CN110110630A - A kind of method and apparatus of recognition of face - Google Patents
A kind of method and apparatus of recognition of face Download PDFInfo
- Publication number
- CN110110630A CN110110630A CN201910337524.2A CN201910337524A CN110110630A CN 110110630 A CN110110630 A CN 110110630A CN 201910337524 A CN201910337524 A CN 201910337524A CN 110110630 A CN110110630 A CN 110110630A
- Authority
- CN
- China
- Prior art keywords
- target object
- numerical value
- terminal
- concave
- face
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of methods and apparatus of recognition of face can replace and check card when checking card to solve use recognition of face progress attendance existing in the prior art, the low problem of attendance management accuracy rate.Terminal of the present invention acquires the distance between at least two default face feature points and the terminal of target object first, determine that at least one is used to indicate the detection bumps numerical value of the concave-convex degree of the face of the target object further according to the distance between at least two default face feature points of the collected target object and the terminal, if it is determined that at least one quantity for detecting target bumps numerical value in concave-convex numerical value be greater than concave-convex threshold value, then the terminal determines that the recognition of face of the target object passes through.Since the terminal has determined that the recognition of face of target object passes through, so that identification is true face, rather than a face picture when carrying out attendance and checking card, prevents from replacing checking card, improve the accuracy rate of attendance management.
Description
Technical field
The present invention relates to technical field of face recognition, in particular to a kind of method and apparatus of recognition of face.
Background technique
More and more enterprises carry out attendance management using Work attendance management system at present, for example use fingerprint recognition, ID card
Identification, recognition of face etc. carry out attendance management.
Fingerprint recognition and ID card are identified, are not easy to be identified when the discrimination of fingerprint recognition is lower, weather is cold;ID card
Identification might have for the phenomenon that checking card, and employee needed to carry ID card always.Therefore, recognition of face conduct
Most common attendance management mode.
Using recognition of face carry out attendance check card when, first Time Attendance Device acquisition employee face-image, by acquisition person
The living body characteristics of work determine that the face-image currently acquired is the face-image of living body, and living body characteristics can be the eye of employee
Feature.Collected face-image and employee information are bound, such as employee's card number of employee, then by face-image with
In the database, when employee's progress attendance is checked card, Time Attendance Device acquires the face of employee again for the corresponding relationship storage of employee information
Portion's image and living body characteristics determine the corresponding employee information of collected face-image, check card and pass through according to corresponding relationship, and
Record the information of checking card of the employee.
Whether pass through due to determining that employee checks card using face-image and living body characteristics in the prior art, if employee A makes
Employee B is replaced to check card with the face-image of the employee B of removal eye locations, Time Attendance Device can identify the eye of employee A
Living body characteristics identify the face-image of employee B, then may be implemented to replace checking card.
In conclusion in the prior art, when being checked card using recognition of face progress attendance, can replace and check card, attendance management
Accuracy rate is low.
Summary of the invention
The present invention provides a kind of method and apparatus of recognition of face, knows to solve use face existing in the prior art
When other technology progress attendance is checked card, it can replace and check card, the low problem of attendance management accuracy rate.
In a first aspect, the embodiment of the present invention provides a kind of method of recognition of face, this method comprises:
The distance between at least two default face feature points of terminal acquisition target object and the terminal;
The terminal according at least two default face feature points of the collected target object and the terminal it
Between distance determine the detection bumps numerical value of at least one concave-convex degree of face for indicating the target object;
If it is determined that at least one described quantity for detecting target bumps numerical value in concave-convex numerical value be greater than concave-convex threshold value, then institute
It states terminal and determines that the recognition of face of the target object passes through, wherein the target bumps numerical value is according to the concave-convex number of the detection
Value with it is corresponding at least one default value comparison result and compared with threshold value determine.
The above method, terminal acquire first between at least two default face feature points of target object and the terminal away from
From determining at least one at a distance from the terminal further according at least two default face feature points of the collected target object
For indicating the detection bumps numerical value of the concave-convex degree of face of the target object, if it is determined that at least one concave-convex numerical value in mesh
The quantity for marking concave-convex numerical value is greater than concave-convex threshold value, then the terminal determines that the recognition of face of the target object passes through.Due to the terminal
It has been determined that the recognition of face of target object passes through, so that identification is true face when carrying out attendance and checking card, rather than one
Picture prevents from replacing checking card, improves the accuracy rate of attendance management.
In one possible implementation, the terminal is default according at least two of the collected target object
The distance between facial characteristics and the terminal determine that at least one is used to indicate the concave-convex degree of the face of the target object
Detect concave-convex numerical value, comprising:
The distance between face feature point and the terminal are preset for any two of the collected target object,
Using the absolute value of the difference of two distances as the concave-convex numerical value of the detection.
The above method, gives a kind of determining method for detecting concave-convex numerical value, and terminal is by the collected target object
The absolute value conduct of the difference of any two distance in the distance between at least two default face feature points and the terminal
The detection bumps numerical value, it is determined that after the concave-convex numerical value of at least one described detection, concave-convex numerical value of at least one described detection from this
Middle determining target bumps numerical value.
In one possible implementation, the terminal determines the target bumps numerical value in the following manner:
The terminal is by the concave-convex numerical value of the detection at least one present count corresponding with the detection bumps numerical value respectively
Value is compared, and obtains at least one ratio;
If there is at least one ratio greater than the relatively threshold value in obtained ratio, the concave-convex numerical value is determined as
The target bumps numerical value.
The above method, gives a kind of mode of determining target bumps numerical value, terminal will test concave-convex numerical value respectively with this
It detects at least one corresponding default value of concave-convex numerical value to be compared, at least one ratio is obtained, if in obtained ratio
There is at least one ratio for being greater than and comparing threshold value, then the detection bumps numerical value is determined as target bumps numerical value, it is determined that target
After concave-convex numerical value, determine whether the recognition of face of target object passes through according to the quantity of target bumps numerical value.
In one possible implementation, this method further include:
If it is determined that the concave-convex numerical value of detection in the quantity of target bumps numerical value be not more than concave-convex threshold value, then the terminal determines
The recognition of face of the target object fails.
The above method, if it is determined that the concave-convex numerical value of detection in the quantity of target bumps numerical value be not more than concave-convex threshold value, then
The terminal determine the target object recognition of face failure, if the recognition of face of the target object fails, it is subsequent will not be right
Target object is verified, to save the verification time, improves verifying accuracy rate.
In one possible implementation, the terminal determines that the recognition of face of the target object of acquisition passes through
Afterwards, further includes:
The terminal acquires the face feature information of the target object;
The terminal judges to believe in preset face feature information set with the presence or absence of the facial characteristics of the target object
Breath, if so, determining that the target object is verified.
The above method, it is determined that after the recognition of face of target object passes through, terminal acquires the facial characteristics of the target object
Information, then judge the face feature information that whether there is the target object in preset face feature information set, and if it exists, then
It determines that the target object is verified, due to first determining that the recognition of face of target object passes through, then target object is verified
Pass through, to prevent from replacing the phenomenon that checking card, improves the accuracy of attendance management.
In one possible implementation, at least two default face feature points of terminal acquisition target object with
Before the distance between described terminal, further includes:
The terminal determines that the target object is living object;
The terminal determines that the target object is living object according to following manner:
The terminal determines that the pupil position for collecting the target object within a preset time changes and/or described
The pupil pitch-row of target object changes.
The above method, the terminal is at a distance from least two face feature points for acquiring target object are between the terminal
Before, judge whether the target object is living object, if the target object is living object, then judge the target object
Whether recognition of face passes through, so as to improve verification efficiency.
Second aspect, the embodiment of the present invention provide a kind of equipment of recognition of face, which includes: that at least one processing is single
Member and at least one storage unit, wherein the storage unit is stored with program code, when said program code is by the processing
When unit executes, so that the processing unit executes following process:
The distance between at least two default face feature points of acquisition target object and the terminal;
According to the distance between at least two default face feature points of the collected target object and described terminal
Determine that at least one is used to indicate the detection bumps numerical value of the concave-convex degree of the face of the target object;
If it is determined that at least one described quantity for detecting target bumps numerical value in concave-convex numerical value be greater than concave-convex threshold value, then really
The recognition of face of the fixed target object passes through, wherein the target bumps numerical value be according to the detection bumps numerical value with it is corresponding
The default value of at least one comparison result and compare threshold value determine.
In one possible implementation, the processing unit is specifically used for:
The distance between face feature point and the terminal are preset for any two of the collected target object,
Using the absolute value of the difference of two distances as the concave-convex numerical value of the detection.
In one possible implementation, target bumps numerical value is determined in the following manner:
By the concave-convex numerical value of the detection, at least one default value corresponding with the concave-convex numerical value of the detection compares respectively
Compared with obtaining at least one ratio;
If there is at least one ratio greater than the relatively threshold value in obtained ratio, the concave-convex numerical value is determined as
The target bumps numerical value.
In one possible implementation, the processing unit is also used to:
If it is determined that concave-convex numerical value in the quantity of target bumps numerical value be not more than concave-convex threshold value, it is determined that the target object
Recognition of face failure.
In one possible implementation, the processing unit is also used to:
Acquire the face feature information of the target object;
Judge the face feature information that whether there is the target object in preset face feature information set, if so,
Then determine that the target object is verified.
In one possible implementation, the processing unit is also used to:
Determine that the target object is living object;
The determining pupil position for collecting the target object within a preset time changes and/or the target object
Pupil pitch-row change.
The third aspect, the embodiment of the present invention also provide a kind of equipment of recognition of face, which includes:
Acquisition module: at least two default face feature points for acquiring target object and between the terminal away from
From;
Numerical value determining module: for according at least two default face feature points of the collected target object and institute
It states the distance between terminal and determines that at least one is used to indicate the detection bumps numerical value of the concave-convex degree of the face of the target object;
Object determining module: if for target bumps numerical value at least one described concave-convex numerical value of detection of the determination
Quantity is greater than concave-convex threshold value, it is determined that the recognition of face of the target object passes through, wherein the target bumps numerical value is basis
It is described detect concave-convex numerical value with it is corresponding at least one default value comparison result and compared with threshold value determination.
In one possible implementation, the numerical value determining module is specifically used for:
The distance between face feature point and the terminal are preset for any two of the collected target object,
Using the absolute value of the difference of two distances as the concave-convex numerical value of the detection.
In one possible implementation, the target bumps numerical value is determined in the following manner:
By the concave-convex numerical value of the detection, at least one default value corresponding with the concave-convex numerical value of the detection compares respectively
Compared with obtaining at least one ratio;
If there is at least one ratio greater than the relatively threshold value in obtained ratio, the concave-convex numerical value is determined as
The target bumps numerical value.
In one possible implementation, the object determining module is also used to:
If it is determined that concave-convex numerical value in the quantity of target bumps numerical value be not more than concave-convex threshold value, it is determined that the target object
Recognition of face failure.
In one possible implementation, the object determining module is also used to:
Acquire the face feature information of the target object;
Judge the face feature information that whether there is the target object in preset face feature information set, if so,
Then determine that the target object is verified.
In one possible implementation, the acquisition module is also used to:
Determine that the target object is living object;
The determining pupil position for collecting the target object within a preset time changes and/or the target object
Pupil pitch-row change.
Fourth aspect, the embodiment of the present invention also provide a kind of computer storage medium, are stored thereon with computer program, should
The step of first aspect the method is realized when computer program is executed by processor.
In addition, second aspect technical effect brought by any implementation into fourth aspect can be found in first aspect
Technical effect brought by middle difference implementation, details are not described herein again.
The aspects of the invention or other aspects can more straightforwards in the following description.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a kind of method flow schematic diagram of recognition of face provided in an embodiment of the present invention;
Fig. 2 be target object provided in an embodiment of the present invention two default face feature points and terminal between it is vertical away from
From schematic diagram;
Fig. 3 is a kind of two default face feature points of target object provided in an embodiment of the present invention and a certain spy of terminal
The distance between fixed point schematic diagram;
Fig. 4 be another target object provided in an embodiment of the present invention two default face feature points and terminal it is a certain
The distance between specified point schematic diagram;
Fig. 5 is a kind of complete method flow diagram of recognition of face provided in an embodiment of the present invention;
Fig. 6 is the structural schematic diagram of the equipment of the first recognition of face provided in an embodiment of the present invention;
Fig. 7 is the structural schematic diagram of the equipment of second of recognition of face provided in an embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that the described embodiments are only some of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
All other embodiment, shall fall within the protection scope of the present invention.
When carrying out attendance management using face recognition technology at present, the personnel that check card first stand before attendance recorder, on attendance recorder
Camera acquisition check card the living body characteristics of personnel, such as eye living body characteristics, after attendance recorder recognizes living body characteristics, determination is adopted
The personnel that check card integrated then acquire the facial picture for the personnel that check card, are compared with the facial picture stored in database as living body
It is right, if the facial picture stored in database includes the facial picture of the collected personnel that check card of attendance recorder, success of checking card.
Due to attendance recorder first according to living body characteristics determine check card personnel be living body after, check card personnel's further according to collected
Facial picture recognition is checked card personnel, is possible to will appear generation the phenomenon that checking card in this way, for example employee A holds removal eye locations
The photo of employee B, exposes the eyes of employee A at the eye locations of the photo of the employee B of removal eye locations, and attendance recorder can lead to
The eyes for crossing identification employee A determine that the personnel that check card are living body, are verified further according to the mug shot of employee B, i.e., in fact
Show employee A to check card for employee B progress attendance.
If before the facial picture that attendance recorder stores in comparing the facial picture and attendance recorder for checking card personnel, determination is adopted
The accurate of attendance management then can be improved in the facial not instead of picture of the personnel that check card collected, a true face
Rate.The face for determining the personnel that check card is a true face, the face feature point for the personnel that can be checked card by acquisition and attendance
The distance between machine, such as the distance between nose and attendance recorder, the distance between cheekbone and attendance recorder, then further according to this two
A distance is determining for indicating the detection bumps numerical value of the facial concave-convex degree of the target object, further according to the concave-convex numerical value of detection and is somebody's turn to do
It detects the comparison result of at least one corresponding default value of concave-convex numerical value and compares threshold value and determined from the concave-convex numerical value of detection
Target bumps numerical value, if the quantity of target bumps numerical value is greater than concave-convex threshold value, terminal determines that the face of the target object is known
Do not pass through, that is, the face of the collected target object of terminal is true face, is not a picture.
The application scenarios of description of the embodiment of the present invention are the technical solutions in order to more clearly illustrate the embodiment of the present invention,
The restriction for technical solution provided in an embodiment of the present invention is not constituted, those of ordinary skill in the art are it is found that with newly answering
With the appearance of scene, technical solution provided in an embodiment of the present invention is equally applicable for similar technical problem.
For above-mentioned application scenarios, the embodiment of the present invention provides a kind of method of recognition of face, as shown in Figure 1, this method
Specifically comprise the following steps:
The distance between S100, at least two default face feature points of terminal acquisition target object and described terminal;
At least two default face feature points and the end of S101, the terminal according to the collected target object
The distance between end determines that at least one is used to indicate the detection bumps numerical value of the concave-convex degree of the face of the target object;
S102, if it is determined that at least one described quantity for detecting target bumps numerical value in concave-convex numerical value be greater than concave-convex threshold
Value, then the terminal determines that the recognition of face of the target object passes through, wherein the target bumps numerical value is according to the inspection
Survey concave-convex numerical value and the comparison result of at least one corresponding default value and compared with threshold value determination.
In the embodiment of the present invention terminal acquire first target object at least two default face feature points and the terminal it
Between distance, it is true further according to the distance between at least two default face feature points of the collected target object and the terminal
It is fixed at least one be used to indicate detection bumps numerical value of the concave-convex degree of the face of the target object, if it is determined that detection bumps number
The quantity of target bumps numerical value is greater than concave-convex threshold value in value, then the terminal determines that the recognition of face of the target object passes through.Due to
The terminal has determined that the recognition of face of target object passes through, so that identification is true face when carrying out attendance and checking card, without
It is a picture, prevents from replacing checking card, improve the accuracy rate of attendance management.
Terminal in the embodiment of the present invention, can be Time Attendance Device, other for being also possible to have attendance management function are set
It is standby, such as mobile phone, tablet computer etc..
Target object in the embodiment of the present invention is behaved.
Terminal acquires at least two default face feature points and the distance between the terminal of target object, presetting here
Face feature point can be certain point on the nose of the face of target object, the certain point at cheekbone, the certain point on forehead,
These face feature points can be pre-set.
Terminal acquire target object preset the distance between face feature point and the terminal when, can be face feature point and
Vertical range between the terminal is also possible to the distance between a certain specified point of face feature point Yu the terminal.
For example, as shown in Fig. 2, the vertical range between the two default face feature points and terminal of target object is illustrated
Figure.From figure 2 it can be seen that distance d1 is the certain point at the nose of target object and the vertical range between terminal, distance
D2 is the certain point at the chin of target object and the vertical range between terminal.
In actual implementation, the height of people is different, and for ease of use, terminal can acquire default face feature point and end
The distance between a certain specified point at end, such as the center position of terminal.
For example, as shown in figure 3, for a kind of target object two default face feature points and terminal a certain specified point it
Between distance.From figure 3, it can be seen that distance d1 be target object nose at certain point and terminal center point it
Between distance, distance d2 is the certain point and the distance between the center point of terminal at the chin of target object.
For another example, as shown in figure 4, for another target object two default face feature points and terminal it is a certain specific
The distance between point.From fig. 4, it can be seen that the head of target object is higher than the location of terminal, target object needs are bowed
Verified, distance d1 be target object bow between certain point when verifying at nose and the center point of terminal away from
It is that target object is bowed the distance between the center point of certain point and terminal when verifying at chin from, distance d2.
In terminal according between at least two default face feature points of the collected target object and the terminal
When distance determines that at least one is used to indicate the detection bumps numerical value of the concave-convex degree of the face of the target object, terminal can be directed to
Any two of collected target object preset the distance between face feature point and the terminal, by the difference of two distances
Absolute value as the detection bumps numerical value.
For example, terminal acquires 3 distances, i.e., the distance between certain point and terminal are at the nose of target object
40cm, the distance between certain point and terminal 38cm at the cheekbone of target object, certain point and terminal at the forehead of target object
The distance between be 37cm, then at the distance between certain point and terminal at nose and cheekbone between certain point and terminal
Distance, for terminal using the absolute value of the difference of two distances as concave-convex numerical value is detected, i.e., first detects bumps numerical value as 2cm;
The distance between certain point and terminal at the distance between certain point and terminal at cheekbone and forehead, then terminal determines second
Detecting concave-convex numerical value is 1cm;At the distance between certain point and terminal at nose and forehead between certain point and terminal
Distance, then it is 3cm that terminal, which determines that third detects concave-convex numerical value,.
What needs to be explained here is that when calculating concave-convex numerical value, not necessarily by the difference of all any two distances
Absolute value, can be determine according to actual needs all as concave-convex numerical value is detected.
For example, terminal acquires 3 distances, the distance between certain point and terminal at the nose of target object, target pair
The distance between certain point and terminal at the cheekbone of elephant, the distance between certain point and terminal at the forehead of target object, according to
Actual needs may only need at nose the distance between certain point and terminal at the distance between certain point and terminal and cheekbone
The distance between certain point and terminal at the distance between certain point and terminal and forehead at the concave-convex numerical value of corresponding detection, nose
The concave-convex numerical value of corresponding detection, the two detect concave-convex numerical value, so not needing all any two apart from corresponding inspection
Concave-convex numerical value is surveyed all to calculate.
After the concave-convex numerical value of at least one described detection has been determined, target is determined from the concave-convex numerical value of detection described at least one
Concave-convex numerical value, the target bumps numerical value be according to detect concave-convex numerical value and the comparison result of at least one corresponding default value with
And compare what threshold value determined.
In an implementation, the concave-convex numerical value of each detection can correspond at least one default value, for example, at the nose of target object
Certain point detection corresponding with the distance between terminal is concave-convex at the cheekbone of the distance between certain point and terminal and target object
Numerical value can store at least one corresponding default value of detection bumps numerical value, such as basis in the terminal or in the server
Different ethnic groups, in terminal or server store 4 noses at certain point between terminal at a distance from and target object cheekbone
Certain point default value corresponding with the distance between terminal at bone, that is, the corresponding default value of detection bumps numerical value.
Determine that default value is merely illustrative above according to different ethnic groups, in addition to determining default value according to ethnic group
Outside, for some special face feature points, other default values can also be set, such as around eyes, some people may
It can wear glasses, so some face feature points around eyes, can be set some special default values.
Specifically, determine target bumps numerical value when, terminal first by the detection bumps numerical value respectively with the detection bumps number
It is worth at least one corresponding default value to be compared, obtains at least one ratio, then determines whether have in obtained ratio
Greater than at least one ratio for comparing threshold value, if so, then the detection bumps numerical value is determined as target bumps numerical value by the terminal.
For example, corresponding 4 default values of the concave-convex numerical value of a detection, detecting concave-convex numerical value is 3,4 default value difference
Be 4.5,4,3.5,3.2,3 be compared respectively with 4 default values, obtained ratio be 66.7%, 75%, 85.7%,
93.8%, if comparing threshold value is 90%, there are one greater than the detection bumps numerical value for comparing threshold value, then target is used as by 3
Concave-convex numerical value;If comparing threshold value is 95%, there is no the detection bumps numerical value for comparing threshold value is greater than, i.e., target can not be determined
Concave-convex numerical value.
After target bumps numerical value has been determined, judge whether the quantity of target bumps numerical value is greater than concave-convex threshold value, if it is greater than
Concave-convex threshold value, then terminal determines that the recognition of face of the target object passes through, if the quantity of target bumps numerical value is no more than bumps
Threshold value, then terminal determines the recognition of face failure that the target object is.
For example, concave-convex threshold value is 0, if target bumps numerical value is 1, it is determined that the recognition of face of target object passes through, such as
Fruit target bumps numerical value is 0, it is determined that the recognition of face of target object fails.
For another example, the quantity of the concave-convex numerical value of the detection determined is 5, and concave-convex threshold value is 4, from the concave-convex numerical value of 5 detections
Determining target bumps numerical value is 4, then terminal determines the recognition of face failure of the target object.
It should be noted that target object is different, concave-convex threshold value is possible to different, for example, being used to identify the concave-convex threshold of people
Value and for identifying that the concave-convex threshold value of animal may be different, concave-convex threshold value needs determine according to actual needs.
The terminal of that embodiment of the invention acquires the distance between face feature point and the terminal of at least two target objects,
Then it determines and examines further according to the distance between at least two default face feature points of the collected target object and the terminal
Concave-convex numerical value is surveyed, which is used to indicate that the concave-convex degree of the face of the target object, finally recessed according to detecting
The quantity of target bumps numerical value determines that the recognition of face of the target object passes through in convex numerical value, due to detect concave-convex numerical value be for
The concave-convex degree of the face of the target object is indicated, if the recognition of face of target object fails, such as picture, without bumps journey
Degree, therefore can determine whether the recognition of face of the target object passes through.
After judging whether the recognition of face of target object passes through, if the recognition of face of the target object passes through, terminal
The face feature information for acquiring the target object judges in preset face feature information set with the presence or absence of the target object
Face feature information, if it is present determine the target object be verified.Due to first determining that the face of the target object is known
Do not pass through, then acquire the face feature information of target object, judge whether the target object is verified, so as to prevent from making
The verifying that target object is carried out with face picture improves the accuracy rate of verifying.
If it is determined that the recognition of face of the target object fails, then terminal will not acquire the facial characteristics letter of target object again
Breath, directly determines target object authentication failed, to can be improved the accuracy rate of verifying while saving resource.
When verifying to target object, the terminal of that embodiment of the invention can also acquire target object in the terminal
Before the distance between at least two default face feature points and the terminal, determine that the target object is living object.?
Exactly before whether the recognition of face for judging the target object passes through, first judge whether the target object is living object, such as
Fruit determines that the target object is living object, then judges whether the recognition of face of the target object passes through, if it is determined that the target
Object is non-living body target, then authentication failed, to improve verification efficiency.
Specifically, determining that the target object is living object, can determine in the following manner: the terminal is determined pre-
If the pupil position for collecting the target object in the time changes and/or the pupil pitch-row of the target object becomes
Change.
That is, if the pupil position of target object changes and/or the pupil of target object within a preset time
Hole pitch-row changes, and terminal determines that the target object is living object.
If determining that the pupil position of target object and the pupil pitch-row of the target object all do not occur within a preset time
Variation, then terminal determines that the target object is non-living body target.
Determine that the target object is after non-living body target, terminal stopping detection, terminal can be in display interface display verifying
The prompt information of failure, can also pass through voice prompting authentication failed.
As shown in figure 5, being a kind of flow diagram of the complete method of recognition of face provided in an embodiment of the present invention.
S500, terminal acquire the pupil position of target object and pupil pitch-row within a preset time;
S501, whether the pupil position of collected target object and pupil pitch-row occur within a preset time for terminal judgement
Otherwise variation executes S513 if so, executing S511;
The distance between S502, at least two default face feature points of terminal acquisition target object and the terminal;
S503, it is preset between face feature point and the terminal for any two of the collected target object
Distance, terminal is using the absolute value of the difference of two distances as concave-convex numerical value.
The bumps numerical value is compared by S504, terminal respectively at least one corresponding default value of the bumps numerical value,
Obtain at least one ratio;
Whether there is the ratio for being greater than and comparing threshold value in the ratio that S505, judgement obtain, if so, executing S506, otherwise holds
Row step S512;
S506, using the bumps numerical value as target bumps numerical value;
S507, judge whether the quantity of target bumps numerical value is greater than concave-convex threshold value, if so, executing S508, otherwise execute
Step S512;
S508, determine that the recognition of face of target object passes through;
The face feature information of S509, terminal acquisition target object;
S510, judge the face feature information that whether there is the target object in default face feature information set;If so,
S511 is then executed, S513 is otherwise executed;
S511, target object are verified;
S512, the recognition of face failure for determining target object;
S513, target object authentication failed.
Based on the same inventive concept, a kind of equipment of recognition of face is additionally provided in the embodiment of the present invention, due to the equipment
Corresponding is the corresponding equipment of method of recognition of face of the embodiment of the present invention, and the principle and this method that the equipment solves the problems, such as
It is similar, therefore the implementation of the equipment may refer to the implementation of method, overlaps will not be repeated.
As shown in fig. 6, the structural schematic diagram of the equipment for the first recognition of face provided in an embodiment of the present invention, the equipment
It include: at least one processing unit 600 and at least one storage unit 601, wherein the storage unit 601 is stored with program
Code, when said program code is executed by the processing unit, so that the processing unit holds the following process of 600 execution:
The distance between at least two default face feature points of acquisition target object and the terminal;
According to the distance between at least two default face feature points of the collected target object and described terminal
Determine that at least one is used to indicate the detection bumps numerical value of the concave-convex degree of the face of the target object;
If it is determined that at least one described quantity for detecting target bumps numerical value in concave-convex numerical value be greater than concave-convex threshold value, then really
The recognition of face of the fixed target object passes through, wherein the target bumps numerical value be according to the detection bumps numerical value with it is corresponding
At least one default value comparison result and compare threshold value determine.
Optionally, the processing unit 600 is specifically used for:
The distance between face feature point and the terminal are preset for any two of the collected target object,
Using the absolute value of the difference of two distances as the concave-convex numerical value of the detection.
Optionally, target bumps numerical value is determined in the following manner:
By the concave-convex numerical value of the detection, at least one default value corresponding with the concave-convex numerical value of the detection compares respectively
Compared with obtaining at least one ratio;
It is if there is at least one ratio greater than the relatively threshold value in obtained ratio, the concave-convex numerical value of the detection is true
It is set to the target bumps numerical value.
Optionally, the processing unit 600 is also used to:
If it is determined that concave-convex numerical value in the quantity of target bumps numerical value be not more than concave-convex threshold value, it is determined that the target object
Recognition of face failure.
Optionally, the processing unit 600 is also used to:
Acquire the face feature information of the target object;
Judge the face feature information that whether there is the target object in preset face feature information set, if so,
Then determine that the target object is verified.
Optionally, the processing unit 600 is also used to:
Determine that the target object is living object;
The determining pupil position for collecting the target object within a preset time changes and/or the target object
Pupil pitch-row change.Based on the same inventive concept, a kind of equipment of recognition of face is additionally provided in the embodiment of the present invention,
It is the corresponding equipment of method of recognition of face of the embodiment of the present invention since the equipment is corresponding, and the original that the equipment solves the problems, such as
Reason is similar to this method, therefore the implementation of the equipment may refer to the implementation of method, and overlaps will not be repeated.
As shown in fig. 7, the structural schematic diagram of the equipment for second of recognition of face provided in an embodiment of the present invention, the equipment
It include: acquisition module 700, numerical value determining module 701, object determining module 702.
Acquisition module 700: at least two default face feature points for acquiring target object and between the terminal
Distance;
Numerical value determining module 701: for at least two default face feature points according to the collected target object
The distance between described terminal determines that at least one is used to indicate that the detection of the concave-convex degree of the face of the target object to be concave-convex
Numerical value;
Object determining module 702: for if it is determined that at least one described detect target bumps numerical value in concave-convex numerical value
Quantity is greater than concave-convex threshold value, it is determined that the recognition of face of the target object passes through, wherein the target bumps numerical value is basis
It is described detect concave-convex numerical value with it is corresponding at least one default value comparison result and compared with threshold value determination.
Optionally, the numerical value determining module 701 is specifically used for:
The distance between face feature point and the terminal are preset for any two of the collected target object,
Using the absolute value of the difference of two distances as the concave-convex numerical value of the detection.
Optionally, target bumps numerical value is determined in the following manner:
By the concave-convex numerical value of the detection, at least one default value corresponding with the concave-convex numerical value of the detection compares respectively
Compared with obtaining at least one ratio;
If there is at least one ratio greater than the relatively threshold value in obtained ratio, the concave-convex numerical value is determined as
The target bumps numerical value.
Optionally, the object determining module 702 is also used to:
If it is determined that concave-convex numerical value in the quantity of target bumps numerical value be not more than concave-convex threshold value, it is determined that the target object
For recognition of face failure.
Optionally, the object determining module 702 is also used to:
Acquire the face feature information of the target object;
Judge the face feature information that whether there is the target object in preset face feature information set, if so,
Then determine that the target object is verified.
Optionally, the acquisition module 700 is also used to:
Determine that the target object is living object;
The determining pupil position for collecting the target object within a preset time changes and/or the target object
Pupil pitch-row change.
The embodiment of the present invention also provides a kind of readable storage medium storing program for executing of recognition of face, including program code, works as described program
When code is run on the computing device, said program code is used to make the step for calculating equipment executor and knowing method for distinguishing on the face
Suddenly.
Above by reference to showing according to the method, apparatus (system) of the embodiment of the present application and/or the frame of computer program product
Figure and/or flow chart describe the application.It should be understood that can realize that block diagram and or flow chart is shown by computer program instructions
The combination of the block of a block and block diagram and or flow chart diagram for figure.These computer program instructions can be supplied to logical
With computer, the processor of special purpose computer and/or other programmable data processing units, to generate machine, so that via meter
The instruction that calculation machine processor and/or other programmable data processing units execute creates for realizing block diagram and or flow chart block
In specified function action method.
Correspondingly, the application can also be implemented with hardware and/or software (including firmware, resident software, microcode etc.).More
Further, the application can take computer usable or the shape of the computer program product on computer readable storage medium
Formula has the computer realized in the medium usable or computer readable program code, to be made by instruction execution system
It is used with or in conjunction with instruction execution system.In the present context, computer can be used or computer-readable medium can be with
It is arbitrary medium, may include, stores, communicates, transmits or transmit program, is made by instruction execution system, device or equipment
With, or instruction execution system, device or equipment is combined to use.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (12)
1. a kind of method of recognition of face, which is characterized in that this method comprises:
The distance between at least two default face feature points of terminal acquisition target object and the terminal;
The terminal is according between at least two default face feature points of the collected target object and the terminal
Distance determines that at least one is used to indicate the detection bumps numerical value of the concave-convex degree of the face of the target object;
If it is determined that at least one described quantity for detecting target bumps numerical value in concave-convex numerical value be greater than concave-convex threshold value, then end
End determines that the recognition of face of the target object passes through, wherein the target bumps numerical value be according to the concave-convex numerical value of the detection and
The comparison result of at least one corresponding default value and compare threshold value determine.
2. the method as described in claim 1, which is characterized in that the terminal according to the collected target object at least
The distance between two default facial characteristics and the terminal determine at least one for indicating the facial recessed of the target object
The detection bumps numerical value of convex degree, comprising:
The distance between face feature point and the terminal are preset for any two of the collected target object, it is described
Terminal is using the absolute value of the difference of two distances as the concave-convex numerical value of the detection.
3. the method as described in claim 1, which is characterized in that the terminal determines the target bumps number in the following manner
Value:
The terminal by the concave-convex numerical value of the detection respectively at least one default value corresponding with the detection bumps numerical value into
Row compares, and obtains at least one ratio;
If there is at least one ratio greater than the relatively threshold value in obtained ratio, the terminal is true by the concave-convex numerical value
It is set to the target bumps numerical value.
4. the method as described in claim 1, which is characterized in that this method further include:
If it is determined that concave-convex numerical value in the quantity of target bumps numerical value be not more than concave-convex threshold value, then the terminal determines the target
The recognition of face of object fails.
5. the method as described in Claims 1 to 4 is any, which is characterized in that the terminal determines the face of the target object
After being identified by, further includes:
The terminal acquires the face feature information of the target object;
The terminal judges the face feature information that whether there is the target object in preset face feature information set, if
It is, it is determined that the target object is verified.
6. method as claimed in claim 5, which is characterized in that at least two default faces of the terminal acquisition target object
Before the distance between characteristic point and the terminal, further includes:
The terminal determines that the target object is living object;
The terminal determines that the target object is living object according to following manner:
The determining pupil position for collecting the target object within a preset time of the terminal changes and/or the target
The pupil pitch-row of object changes.
7. a kind of equipment of recognition of face, which is characterized in that the equipment includes: at least one processing unit and at least one storage
Unit, wherein the storage unit is stored with program code, when said program code is executed by the processing unit, so that
The processing unit executes following process:
The distance between at least two default face feature points of acquisition target object and the terminal;
It is determined according to the distance between at least two default face feature points of the collected target object and described terminal
At least one is used to indicate the detection bumps numerical value of the concave-convex degree of the face of the target object;
If it is determined that at least one described quantity for detecting target bumps numerical value in concave-convex numerical value be greater than concave-convex threshold value, it is determined that institute
The recognition of face for stating target object passes through, wherein the target bumps numerical value be according to the concave-convex numerical value of the detection with it is corresponding extremely
Lack the comparison result an of default value and compares what threshold value determined.
8. equipment as claimed in claim 7, which is characterized in that the processing unit is specifically used for:
The distance between face feature point and the terminal are preset for any two of the collected target object, by two
The absolute value of the difference of a distance is as the concave-convex numerical value of the detection.
9. equipment as claimed in claim 7, which is characterized in that determine the target bumps numerical value in the following manner:
By the concave-convex numerical value of the detection, at least one default value corresponding with the concave-convex numerical value of the detection is compared respectively, is obtained
To at least one ratio;
If there is at least one ratio greater than the relatively threshold value in obtained ratio, the concave-convex numerical value is determined as described
Target bumps numerical value.
10. equipment as claimed in claim 7, which is characterized in that the processing unit is also used to:
If it is determined that concave-convex numerical value in the quantity of target bumps numerical value be not more than concave-convex threshold value, it is determined that the people of the target object
Face recognition failures.
11. the equipment as described in claim 7~10 is any, which is characterized in that the processing unit is also used to:
Acquire the face feature information of the target object;
The face feature information that whether there is the target object in preset face feature information set is judged, if so, really
The fixed target object is verified.
12. equipment as claimed in claim 11, which is characterized in that the processing unit is also used to:
Determine that the target object is living object;
The determining pupil position for collecting the target object within a preset time changes and/or the pupil of the target object
Hole pitch-row changes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910337524.2A CN110110630B (en) | 2019-04-25 | 2019-04-25 | Face recognition method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910337524.2A CN110110630B (en) | 2019-04-25 | 2019-04-25 | Face recognition method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110110630A true CN110110630A (en) | 2019-08-09 |
CN110110630B CN110110630B (en) | 2021-07-13 |
Family
ID=67486580
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910337524.2A Active CN110110630B (en) | 2019-04-25 | 2019-04-25 | Face recognition method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110110630B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105389554A (en) * | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Face-identification-based living body determination method and equipment |
CN107273875A (en) * | 2017-07-18 | 2017-10-20 | 广东欧珀移动通信有限公司 | Human face in-vivo detection method and Related product |
CN108921080A (en) * | 2018-06-27 | 2018-11-30 | 北京旷视科技有限公司 | Image-recognizing method, device and electronic equipment |
-
2019
- 2019-04-25 CN CN201910337524.2A patent/CN110110630B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105389554A (en) * | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Face-identification-based living body determination method and equipment |
CN107273875A (en) * | 2017-07-18 | 2017-10-20 | 广东欧珀移动通信有限公司 | Human face in-vivo detection method and Related product |
CN108921080A (en) * | 2018-06-27 | 2018-11-30 | 北京旷视科技有限公司 | Image-recognizing method, device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN110110630B (en) | 2021-07-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101661557B (en) | Face recognition system and face recognition method based on intelligent card | |
EP2546782B1 (en) | Liveness detection | |
WO2021036436A1 (en) | Facial recognition method and apparatus | |
RU2670798C1 (en) | Method of iris authentication of user and device therefor | |
US20180075291A1 (en) | Biometrics authentication based on a normalized image of an object | |
CN104143086A (en) | Application technology of portrait comparison to mobile terminal operating system | |
US20210224752A1 (en) | Work support system and work support method | |
CN109002786A (en) | Method for detecting human face, equipment and computer readable storage medium | |
US20220343682A1 (en) | Information processing system, method for managing object to be authenticated, and program | |
CN109766785A (en) | A kind of biopsy method and device of face | |
CN107742101A (en) | A kind of site operation personnel verification method | |
CN111724496A (en) | Attendance checking method, attendance checking device and computer readable storage medium | |
CN106778636A (en) | Auth method and device | |
JP4992517B2 (en) | Face matching device | |
CN106250890B (en) | Fingerprint identification method and device | |
US11144773B2 (en) | System for characterizing biometric station metrics with genericized biometric information | |
CN110415113A (en) | Finance data processing method, device, server and readable storage medium storing program for executing | |
CN111428594A (en) | Identity authentication method and device, electronic equipment and storage medium | |
CN112489241A (en) | Electronic patrol system capable of supervising patrol personnel | |
CN110110630A (en) | A kind of method and apparatus of recognition of face | |
CN108596127B (en) | Fingerprint identification method, identity verification method and device and identity verification machine | |
CN116580432A (en) | Online examination monitoring method, system, computing device and storage medium | |
KR20230017454A (en) | Method, Device and Computer Program For Preventing Cheating In Non-face-to-face Evaluation | |
EP3196829A1 (en) | Non-facing financial service system using user confirmation apparatus using parallel signature processing, and handwriting signature authentication technique | |
CN112069915A (en) | ATM with face recognition system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |