021-08-31 | 北京中科奥森数据科技有限公司 | Face living body detection method and device |
| CN106713368B (en) * | 2017-03-08 | 2019-09-27 | 四川大学 | A kind of auth method and device |
| CN106713368A (en) * | 2017-03-08 | 2017-05-24 | 四川大学 | Identity authentication method and identity authentication device |
| CN106850685A (en) * | 2017-03-25 | 2017-06-13 | 安徽味唯网络科技有限公司 | A kind of auth method for having a sense of independence |
| CN108693543A (en) * | 2017-03-31 | 2018-10-23 | 法拉第未来公司 | Method and system for detecting signal deception |
| CN107273794A (en) * | 2017-04-28 | 2017-10-20 | 北京建筑大学 | Live body discrimination method and device in a kind of face recognition process |
| CN107154095A (en) * | 2017-06-06 | 2017-09-12 | 信利光电股份有限公司 | A kind of car entry system and method |
| CN107451547A (en) * | 2017-07-17 | 2017-12-08 | 广东欧珀移动通信有限公司 | Identify the method and Related product of live body |
| CN107590429A (en) * | 2017-07-20 | 2018-01-16 | 阿里巴巴集团控股有限公司 | The method and device verified based on eyeprint feature |
| WO2019024717A1 (en) * | 2017-07-29 | 2019-02-07 | Oppo广东移动通信有限公司 | Anti-counterfeiting processing method and related product |
| CN107506696A (en) * | 2017-07-29 | 2017-12-22 | 广东欧珀移动通信有限公司 | Anti-fake processing method and related product |
| US11074466B2 (en) | 2017-07-29 | 2021-07-27 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Anti-counterfeiting processing method and related products |
| CN108304784A (en) * | 2018-01-15 | 2018-07-20 | 武汉神目信息技术有限公司 | A kind of blink detection method and device |
| CN108399365B (en) * | 2018-01-19 | 2022-03-25 | 东北电力大学 | Method and device for detecting living human face by using pupil diameter |
| CN108537103B (en) * | 2018-01-19 | 2022-06-10 | 东北电力大学 | Living body face detection method and device based on pupil axis measurement |
| CN108399365A (en) * | 2018-01-19 | 2018-08-14 | 东北电力大学 | The method and its equipment of living body faces are detected using pupil diameter |
| CN108537103A (en) * | 2018-01-19 | 2018-09-14 | 东北电力大学 | The living body faces detection method and its equipment measured based on pupil axle |
| CN108701228A (en) * | 2018-04-18 | 2018-10-23 | 深圳阜时科技有限公司 | Identification authentication method, identification authentication device and electronic equipment |
| CN108615159A (en) * | 2018-05-03 | 2018-10-02 | 百度在线网络技术（北京）有限公司 | Access control method and device based on blinkpunkt detection |
| CN108900700A (en) * | 2018-06-04 | 2018-11-27 | 北京大学 | Authentication method and system based on the double verification that recognition of face and sight position |
| CN110738072A (en) * | 2018-07-18 | 2020-01-31 | 浙江宇视科技有限公司 | Living body judgment method and device |
| TWI706270B (en) * | 2018-08-13 | 2020-10-01 | 香港商阿里巴巴集團服務有限公司 | Identity recognition method, device and computer readable storage medium |
| CN109325462B (en) * | 2018-10-11 | 2021-03-12 | 深圳斐视沃德科技有限公司 | Face recognition living body detection method and device based on iris |
| CN109325462A (en) * | 2018-10-11 | 2019-02-12 | 深圳斐视沃德科技有限公司 | Recognition of face biopsy method and device based on iris |
| CN111046696A (en) * | 2018-10-12 | 2020-04-21 | 宏碁股份有限公司 | Living body identification method and electronic device |
| CN109753871A (en) * | 2018-11-21 | 2019-05-14 | 惠州Tcl移动通信有限公司 | A kind of method and mobile terminal of recognition of face |
| CN109271978A (en) * | 2018-11-23 | 2019-01-25 | 四川长虹电器股份有限公司 | Recognition of face anti-fraud method |
| CN109871796A (en) * | 2019-01-31 | 2019-06-11 | 杭州创匠信息科技有限公司 | Method for anti-counterfeit and device based on living body iris |
| KR102442220B1 (en) * | 2019-05-20 | 2022-09-08 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Living-body detection method and apparatus for face, electronic device ad computer readable medium |
| KR20200134160A (en) * | 2019-05-20 | 2020-12-01 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Living-body detection method and apparatus for face, electronic device ad computer readable medium |
| CN110135370A (en) * | 2019-05-20 | 2019-08-16 | 北京百度网讯科技有限公司 | The method and device of face In vivo detection, electronic equipment, computer-readable medium |
| US11188771B2 (en) | 2019-05-20 | 2021-11-30 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Living-body detection method and apparatus for face, and computer readable medium |
| CN110720105A (en) * | 2019-09-11 | 2020-01-21 | 深圳市汇顶科技股份有限公司 | Face anti-counterfeiting detection method, device, chip, electronic equipment and computer readable medium |
| CN112784655A (en) * | 2019-11-11 | 2021-05-11 | 七鑫易维(深圳)科技有限公司 | Living body detection method and device based on gazing information and detection equipment |
| CN111159678A (en) * | 2019-12-26 | 2020-05-15 | 联想(北京)有限公司 | Identity recognition method, device and storage medium |
| CN111159678B (en) * | 2019-12-26 | 2023-08-18 | 联想(北京)有限公司 | Identity recognition method, device and storage medium |
| CN111324878A (en) * | 2020-02-05 | 2020-06-23 | 重庆特斯联智慧科技股份有限公司 | Identity verification method and device based on face recognition, storage medium and terminal |
| CN111967293A (en) * | 2020-06-22 | 2020-11-20 | 云知声智能科技股份有限公司 | Face authentication method and system combining voiceprint recognition and attention detection |
| CN112016482A (en) * | 2020-08-31 | 2020-12-01 | 成都新潮传媒集团有限公司 | Method and device for distinguishing false face and computer equipment |
| CN112257050A (en) * | 2020-10-26 | 2021-01-22 | 上海鹰瞳医疗科技有限公司 | Identity authentication method and equipment based on gazing action |
| CN113255529A (en) * | 2021-05-28 | 2021-08-13 | 支付宝(杭州)信息技术有限公司 | Biological feature identification method, device and equipment |
| CN113420613B (en) * | 2021-06-03 | 2023-09-05 | 中国联合网络通信集团有限公司 | Identity verification method based on face recognition, face recognition system and associated equipment |
| CN113420613A (en) * | 2021-06-03 | 2021-09-21 | 中国联合网络通信集团有限公司 | Identity verification method based on face recognition, face recognition system and associated equipment |
| CN113886791A (en) * | 2021-10-19 | 2022-01-04 | 中国科学院上海微系统与信息技术研究所 | Identity information determining method and device, electronic equipment and storage medium |
| CN114677746A (en) * | 2022-04-15 | 2022-06-28 | Oppo广东移动通信有限公司 | Living body face detection method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105184277B (en) | 2020-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105184277A (en) | Living body human face recognition method and device | |
| CN107609383B (en) | 3D face identity authentication method and device | |
| CN107748869B (en) | 3D face identity authentication method and device | |
| KR102573482B1 (en) | Biometric security system and method | |
| CN107633165B (en) | 3D face identity authentication method and device | |
| CN106407914B (en) | Method and device for detecting human face and remote teller machine system | |
| JP6722272B2 (en) | User identification and/or authentication using gaze information | |
| US9791927B2 (en) | Systems and methods of eye tracking calibration | |
| US10678897B2 (en) | Identification, authentication, and/or guiding of a user using gaze information | |
| CN106295287B (en) | Biopsy method and device and identity identifying method and device | |
| KR101356358B1 (en) | Computer-implemented method and apparatus for biometric authentication based on images of an eye | |
| US20090273562A1 (en) | Enhancing computer screen security using customized control of displayed content area | |
| JP2019522278A (en) | Identification method and apparatus | |
| CN104584070A (en) | Authentication device and authentication method | |
| CN108875468B (en) | Living body detection method, living body detection system, and storage medium | |
| CN106709303B (en) | Display method and device and intelligent terminal | |
| CN110114777A (en) | Use identification, certification and/or the guiding of the user for watching information progress attentively | |
| WO2020020022A1 (en) | Method for visual recognition and system thereof | |
| KR101738593B1 (en) | System and method for authenticating user by multiple means | |
| CN106599656A (en) | Display method, device and electronic equipment | |
| CN104615993B (en) | The certification device and method that a kind of finger vena identification combines with face hand vein recognition | |
| CN111445640A (en) | Express delivery pickup method, device, equipment and storage medium based on iris recognition | |
| CN113260299A (en) | System and method for eye tracking | |
| CN107209936B (en) | Information processing apparatus, information processing method, and program | |
| CN114967128B (en) | Sight tracking system and method applied to VR glasses |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |