CN109784124A - A kind of determination method of vivo identification, decision-making system and computer installation - Google Patents
A kind of determination method of vivo identification, decision-making system and computer installation Download PDFInfo
- Publication number
- CN109784124A CN109784124A CN201711102090.5A CN201711102090A CN109784124A CN 109784124 A CN109784124 A CN 109784124A CN 201711102090 A CN201711102090 A CN 201711102090A CN 109784124 A CN109784124 A CN 109784124A
- Authority
- CN
- China
- Prior art keywords
- facial
- face
- living body
- identification
- area ratio
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention proposes a kind of determination method of vivo identification, decision-making system, computer installation and computer readable storage medium, the determination method of vivo identification includes: to send commander's action command;Receive the image information of the identification target according to commander's action command feedback;Face-image area ratio is calculated according to image information;Judge whether face-image area ratio is more than or equal to preset threshold;When facial image area ratio is less than preset threshold, determine that identification target is non-living body;When facial image area ratio is more than or equal to preset threshold, determine that identification target is living body.The present invention by face-image area ratio carry out living body judgement, can be effectively avoided by two-dimension picture substitute living body carry out face recognition the case where, can guarantee in face recognition scene using safe.
Description
Technical field
The present invention relates to area of face recognition technology, are in particular to a kind of determination method of vivo identification, judgement
System, computer installation and computer readable storage medium.
Background technique
The relevant technologies face recognition scene (for example, realizing door by face identification logging-on system, by recognition of face
Prohibit unlatching etc.) in, user can may be replaced by the photo of user, realize face recognition.In addition, further, it can
Me can also be replaced by threedimensional model, identifier of out-tricking.Therefore it provides it is a kind of accurately and can judge two-dimension picture and
The In vivo detection technology of threedimensional model is very important.
Summary of the invention
The present invention is directed to solve at least one of the technical problems existing in the prior art or related technologies.
For this purpose, one aspect of the present invention is to propose a kind of determination method of vivo identification.
Another aspect of the present invention is to propose a kind of decision-making system of vivo identification.
Another aspect of the invention is to propose a kind of computer installation.
An additional aspect of the present invention is to propose a kind of computer readable storage medium.
In view of this, according to an aspect of the present invention, it proposes a kind of determination methods of vivo identification, comprising: send
Command action command;Receive the image information of the identification target according to commander's action command feedback;Face is calculated according to image information
Portion's image area ratio;Judge whether face-image area ratio is more than or equal to preset threshold;When facial image area ratio is small
When preset threshold, determine that identification target is non-living body;When facial image area ratio is more than or equal to preset threshold, determine to know
Other target is living body.
The determination method of vivo identification provided by the invention sends commander's action command to identification target, and commander's movement refers to
Order may include " please shake the head and keep to the left ", " please shake the head and keep to the right " etc., and control camera takes identification target
Image information receives the ratio that two face-image areas are calculated after the image information, according to face-image area ratio
Determine whether identification target is living body with the size relation of preset threshold, wherein preset threshold can be system default value (for example,
1.5) it, can also be manually set.That is, two face-images when facial image area ratio is more than or equal to preset threshold
Area is different, illustrates that the identification target is acted according to the instruction execution really, therefore, it is determined that it is living body.The present invention passes through face
Portion's image area ratio carries out living body judgement, can be effectively avoided and substitutes the feelings that living body carries out face recognition by two-dimension picture
Condition, can guarantee in face recognition scene using safe.
The determination method of above-mentioned vivo identification according to the present invention, can also have following technical characteristic:
In the above-mentioned technical solutions, it is preferable that further include: it sends and plays video instructions;It is receiving according to broadcasting video
After the EEG signals of the identification target of instruction feedback, determine that identification target is living body.
In the technical scheme, by causing to identify to identification target shuffle video pictures (for example, terrified picture)
The mood swing of target, the mood swing can be presented as the fluctuation of EEG signals, and then can be by detecting and analyzing brain electricity
Signal carries out living body determination.Wherein EEG signals refer to that the neuron activity of brain reaches cerebral cortex by ionic conduction, lead to
It crosses and fixes the faint voltage change that overhead conductive electrode senses.Carrying out living body judgement by EEG signals can be effective
Ground avoids passing through the case where three-dimensional stereo model carries out face recognition instead of living body.
In any of the above-described technical solution, it is preferable that when facial image area ratio is more than or equal to preset threshold, sentence
Surely identification target is after living body, further includes: sends and plays video instructions;When receive according to play video instructions feedback knowledge
After the EEG signals of other target, further determine that identification target is living body.
In the technical scheme, it after carrying out living body judgement by face-image area ratio, is further advanced by identification
Target shuffle video pictures cause the mood swing for identifying target, receive EEG signals and determine that identification target is living body, i.e.,
Carry out secondary judgement.It is effectively prevented from the case where replacing living body to carry out face recognition by two-dimension picture, and avoids passing through three
The case where dimension module replaces living body to carry out face recognition improves the safety in utilization in face recognition scene to a greater degree.
In any of the above-described technical solution, it is preferable that the step of calculating face-image area ratio according to image information, tool
Body includes: the facial information identified in image information, and facial information includes first facial position, the second facial positions, third face
Portion position, fourth face portion position, the 5th facial positions;Obtain first facial position, third facial positions, fourth face portion set of locations
At the first triangle area;Obtain the second triangle that the second facial positions, third facial positions, the 5th facial positions form
The area of shape;The ratio for calculating the area of the first triangle and the area of the second triangle, as face-image area ratio.
In the technical scheme, five facial positions having in image information are identified, and pass through five facial positions
Two different triangles are formed, i.e. face left side triangle and face right side triangle, calculates separately out the two triangles
Area, and then calculate two triangle areas ratio.Specifically, when above-mentioned commander's action command is " please to shake the head to the left simultaneously
Keep " when, ratio is the ratio of right side triangle area and left side triangle area;When above-mentioned commander's action command be " please to
Shake the head and keep in the right side " when, ratio be left side triangle area and right side triangle area ratio, can be by the ratio into
Whether row for the judgement of living body provides foundation.
In any of the above-described technical solution, it is preferable that third facial positions are prenasale position;When commander's action command is
When shaking the head and keep to the left, first facial position is right position of eye point, the second facial positions are left position of eye point, fourth face position
It is set to right corners of the mouth position, the 5th facial positions are left corners of the mouth position;When commanding action command is to shake the head and keep to the right, first
Facial positions are left position of eye point, the second facial positions are that right position of eye point, fourth face position are set to left corners of the mouth position, the 5th face
Position is set to right corners of the mouth position.
In the technical scheme, the facial positions specifically identified include prenasale position, right position of eye point, left eye point
It sets, right corners of the mouth position, left corners of the mouth position, for example, left (right side) position of eye point can be left (right side) eye center (pupil) position, a left side
(right side) canthus position, when shaking the head to the left, right position of eye point, prenasale position, right corners of the mouth position form the first triangle, left eye
Point position, prenasale position, left corners of the mouth position form the second triangle;When shaking the head to the right, left position of eye point, nose point
It sets, left corners of the mouth position forms the first triangle, right position of eye point, prenasale position, right corners of the mouth position the second triangle of composition;It is logical
Face-image area can be accurately acquired by crossing above-mentioned facial positions.It is above-mentioned it is left and right be based on user
Direction, if when direction based on camera, above-mentioned face-image area ratio is the area and the one or three of the second triangle
The ratio of angular area.
It should be noted that fourth face portion position and the 5th facial positions can also be mouth center or upper mouth
Point position or lower mouth point position.
According to another aspect of the present invention, a kind of decision-making system of vivo identification is proposed, comprising: transmission unit is used
Action command is commanded in sending;Receiving unit, for receiving the image information of the identification target according to commander's action command feedback;
Computing unit, for calculating face-image area ratio according to image information;Judging unit, for judging face-image area ratio
Whether value is more than or equal to preset threshold;When facial image area ratio is less than preset threshold, determine that identification target is non-living body;
When facial image area ratio is more than or equal to preset threshold, determine that identification target is living body.
The decision-making system of vivo identification provided by the invention, transmission unit send commander's action command to identification target, refer to
Waving action command may include " please shake the head and keep to the left ", " please shake the head and keep to the right " etc., and control camera takes knowledge
The image information of other target after receiving unit receives the image information, calculates two face-image faces by computing unit
Long-pending ratio, judging unit determine whether identification target is living according to the size relation of face-image area ratio and preset threshold
Body, wherein preset threshold can be system default value (for example, 1.5), can also be manually set.That is, working as face-image
Two face-image areas are different when area ratio is more than or equal to preset threshold, illustrate that the identification target is held according to the instruction really
Movement is gone, therefore, it is determined that it is living body.The present invention carries out living body judgement by face-image area ratio, can effectively keep away
Exempt from by two-dimension picture substitute living body carry out face recognition the case where, can guarantee in face recognition scene using safe.
The decision-making system of above-mentioned vivo identification according to the present invention, can also have following technical characteristic:
In the above-mentioned technical solutions, it is preferable that transmission unit is also used to send broadcasting video instructions;Receiving unit is also used
In the EEG signals for receiving the identification target according to broadcasting video instructions feedback;Judging unit is also used to receiving according to broadcasting
After the EEG signals for putting the identification target of video instructions feedback, determine that identification target is living body.
In the technical scheme, by causing to identify to identification target shuffle video pictures (for example, terrified picture)
The mood swing of target, the mood swing can be presented as the fluctuation of EEG signals, and then can be by detecting and analyzing brain electricity
Signal carries out living body determination.Wherein EEG signals refer to that the neuron activity of brain reaches cerebral cortex by ionic conduction, lead to
It crosses and fixes the faint voltage change that overhead conductive electrode senses.Carrying out living body judgement by EEG signals can be effective
Ground avoids passing through the case where three-dimensional stereo model carries out face recognition instead of living body.
In any of the above-described technical solution, it is preferable that transmission unit is also used to be greater than when facial image area ratio etc.
When preset threshold, after determining identification target for living body, sends and play video instructions;Receiving unit is also used to receive basis
Play the EEG signals of the identification target of video instructions feedback;Judging unit is also used to receiving according to broadcasting video instructions
After the EEG signals of the identification target of feedback, determine that identification target is living body.
In the technical scheme, it after carrying out living body judgement by face-image area ratio, is further advanced by identification
Target shuffle video pictures cause the mood swing for identifying target, receive EEG signals and determine that identification target is living body, i.e.,
Carry out secondary judgement.It is effectively prevented from the case where replacing living body to carry out face recognition by two-dimension picture, and avoids passing through three
The case where dimension module replaces living body to carry out face recognition improves the safety in utilization in face recognition scene to a greater degree.
In any of the above-described technical solution, it is preferable that computing unit, comprising: recognition unit, for identification in image information
Facial information, facial information includes first facial position, the second facial positions, third facial positions, fourth face portion position,
Five facial positions;Acquiring unit, for obtain first facial position, third facial positions, fourth face portion position composition first
The area of triangle;And obtain the second triangle that the second facial positions, third facial positions, the 5th facial positions form
Area;Computing unit is schemed specifically for calculating the ratio of the area of the first triangle and the area of the second triangle as face
As area ratio.
In the technical scheme, five facial positions having in image information are identified, and pass through five facial positions
Two different triangles are formed, i.e. face left side triangle and face right side triangle, calculates separately out the two triangles
Area, and then calculate two triangle areas ratio.Specifically, when above-mentioned commander's action command is " please to shake the head to the left simultaneously
Keep " when, ratio is the ratio of right side triangle area and left side triangle area;When above-mentioned commander's action command be " please to
Shake the head and keep in the right side " when, ratio be left side triangle area and right side triangle area ratio, can be by the ratio into
Whether row for the judgement of living body provides foundation.
In any of the above-described technical solution, it is preferable that third facial positions are prenasale position;When commander's action command is
When shaking the head and keep to the left, first facial position is right position of eye point, the second facial positions are left position of eye point, fourth face position
It is set to right corners of the mouth position, the 5th facial positions are left corners of the mouth position;When commanding action command is to shake the head and keep to the right, first
Facial positions are left position of eye point, the second facial positions are that right position of eye point, fourth face position are set to left corners of the mouth position, the 5th face
Position is set to right corners of the mouth position.
In the technical scheme, the facial positions specifically identified include prenasale position, right position of eye point, left eye point
It sets, right corners of the mouth position, left corners of the mouth position, for example, left (right side) position of eye point can be left (right side) eye center (pupil) position, a left side
(right side) canthus position, when shaking the head to the left, right position of eye point, prenasale position, right corners of the mouth position form the first triangle, left eye
Point position, prenasale position, left corners of the mouth position form the second triangle;When shaking the head to the right, left position of eye point, nose point
It sets, left corners of the mouth position the first triangle of composition, right position of eye point, prenasale position, right corners of the mouth position form the second triangle, lead to
Face-image area can be accurately acquired by crossing above-mentioned facial positions.It is above-mentioned it is left and right be based on user
Direction, if when direction based on camera, above-mentioned face-image area ratio is the area and the one or three of the second triangle
The ratio of angular area.
It should be noted that fourth face portion position and the 5th facial positions can also be mouth center or upper mouth
Point position or lower mouth point position.
According to a further aspect of the invention, it proposes a kind of computer installation, including memory, processor and is stored in
On memory and the computer program that can run on a processor, processor realize such as any of the above-described when executing computer program
Vivo identification determination method the step of.
Computer installation provided by the invention, processor realize that sending commander to identification target moves when executing computer program
It instructs, commander's action command may include " please shake the head and keep to the left ", " please shake the head and keep to the right " etc., control camera
The image information for taking identification target receives the ratio that two face-image areas are calculated after the image information, according to
The size relation of face-image area ratio and preset threshold determines whether identification target is living body, and wherein preset threshold can be
System default value (for example, 1.5), can also be manually set.That is, when facial image area ratio is more than or equal to default threshold
Two face-image areas are different when value, illustrate that the identification target is acted according to the instruction execution really, therefore, it is determined that it is
Living body.The present invention carries out living body judgement by face-image area ratio, can be effectively avoided to substitute by two-dimension picture and live
Body carry out face recognition the case where, can guarantee in face recognition scene using safe.
According to a further aspect of the invention, a kind of computer readable storage medium is proposed, computer is stored thereon with
Program, when computer program is executed by processor the step of the realization such as determination method of the vivo identification of any of the above-described.
Computer readable storage medium provided by the invention is realized when computer program is executed by processor to identification target
Commander's action command is sent, commander's action command may include " please shake the head and keep to the left ", " please shake the head and keep to the right " etc.,
Control camera takes the image information of identification target, calculates two face-image areas after receiving the image information
Ratio determines whether identification target is living body according to the size relation of face-image area ratio and preset threshold, wherein presetting
Threshold value can be system default value (for example, 1.5), can also be manually set.That is, when facial image area ratio is greater than
Two face-image areas are different when equal to preset threshold, illustrate that the identification target is acted according to the instruction execution really, because
This determines that it is living body.The present invention carries out living body judgement by face-image area ratio, can be effectively avoided and passes through two dimension
Picture substitute living body carry out face recognition the case where, can guarantee in face recognition scene using safe.
Additional aspect and advantage of the invention will become obviously in following description section, or practice through the invention
Recognize.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 shows the flow diagram of the determination method of the vivo identification of one embodiment of the present of invention;
Fig. 2 shows the flow diagrams of the determination method of the vivo identification of another embodiment of the invention;
Fig. 3 shows the flow diagram of the determination method of the vivo identification of yet another embodiment of the present invention;
Fig. 4 shows the flow diagram of the determination method of the vivo identification of another embodiment of the invention;
Fig. 5 a shows the schematic diagram of facial triagnle shaped position when shaking the head to the left of one embodiment of the present of invention;
Figure 5b shows that the schematic diagrames of facial triagnle shaped position when shaking the head to the right of another embodiment of the invention;
Fig. 6 a shows the schematic block diagram of the decision-making system of the vivo identification of one embodiment of the present of invention;
Fig. 6 b shows the schematic block diagram of the decision-making system of the vivo identification of another embodiment of the invention;
Fig. 7 shows the schematic block diagram of the computer installation of one embodiment of the present of invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention is further described in detail.It should be noted that in the absence of conflict, the implementation of the application
Feature in example and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
To be implemented using other than the one described here other modes, therefore, protection scope of the present invention is not limited to following public affairs
The limitation for the specific embodiment opened.
The embodiment of first aspect present invention proposes that a kind of determination method of vivo identification, Fig. 1 show of the invention one
The flow diagram of the determination method of the vivo identification of a embodiment.Wherein, this method comprises:
Step 102, commander's action command is sent;
Step 104, the image information of the identification target according to commander's action command feedback is received;
Step 106, face-image area ratio is calculated according to image information;
Step 108, judge whether face-image area ratio is more than or equal to preset threshold;
Step 110, when facial image area ratio is less than preset threshold, determine that identification target is non-living body;
Step 112, determine that identification target is living body when facial image area ratio is more than or equal to preset threshold.
The determination method of vivo identification provided by the invention sends commander's action command to identification target, and commander's movement refers to
Order may include " please shake the head and keep to the left ", " please shake the head and keep to the right " etc., and control camera takes identification target
Image information receives the ratio that two face-image areas are calculated after the image information, according to face-image area ratio
Determine whether identification target is living body with the size relation of preset threshold, wherein preset threshold can be system default value (for example,
1.5) it, can also be manually set.That is, two face-images when facial image area ratio is more than or equal to preset threshold
Area is different, illustrates that the identification target is acted according to the instruction execution really, therefore, it is determined that it is living body.The present invention passes through face
Portion's image area ratio carries out living body judgement, can be effectively avoided and substitutes the feelings that living body carries out face recognition by two-dimension picture
Condition, can guarantee in face recognition scene using safe.
Fig. 2 shows the flow diagrams of the determination method of the vivo identification of another embodiment of the invention.Wherein, should
Method includes:
Step 202, it sends and plays video instructions;
Step 204, after receiving the EEG signals according to the identification target for playing video instructions feedback, determine identification mesh
It is designated as living body.
In this embodiment, by causing to identify mesh to identification target shuffle video pictures (for example, terrified picture)
Target mood swing, the mood swing can be presented as the fluctuation of EEG signals, and then can be by detecting and analyzing brain telecommunications
Number, carry out living body determination.Wherein EEG signals refer to that the neuron activity of brain reaches cerebral cortex by ionic conduction, pass through
The faint voltage change that fixed overhead conductive electrode senses.Carrying out living body judgement by EEG signals can be effectively
Avoid passing through the case where three-dimensional stereo model carries out face recognition instead of living body.
Fig. 3 shows the flow diagram of the determination method of the vivo identification of yet another embodiment of the present invention.Wherein, should
Method includes:
Step 302, commander's action command is sent;
Step 304, the image information of the identification target according to commander's action command feedback is received;
Step 306, face-image area ratio is calculated according to image information;
Step 308, judge whether face-image area ratio is more than or equal to preset threshold;
Step 310, when facial image area ratio is less than preset threshold, determine that identification target is non-living body;
Step 312, when facial image area ratio is more than or equal to preset threshold, determine that identification target is living body;
Step 314, it sends and plays video instructions;
Step 316, it after receiving the EEG signals according to the identification target for playing video instructions feedback, further determines
Identification target is living body.
In this embodiment, it after carrying out living body judgement by face-image area ratio, is further advanced by identification mesh
Mark shuffle video pictures cause identify target mood swing, receive EEG signals determine identification target be living body, i.e., into
The secondary judgement of row.It is effectively prevented from the case where replacing living body to carry out face recognition by two-dimension picture, and avoids passing through three-dimensional
The case where model replaces living body to carry out face recognition improves the safety in utilization in face recognition scene to a greater degree.
Fig. 4 shows the flow diagram of the determination method of the vivo identification of another embodiment of the invention.Wherein, should
Method includes:
Step 402, commander's action command is sent;
Step 404, the image information of the identification target according to commander's action command feedback is received;
Step 406, identify that the facial information in image information, facial information include first facial position, the second facial position
It sets, third facial positions, fourth face portion position, the 5th facial positions;
Step 408, the first triangle that acquisition first facial position, third facial positions, fourth face portion position form
Area;Obtain the area for the second triangle that the second facial positions, third facial positions, the 5th facial positions form;
Step 410, the ratio for calculating the area of the first triangle and the area of the second triangle, as face-image area
Ratio;
Step 412, judge whether face-image area ratio is more than or equal to preset threshold;
Step 414, when facial image area ratio is less than preset threshold, determine that identification target is non-living body;
Step 416, determine that identification target is living body when facial image area ratio is more than or equal to preset threshold;
Step 418, it sends and plays video instructions;
Step 420, it after receiving the EEG signals according to the identification target for playing video instructions feedback, further determines
Identification target is living body.
In this embodiment, five facial positions having in image information are identified, and pass through five facial positions groups
At two different triangles, i.e. face left side triangle and face right side triangle, the two triangles are calculated separately out
Area, and then calculate the ratio of two triangle areas.Specifically, when above-mentioned commander's action command is " please to shake the head and protect to the left
Hold " when, ratio is the ratio of right side triangle area and left side triangle area;When above-mentioned commander's action command is " please to the right
Shake the head and keep " when, ratio is the ratio of left side triangle area and right side triangle area, can be to be carried out by the ratio
Whether for the judgement of living body foundation is provided.
In one embodiment of the invention, it is preferable that third facial positions are prenasale position;When commander's action command
When to shake the head and keep to the left, first facial position is right position of eye point, the second facial positions are left position of eye point, fourth face portion
Position is right corners of the mouth position, the 5th facial positions are left corners of the mouth position;When commanding action command is to shake the head and keep to the right, the
Position is set to left position of eye point on one side, the second facial positions are right position of eye point, fourth face position is set to left corners of the mouth position, the 5th
Facial positions are right corners of the mouth position.
In this embodiment, the facial positions specifically identified include prenasale position, right position of eye point, left position of eye point,
Right corners of the mouth position, left corners of the mouth position, for example, left (right side) position of eye point can be left (right side) eye center (pupil) position, a left side (right side)
Canthus position, when shaking the head to the left, as shown in Figure 5 a, right position of eye point, prenasale position, right corners of the mouth position form the first triangle
Shape 502, left position of eye point, prenasale position, left corners of the mouth position form the second triangle 504;As shown in Figure 5 b, it shakes the head when to the right
When, left position of eye point, prenasale position, left corners of the mouth position form the first triangle 502, right position of eye point, prenasale position, the right side
Corners of the mouth position forms the second triangle 504, can accurately acquire face-image area by above-mentioned facial positions.Above-mentioned
Left and right is the direction based on user, if when direction based on camera, above-mentioned face-image area ratio
For the ratio of the area of the area and the first triangle of the second triangle.
It should be noted that fourth face portion position and the 5th facial positions can also be mouth center or upper mouth
Point position or lower mouth point position.
The embodiment of second aspect of the present invention, proposes a kind of decision-making system of vivo identification, and Fig. 6 a shows of the invention
The schematic block diagram of the decision-making system 600 of the vivo identification of one embodiment.Wherein, which includes:
Transmission unit 602, for sending commander's action command;
Receiving unit 604, for receiving the image information of the identification target according to commander's action command feedback;
Computing unit 606, for calculating face-image area ratio according to image information;
Judging unit 608, for judging whether face-image area ratio is more than or equal to preset threshold;When facial image surface
When product ratio is less than preset threshold, determine that identification target is non-living body;When facial image area ratio is more than or equal to preset threshold
When, determine that identification target is living body.
The decision-making system 600 of vivo identification provided by the invention, transmission unit 602 send commander's movement to identification target and refer to
It enables, commander's action command may include " please shake the head and keep to the left ", " please shake the head and keep to the right " etc., control camera shooting
To the image information of identification target, after receiving unit 604 receives the image information, two are calculated by computing unit 606
The ratio of face-image area, judging unit 608 determine to know according to the size relation of face-image area ratio and preset threshold
Whether other target is living body, and wherein preset threshold can be system default value (for example, 1.5), can also be manually set.Namely
It says, when facial image area ratio is more than or equal to preset threshold, two face-image areas are different, illustrate that the identification target is true
Real root is acted according to the instruction execution, therefore, it is determined that it is living body.The present invention carries out living body by face-image area ratio and sentences
It is disconnected, it can be effectively avoided and the case where living body carries out face recognition is substituted by two-dimension picture, can guarantee face recognition scene
In using safe.
In one embodiment of the invention, it is preferable that transmission unit 602 is also used to send broadcasting video instructions;It receives
Unit 604 is also used to receive the EEG signals according to the identification target for playing video instructions feedback;Judging unit 608, is also used to
After receiving the EEG signals according to the identification target for playing video instructions feedback, determine that identification target is living body.
In this embodiment, by causing to identify mesh to identification target shuffle video pictures (for example, terrified picture)
Target mood swing, the mood swing can be presented as the fluctuation of EEG signals, and then can be by detecting and analyzing brain telecommunications
Number, carry out living body determination.Wherein EEG signals refer to that the neuron activity of brain reaches cerebral cortex by ionic conduction, pass through
The faint voltage change that fixed overhead conductive electrode senses.Carrying out living body judgement by EEG signals can be effectively
Avoid passing through the case where three-dimensional stereo model carries out face recognition instead of living body.
In one embodiment of the invention, it is preferable that transmission unit 602 is also used to when facial image area ratio
When more than or equal to preset threshold, after determining identification target for living body, sends and play video instructions;Receiving unit 604, is also used to
Receive the EEG signals according to the identification target for playing video instructions feedback;Judging unit 608 is also used to receiving according to broadcasting
After the EEG signals for putting the identification target of video instructions feedback, determine that identification target is living body.
In this embodiment, it after carrying out living body judgement by face-image area ratio, is further advanced by identification mesh
Mark shuffle video pictures cause identify target mood swing, receive EEG signals determine identification target be living body, i.e., into
The secondary judgement of row.It is effectively prevented from the case where replacing living body to carry out face recognition by two-dimension picture, and avoids passing through three-dimensional
The case where model replaces living body to carry out face recognition improves the safety in utilization in face recognition scene to a greater degree.
Fig. 6 b shows the schematic block diagram of the decision-making system 600 of the vivo identification of another embodiment of the invention.Wherein,
The system 600 includes:
Transmission unit 602, for sending commander's action command;
Receiving unit 604, for receiving the image information of the identification target according to commander's action command feedback;
Computing unit 606, comprising: recognition unit 6062, for identification facial information in image information, facial information packet
Include first facial position, the second facial positions, third facial positions, fourth face portion position, the 5th facial positions;Acquiring unit
6064, for obtain first facial position, third facial positions, fourth face portion position composition the first triangle area;With
And obtain the area for the second triangle that the second facial positions, third facial positions, the 5th facial positions form;
Computing unit 606, specifically for calculating the ratio of the area of the first triangle and the area of the second triangle, as
Face-image area ratio;
Judging unit 608, for judging whether face-image area ratio is more than or equal to preset threshold;When facial image surface
When product ratio is less than preset threshold, determine that identification target is non-living body;When facial image area ratio is more than or equal to preset threshold
When, determine that identification target is living body;
And transmission unit 602, it is also used to send broadcasting video instructions;Receiving unit 604 is also used to receive according to broadcasting
The EEG signals of the identification target of video instructions feedback;Judging unit 608, be also used to receive according to play video instructions it is anti-
After the EEG signals of the identification target of feedback, determine that identification target is living body.
In this embodiment, five facial positions having in image information are identified, and pass through five facial positions groups
At two different triangles, i.e. face left side triangle and face right side triangle, the two triangles are calculated separately out
Area, and then calculate the ratio of two triangle areas.Specifically, when above-mentioned commander's action command is " please to shake the head and protect to the left
Hold " when, ratio is the ratio of right side triangle area and left side triangle area;When above-mentioned commander's action command is " please to the right
Shake the head and keep " when, ratio is the ratio of left side triangle area and right side triangle area, can be to be carried out by the ratio
Whether for the judgement of living body foundation is provided.
In one embodiment of the invention, it is preferable that third facial positions are prenasale position;When commander's action command
When to shake the head and keep to the left, first facial position is right position of eye point, the second facial positions are left position of eye point, fourth face portion
Position is right corners of the mouth position, the 5th facial positions are left corners of the mouth position;When commanding action command is to shake the head and keep to the right, the
Position is set to left position of eye point on one side, the second facial positions are right position of eye point, fourth face position is set to left corners of the mouth position, the 5th
Facial positions are right corners of the mouth position.
In this embodiment, the facial positions specifically identified include prenasale position, right position of eye point, left position of eye point,
Right corners of the mouth position, left corners of the mouth position, for example, left (right side) position of eye point can be left (right side) eye center (pupil) position, a left side (right side)
Canthus position, when shaking the head to the left, as shown in Figure 5 a, right position of eye point, prenasale position, right corners of the mouth position form the first triangle
Shape 502, left position of eye point, prenasale position, left corners of the mouth position form the second triangle 504;As shown in Figure 5 b, it shakes the head when to the right
When, left position of eye point, prenasale position, left corners of the mouth position form the first triangle 502, right position of eye point, prenasale position, the right side
Corners of the mouth position forms the second triangle 504, can accurately acquire face-image area by above-mentioned facial positions.Above-mentioned
Left and right is the direction based on user, if when direction based on camera, above-mentioned face-image area ratio
For the ratio of the area of the area and the first triangle of the second triangle.
It should be noted that fourth face portion position and the 5th facial positions can also be mouth center or upper mouth
Point position or lower mouth point position.
In a specific embodiment of the invention, by measuring facial left and right sides product, when analysis EEG signals are carried out
In vivo detection, the specific steps are as follows:
Step 1 is issued to target to be detected and is instructed.The instruction may include: " please shake the head and keep to the left ", " please to the right
It shakes the head and keeps ".
Step 2, after target to be detected is shaken the head according to instruction, camera shoots the head image of target to be detected, and will
Image transmitting is to background processor.Background processor can identify the index point in image (for example, left eye, right eye, nose, mouth
Bar, left ear, auris dextra etc.), and further determine that left side area and right side area in head image.
It is specific for example, target to be detected shakes the head to the left after, camera shoots the head image of target to be detected.Background process
Device can identify left eye point in image, right eye point, prenasale, left corners of the mouth point and right corners of the mouth point, and further determine that right eye point, nose
The area of the closed triangle of cusp and right corners of the mouth point composition (is denoted as right side area b) and left eye point, prenasale and the left corners of the mouth
The area of the closed triangle of point composition (is denoted as left side area a), for example, left (right side) eyespot can be left (right side) eye center (pupil
Hole), left (right side) canthus.The process shaken the head to the right is also similar.
Step 3 determines the area ratio b/a of right side area and left side area.
Step 4, when area ratio b/a is greater than preset threshold, it can be determined that the target to be detected is living body.It is described default
Threshold value can be system default value (for example, 1.5), can also be manually set.
Step 5, by causing target to be detected to target shuffle video pictures to be detected (for example, terrified picture)
Mood swing, which can be presented as the fluctuation of EEG signals, so can by detecting and analyzing EEG signals,
Carry out living body determination.EEG signals refer to that the neuron activity of brain reaches cerebral cortex by ionic conduction, by being fixed on
The faint voltage change that conductive electrode on head senses.
Facial left and right sides product is measured than it is possible to prevente effectively from substituting living body by two-dimension picture carries out face recognition
Situation.EEG signals are analyzed it is possible to prevente effectively from the case where replacing living body to carry out face recognition by three-dimensional stereo model.In addition,
Step 1 to the method for step 4 or the method for step 5 can be used independently.
The embodiment of third aspect present invention proposes that a kind of computer installation, Fig. 7 show one embodiment of the present of invention
Computer installation 700 schematic block diagram.Wherein, which includes:
Memory 702, processor 704 and it is stored in the computer journey that can be run on memory 702 and on processor 704
The step of sequence, processor 704 realizes the determination method such as the vivo identification of any of the above-described when executing computer program.
Computer installation 700 provided by the invention, processor 704 is realized when executing computer program to be sent to identification target
Action command is commanded, commander's action command may include " please shake the head and keep to the left ", " please shake the head and keep to the right " etc., control
Camera takes the image information of identification target, receives the ratio that two face-image areas are calculated after the image information
Value determines whether identification target is living body according to the size relation of face-image area ratio and preset threshold, wherein default threshold
Value can be system default value (for example, 1.5), can also be manually set.That is, when facial image area ratio is greater than etc.
Two face-image areas are different when preset threshold, illustrate that the identification target is acted according to the instruction execution really, therefore
Determine that it is living body.The present invention carries out living body judgement by face-image area ratio, can be effectively avoided and passes through X-Y scheme
Piece substitute living body carry out face recognition the case where, can guarantee in face recognition scene using safe.
The embodiment of fourth aspect present invention proposes a kind of computer readable storage medium, is stored thereon with computer
Program, when computer program is executed by processor the step of the realization such as determination method of the vivo identification of any of the above-described.
Computer readable storage medium provided by the invention is realized when computer program is executed by processor to identification target
Commander's action command is sent, commander's action command may include " please shake the head and keep to the left ", " please shake the head and keep to the right " etc.,
Control camera takes the image information of identification target, calculates two face-image areas after receiving the image information
Ratio determines whether identification target is living body according to the size relation of face-image area ratio and preset threshold, wherein presetting
Threshold value can be system default value (for example, 1.5), can also be manually set.That is, when facial image area ratio is greater than
Two face-image areas are different when equal to preset threshold, illustrate that the identification target is acted according to the instruction execution really, because
This determines that it is living body.The present invention carries out living body judgement by face-image area ratio, can be effectively avoided and passes through two dimension
Picture substitute living body carry out face recognition the case where, can guarantee in face recognition scene using safe.
In the description of this specification, the description of term " one embodiment ", " some embodiments ", " specific embodiment " etc.
Mean that particular features, structures, materials, or characteristics described in conjunction with this embodiment or example are contained at least one reality of the invention
It applies in example or example.In the present specification, schematic expression of the above terms are not necessarily referring to identical embodiment or reality
Example.Moreover, description particular features, structures, materials, or characteristics can in any one or more of the embodiments or examples with
Suitable mode combines.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of determination method of vivo identification characterized by comprising
Send commander's action command;
Receive the image information of the identification target according to commander's action command feedback;
Face-image area ratio is calculated according to described image information;
Judge whether the face-image area ratio is more than or equal to preset threshold;
When the face-image area ratio is less than the preset threshold, determine that the identification target is non-living body;
When the face-image area ratio is more than or equal to the preset threshold, determine that the identification target is living body.
2. the determination method of vivo identification according to claim 1, which is characterized in that further include:
It sends and plays video instructions;
After receiving the EEG signals according to the identification target of the broadcasting video instructions feedback, determine that the identification target is
Living body.
3. the determination method of vivo identification according to claim 1, which is characterized in that working as the face-image area ratio
When value is more than or equal to the preset threshold, after determining the identification target for living body, further includes:
It sends and plays video instructions;
After receiving the EEG signals according to the identification target of the broadcasting video instructions feedback, the identification is further determined
Target is living body.
4. the determination method of vivo identification according to any one of claim 1 to 3, which is characterized in that according to the figure
The step of calculating the face-image area ratio as information, specifically includes:
Identify that the facial information in described image information, the facial information include first facial position, the second facial positions, the
Three facial positions, fourth face portion position, the 5th facial positions;
Obtain the first facial position, the third facial positions, fourth face portion position composition the first triangle
Area;
Obtain the second triangle that second facial positions, the third facial positions, the 5th facial positions form
Area;
The ratio for calculating the area of first triangle and the area of second triangle, as the face-image area
Ratio.
5. the determination method of vivo identification according to claim 4, which is characterized in that the third facial positions are nose
Point position;
When commander's action command is to shake the head and keep to the left, the first facial position is right position of eye point, described the
Two facial positions are left position of eye point, the fourth face position is set to right corners of the mouth position, the 5th facial positions are the left corners of the mouth
Position;
When commander's action command is to shake the head and keep to the right, the first facial position is the left position of eye point, institute
It states the second facial positions and is set to left corners of the mouth position, the 5th facial positions for the right position of eye point, the fourth face position
For right corners of the mouth position.
6. a kind of decision-making system of vivo identification characterized by comprising
Transmission unit, for sending commander's action command;
Receiving unit, for receiving the image information of the identification target according to commander's action command feedback;
Computing unit, for calculating face-image area ratio according to described image information;
Judging unit, for judging whether the face-image area ratio is more than or equal to preset threshold;When the face-image
When area ratio is less than the preset threshold, determine that the identification target is non-living body;When the face-image area ratio is big
When being equal to the preset threshold, determine that the identification target is living body.
7. the decision-making system of vivo identification according to claim 6, which is characterized in that
The transmission unit is also used to send broadcasting video instructions;
The receiving unit is also used to receive the EEG signals of the identification target according to the broadcasting video instructions feedback;
The judging unit is also used in the EEG signals for receiving the identification target according to the broadcasting video instructions feedback
Afterwards, determine that the identification target is living body.
8. the decision-making system of vivo identification according to claim 6, which is characterized in that
The transmission unit is also used to determine institute when the face-image area ratio is more than or equal to the preset threshold
Stating identification target is transmission broadcasting video instructions after living body;
The receiving unit is also used to receive the EEG signals of the identification target according to the broadcasting video instructions feedback;
The judging unit is also used in the EEG signals for receiving the identification target according to the broadcasting video instructions feedback
Afterwards, determine that the identification target is living body.
9. the decision-making system of the vivo identification according to any one of claim 6 to 8, which is characterized in that the calculating is single
Member, comprising:
Recognition unit, the facial information in described image information, the facial information include first facial position, for identification
Two facial positions, third facial positions, fourth face portion position, the 5th facial positions;
Acquiring unit, for obtain the first facial position, the third facial positions, the fourth face portion position composition
The area of first triangle;And obtain second facial positions, the third facial positions, the 5th facial positions group
At the second triangle area;
The computing unit, specifically for calculating the ratio of the area of first triangle and the area of second triangle
Value, as the face-image area ratio.
10. the decision-making system of vivo identification according to claim 9, which is characterized in that the third facial positions are nose
Position of cusp;
When commander's action command is to shake the head and keep to the left, the first facial position is right position of eye point, described the
Two facial positions are left position of eye point, the fourth face position is set to right corners of the mouth position, the 5th facial positions are the left corners of the mouth
Position;
When commander's action command is to shake the head and keep to the right, the first facial position is the left position of eye point, institute
It states the second facial positions and is set to left corners of the mouth position, the 5th facial positions for the right position of eye point, the fourth face position
For right corners of the mouth position.
11. a kind of computer installation, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 5 when executing the computer program
Any one of described in vivo identification determination method the step of.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of determination method of the vivo identification as described in any one of claims 1 to 5 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711102090.5A CN109784124A (en) | 2017-11-10 | 2017-11-10 | A kind of determination method of vivo identification, decision-making system and computer installation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711102090.5A CN109784124A (en) | 2017-11-10 | 2017-11-10 | A kind of determination method of vivo identification, decision-making system and computer installation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109784124A true CN109784124A (en) | 2019-05-21 |
Family
ID=66484267
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711102090.5A Pending CN109784124A (en) | 2017-11-10 | 2017-11-10 | A kind of determination method of vivo identification, decision-making system and computer installation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109784124A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112464192A (en) * | 2020-10-26 | 2021-03-09 | 国网安徽省电力有限公司信息通信分公司 | Power grid data asset management system based on big data |
CN112839173A (en) * | 2020-12-31 | 2021-05-25 | 深圳瞬玩科技有限公司 | Shooting subject type identification method and system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1471334A (en) * | 2002-06-19 | 2004-01-28 | ��ʽ����Ntt����Ħ | Mobile terminal capable of detecting living-body signal |
CN101419499A (en) * | 2008-11-14 | 2009-04-29 | 东南大学 | Multimedia human-computer interaction method based on cam and mike |
CN102999164A (en) * | 2012-11-30 | 2013-03-27 | 广东欧珀移动通信有限公司 | E-book page turning control method and intelligent terminal |
CN103036680A (en) * | 2012-12-10 | 2013-04-10 | 中国科学院计算机网络信息中心 | Realm name certification system and method based on biological feature recognition |
CN103279253A (en) * | 2013-05-23 | 2013-09-04 | 广东欧珀移动通信有限公司 | Method and terminal device for theme setting |
CN105787420A (en) * | 2014-12-24 | 2016-07-20 | 北京三星通信技术研究有限公司 | Method and device for biometric authentication, and biometric authentication system |
CN105989264A (en) * | 2015-02-02 | 2016-10-05 | 北京中科奥森数据科技有限公司 | Bioassay method and bioassay system for biological characteristics |
CN106101136A (en) * | 2016-07-22 | 2016-11-09 | 飞天诚信科技股份有限公司 | The authentication method of a kind of biological characteristic contrast and system |
-
2017
- 2017-11-10 CN CN201711102090.5A patent/CN109784124A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1471334A (en) * | 2002-06-19 | 2004-01-28 | ��ʽ����Ntt����Ħ | Mobile terminal capable of detecting living-body signal |
CN101419499A (en) * | 2008-11-14 | 2009-04-29 | 东南大学 | Multimedia human-computer interaction method based on cam and mike |
CN102999164A (en) * | 2012-11-30 | 2013-03-27 | 广东欧珀移动通信有限公司 | E-book page turning control method and intelligent terminal |
CN103036680A (en) * | 2012-12-10 | 2013-04-10 | 中国科学院计算机网络信息中心 | Realm name certification system and method based on biological feature recognition |
CN103279253A (en) * | 2013-05-23 | 2013-09-04 | 广东欧珀移动通信有限公司 | Method and terminal device for theme setting |
CN105787420A (en) * | 2014-12-24 | 2016-07-20 | 北京三星通信技术研究有限公司 | Method and device for biometric authentication, and biometric authentication system |
CN105989264A (en) * | 2015-02-02 | 2016-10-05 | 北京中科奥森数据科技有限公司 | Bioassay method and bioassay system for biological characteristics |
CN106101136A (en) * | 2016-07-22 | 2016-11-09 | 飞天诚信科技股份有限公司 | The authentication method of a kind of biological characteristic contrast and system |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112464192A (en) * | 2020-10-26 | 2021-03-09 | 国网安徽省电力有限公司信息通信分公司 | Power grid data asset management system based on big data |
CN112839173A (en) * | 2020-12-31 | 2021-05-25 | 深圳瞬玩科技有限公司 | Shooting subject type identification method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107609383B (en) | 3D face identity authentication method and device | |
Fischer et al. | Rt-gene: Real-time eye gaze estimation in natural environments | |
CN107748869B (en) | 3D face identity authentication method and device | |
CN107633165B (en) | 3D face identity authentication method and device | |
CN111652827B (en) | Front face synthesis method and system based on generation countermeasure network | |
CN110945522B (en) | Learning state judging method and device and intelligent robot | |
CN110287790B (en) | Learning state hybrid analysis method oriented to static multi-user scene | |
CN102058983B (en) | Intelligent toy based on video analysis | |
CN106327482B (en) | A kind of method for reconstructing and device of the facial expression based on big data | |
CN107122744A (en) | A kind of In vivo detection system and method based on recognition of face | |
CN107886032A (en) | Terminal device, smart mobile phone, authentication method and system based on face recognition | |
CN106372629A (en) | Living body detection method and device | |
CN111710036A (en) | Method, device and equipment for constructing three-dimensional face model and storage medium | |
AU2014205858A1 (en) | Apparatus and method for sensing ball in motion | |
CN110675475A (en) | Face model generation method, device, equipment and storage medium | |
CN109784124A (en) | A kind of determination method of vivo identification, decision-making system and computer installation | |
CN107085709A (en) | A kind of Confidence determination methods based on video information, apparatus and system | |
CN109773807B (en) | Motion control method and robot | |
CN105138967A (en) | Living body detection method and apparatus based on active state of human eye region | |
WO2023279557A1 (en) | Fake video inspection method and system based on blink synchronization and binocular movement detection | |
CN108062511A (en) | A kind of trans-regional multi-cam target identification association tracking and computer equipment | |
CN111860394A (en) | Gesture estimation and gesture detection-based action living body recognition method | |
CN115937928A (en) | Learning state monitoring method and system based on multi-vision feature fusion | |
CN110956068B (en) | Fatigue detection method and device based on human eye state recognition | |
CN113064490B (en) | Eye movement track-based virtual enhancement equipment identification method |
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: 20190521 |
|
RJ01 | Rejection of invention patent application after publication |