CN108268765A - Solve lock control method and Related product - Google Patents
Solve lock control method and Related product Download PDFInfo
- Publication number
- CN108268765A CN108268765A CN201810100940.6A CN201810100940A CN108268765A CN 108268765 A CN108268765 A CN 108268765A CN 201810100940 A CN201810100940 A CN 201810100940A CN 108268765 A CN108268765 A CN 108268765A
- Authority
- CN
- China
- Prior art keywords
- image
- facial image
- target
- organic
- angle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
- Collating Specific Patterns (AREA)
Abstract
The embodiment of the present application discloses a kind of solution lock control method and Related product, wherein method include:It treats authentication image progress recognition of face and obtains multiple first organic images in target facial image and the target facial image;The first vertical direction of the target facial image is determined according to the multiple first organic image;Determine the first angle between first vertical direction and the length direction of electronic equipment;The target facial image is rotated to obtain with reference to facial image according to first angle, second angle with reference between the second vertical direction of facial image and the length direction is less than predetermined angle threshold value;It is matched described with reference to facial image with default facial image, and be unlocked in successful match.Using the application, discrimination and the flexibility of unlock can be improved.
Description
Technical field
This application involves technical field of electronic equipment, have related generally to a kind of solution lock control method and Related product.
Background technology
With the continuous development of electronic device technology, the use of the electronic equipments such as mobile phone, computer, tablet is more and more general
And and allow to be unlocked using face identification method.In the prior art, when the facial image to be verified of image acquisition device acquisition
It is unlocked when being matched with default facial image.If however, exist in the facial image to be verified of acquisition with default facial image
Certain angular deviation, the then discrimination for leading to unlock are low.
Invention content
The embodiment of the present application provides a kind of solution lock control method and Related product, can improve discrimination and the spirit of unlock
Activity.
In a first aspect, the embodiment of the present application provides a kind of solution lock control method, including:
It treats authentication image and carries out recognition of face, obtain multiple the in target facial image and the target facial image
One organic image;
The first vertical direction of the target facial image is determined according to the multiple first organic image;
Determine the first angle between first vertical direction and the length direction of electronic equipment;
The target facial image is rotated according to first angle, is obtained with reference to facial image, the reference
The second angle between the second vertical direction and the length direction of facial image is less than predetermined angle threshold value;
It is matched described with reference to facial image with default facial image, and in successful match, be unlocked.
Second aspect, the embodiment of the present application provide a kind of electronic equipment, including processor, depositing of being connected to the processor
Reservoir and image collecting device, wherein:
Described image harvester, for acquiring image to be verified;
The memory, for storing default facial image and predetermined angle threshold value;
The processor for carrying out recognition of face to the image to be verified, obtains target facial image and the mesh
Mark multiple first organic images in facial image;The target facial image is determined according to the multiple first organic image
First vertical direction;Determine the first angle between first vertical direction and the length direction of electronic equipment;According to described
First angle rotates the target facial image, obtains with reference to facial image, described with reference to the second perpendicular of facial image
Second angle of the Nogata between the length direction is less than the predetermined angle threshold value;Facial image and institute are referred to by described
It states default facial image to be matched, and in successful match, is unlocked.
The third aspect, the embodiment of the present application provide a kind of solution lock control device, including:
Recognition unit carries out recognition of face for treating authentication image, obtains target facial image and the target face
Multiple first organic images in image;
Determination unit, for determining the first vertical side of the target facial image according to the multiple first organic image
To;Determine the first angle between first vertical direction and the length direction of electronic equipment;
Rotary unit for being rotated according to first angle to the target facial image, is obtained with reference to face
Image, second angle with reference between the second vertical direction of facial image and the length direction are less than predetermined angle threshold
Value;
Matching unit, for being matched described with reference to facial image with default facial image;
Unlocking unit, in the matching unit successful match, being unlocked.
Fourth aspect, the embodiment of the present application provide another solution lock control method, applied to including processor, with it is described
The memory of processor connection and the electronic equipment of image collecting device, wherein:
Described image harvester acquires image to be verified;
Facial image and predetermined angle threshold value are preset in the memory storage;
The processor carries out recognition of face to the image to be verified, obtains target facial image and the target face
Multiple first organic images in image;Determine the target facial image according to the multiple first organic image first is erected
Nogata to;Determine the first angle between first vertical direction and the length direction of electronic equipment;According to the described first folder
Angle rotates the target facial image, obtains with reference to facial image, second vertical direction with reference to facial image
The second angle between the length direction is less than the predetermined angle threshold value;It is preset described with reference to facial image with described
Facial image is matched, and in successful match, is unlocked.
5th aspect, the embodiment of the present application provide another electronic equipment, including processor, memory, communication interface with
And one or more programs, wherein, said one or multiple programs are stored in above-mentioned memory, and be configured by above-mentioned
Processor performs, and described program includes being used for such as the instruction of the part or all of step described in first aspect.
6th aspect, the embodiment of the present application provide a kind of computer readable storage medium, wherein, it is described computer-readable
Storage medium stores computer program, wherein, the computer program causes computer to perform such as the embodiment of the present application first party
Part or all of step described in face.
7th aspect, the embodiment of the present application provide a kind of computer program product, wherein, the computer program product
Non-transient computer readable storage medium including storing computer program, the computer program are operable to make calculating
Machine is performed such as the part or all of step described in the embodiment of the present application first aspect.The computer program product can be one
A software installation packet.
Implement the embodiment of the present application, will have the advantages that:
After employing above-mentioned solution lock control method and Related product, the target face figure in image to be verified is extracted
Picture obtains multiple first organic images in target facial image, target facial image is determined according to multiple first organic images
The first vertical direction, determine the first angle between the first vertical direction and the length direction of electronic equipment, according to first folder
Angle is rotated to obtain with reference to facial image to target facial image, will refer to facial image and the progress of default facial image
Match, if successful match, be unlocked.That is, when target facial image is there are during certain angular error, by mesh
Mark facial image carries out angle and adjusts to obtain reference man's face image, and with reference to the second vertical direction and length direction of facial image
Between the second angle be less than predetermined angle threshold value, the accuracy rate of recognition of face can be improved, angle is repeatedly carried out without user
Degree adjustment resurveys image to be verified, so as to improve the flexibility of unlock.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or it will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application, for those of ordinary skill in the art, without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Wherein:
Fig. 1 is a kind of flow diagram for solving lock control method provided by the embodiments of the present application;
Figure 1A is the structure diagram of a kind of electronic equipment provided by the embodiments of the present application;
Figure 1B is a kind of schematic diagram of a scenario of recognition of face provided by the embodiments of the present application;
Fig. 1 C are a kind of schematic diagram of a scenario for obtaining the first angle provided by the embodiments of the present application;
Fig. 1 D are a kind of schematic diagram of a scenario for obtaining the first vertical direction provided by the embodiments of the present application;
Fig. 2 is a kind of structure diagram for solving lock control device provided by the embodiments of the present application;
Fig. 3 is the structure diagram of another electronic equipment provided by the embodiments of the present application;
Fig. 4 is another flow diagram for solving lock control method provided by the embodiments of the present application;
Fig. 5 is the structure diagram of another electronic equipment provided by the embodiments of the present application.
Specific embodiment
In order to which those skilled in the art is made to more fully understand application scheme, below in conjunction in the embodiment of the present application
The technical solution in the embodiment of the present application is clearly and completely described in attached drawing, it is clear that described embodiment is only
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
All other embodiments obtained without creative efforts shall fall in the protection scope of this application.
Term " first ", " second " in the description and claims of this application and above-mentioned attached drawing etc. are for distinguishing
Different objects rather than for describing particular order.In addition, term " comprising " and " having " and their any deformations, it is intended that
It is to cover non-exclusive include.Such as process, method, system, product or the equipment for containing series of steps or unit do not have
The step of having listed or unit are defined in, but optionally further includes the step of not listing or unit or optionally also wraps
It includes for other intrinsic steps of these processes, method, product or equipment or unit.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Electronic equipment involved by the embodiment of the present application can include the various handheld devices with wireless communication function,
Mobile unit, wearable device, computing device or other processing equipments and various forms for being connected to radio modem
User equipment (user equipment, UE), mobile station (mobile station, MS), terminal device (terminal
Device) etc..For convenience of description, apparatus mentioned above is referred to as electronic equipment.The embodiment of the present application is carried out below detailed
It is thin to introduce.
The embodiment of the present application provides a kind of solution lock control method and Related product, can improve discrimination and the spirit of unlock
Activity.The embodiment of the present application is introduced below in conjunction with the accompanying drawings.
A kind of flow diagram for solving lock control method is provided referring to Fig. 1, Fig. 1 is the embodiment of the present application.Above-mentioned side
Method can be applied to the structure diagram of electronic equipment 100 as shown in Figure 1A, and above-mentioned electronic equipment 100 includes:Housing, touch-control are shown
Display screen, mainboard, battery and subplate are provided with front camera 21, processor 110, memory 120 and client on mainboard and identify mould
Block (subscriber identity module, SIM) card slot etc. is provided with oscillator, integrated sound chamber and VOOC sudden strains of a muscle and fills on subplate
Interface, above-mentioned front camera 21 form the face recognition module of the electronic equipment 100.
It should be noted that the default camera head for acquiring image to be verified is front camera, if clicking camera switching
Component can switch to rear camera, i.e., when the image authentication to be verified success of rear camera acquisition, can also be unlocked,
So as to improve the convenience of operation.In addition, figure can also be carried out by other image collecting devices being connect with electronic equipment 100
As acquisition, it is not limited thereto.
As shown in Figure 1, solution lock control method includes:
101:Treat authentication image carry out recognition of face obtain it is more in target facial image and the target facial image
A first organic image.
In this application, image to be verified is front camera, rear camera or other image collecting devices default
The image acquired in region.Above-mentioned multiple first organic images are eyebrow, the corresponding figure of at least two organs in eye, ear, nose, mouth
Picture, wherein, eyebrow image, eye pattern picture and ear image include left and right two parts, i.e., left eyebrow image and right eyebrow image, left-eye image and the right side
Eye pattern picture, left ear image and auris dextra image.
Multiple first organic images how identified to obtain in target facial image and target facial image are not limited
It is fixed, optionally, recognition of face is carried out to the target facial image and obtains multiple characteristic points;It is determined according to the multiple characteristic point
Multiple circumferences;The target facial image and the multiple first organic image are determined according to the multiple circumference.
That is, obtaining multiple characteristic points of target facial image by face recognition technology, basic principle is people
Position constraint between the textural characteristics of face and each characteristic point combines.As shown in Figure 1B, the point in figure is the spy of facial image
Sign point position, wherein the corresponding characteristic value of each characteristic point.It can obtain according to the position of above-mentioned multiple characteristic points multiple outer
Profile is enclosed, feature is fallen further according to the exterior feature of multiple circumferences and human face and determines the first organ figure in target facial image
Picture, multiple first organic images include right eyebrow image, left eyebrow image, eye image, left-eye image, auris dextra image, nose image
With face image.
The target facial image in image to be verified is obtained by face recognition technology, may filter that in image to be verified not
Relevant background image or other character images so as to be verified for target facial image, improve image authentication
Treatment effeciency and accuracy rate.It should be noted that above-mentioned target facial image should be the image just put, i.e., forehead is in chin
Top.
Optionally, the target facial image is matched with default facial image;The target facial image with
The default facial image is when it fails to match, performs and described recognition of face is carried out to the image to be verified obtain the multiple the
The step of one organic image.
In this application, for how match being not construed as limiting with default facial image to target facial image.It is optional
, in one first organic image every in the multiple first organic image and the default facial image with the organic image pair
The default organic image answered is matched to obtain multiple matching values;According to one first organ every in the multiple first organic image
The corresponding preset weights of image and the multiple matching value obtain object matching value;It is less than or equal to the in the object matching value
During one threshold value, determining the target facial image, it fails to match with the default facial image.
Wherein, the corresponding preset weights of every one first organic image are also not construed as limiting, it can be according to every one first device
Ratio between official's image and target facial image is allocated, can also be according to the corresponding characteristic point of every one first organic image
The quantity or dense degree of number are allocated, and can be allocated with the significance level of each organ and degree easy to identify
Deng.
It is appreciated that obtain every one first organic image and default people in target facial image respectively in the above-described embodiments
The matching value between organic image is corresponded in face image, object matching is obtained in conjunction with the preset weights of every one first organic image
Value can improve the accuracy for obtaining object matching value, so as to improve the accuracy of the verification result of target facial image.Described
When object matching value is less than or equal to first threshold, determine that the target facial image matches mistake with the default facial image
It loses, just performs described the step of the multiple first organic image is obtained to the image progress recognition of face to be verified;Otherwise,
It determines the target facial image and the default facial image successful match, so as to save power consumption, improves electronic equipment
Cruise duration.
102:The first vertical direction of the target facial image is determined according to the multiple first organic image.
In this application, as shown in Figure 1 C, the first vertical direction is the corresponding image of vertical average line of face.
Optionally, target organ image is chosen from the multiple first organic image and obtains multiple target organ images;
The midpoint for obtaining each target organ image in the multiple target organ image obtains multiple midpoints;To the multiple middle click-through
Row grouping obtains multigroup midpoint;It obtains the corresponding tie point of each class mid point in multigroup midpoint and obtains multiple tie points;Root
First vertical direction is determined according to the multiple tie point.
Wherein, the choosing method of target organ image is not construed as limiting, it can be by including feature in the first organic image
The number and the ratio of characteristic point sum retrievable in the organ of point are obtained, i.e., ratio are more than the first of predetermined threshold value
Organic image is as target organ image.That is, obtaining the first higher organic image of integrity degree, recognition of face can be improved
Accuracy.
The acquisition methods at midpoint are also not construed as limiting, it can be according to target organ image each in multiple target organ images
Corresponding circumference obtains its midpoint, can also choose the corresponding feature of each target organ image in multiple target organ images
The characteristic point of center is in point, it can also be according to the corresponding feature of target organ image each in multiple target organ images
Point obtains its midpoint etc..
Also be not construed as limiting for how to be grouped to multiple midpoints, can be left eyebrow image and right eyebrow image it is corresponding in
Point is one group for one group or left-eye image, eye image and the corresponding midpoint of mouth image, can also be left eyebrow image,
Left-eye image, nose image and the corresponding midpoint of image are one group etc..Wherein, at least corresponding class mid point in a midpoint, that is, exist
Two class mid points include the situation at same midpoint, such as:Left-eye image, eye image, nose image and the corresponding midpoint of mouth image
It it is one group, left eyebrow image, right eyebrow image, nose image and the corresponding midpoint of mouth image are one group, can improve the first vertical direction
Accuracy.
Multiple midpoints are determined for target organ images multiple in target facial image, and multiple midpoints are grouped, from
And the corresponding tie point of each class mid point is obtained, it determines the first vertical direction further according to multiple tie points, that is, it is perpendicular to improve first
Nogata is to the accuracy of acquisition.
For example, as shown in figure iD, multiple first organic images include right eyebrow image, left eyebrow image, eye image, a left side
Eye pattern picture, auris dextra image, nose image and face image, selection target organ image obtains from above-mentioned multiple first organic images
To right eyebrow image, eye image, auris dextra image, nose image and face image, obtain respectively in above-mentioned target organ image
Point obtains midpoint A, midpoint B, midpoint C and midpoint D, then tie point E is determined according to above-mentioned midpoint A and midpoint C, according to above-mentioned midpoint
A and midpoint D determine tie point F, determine tie point G according to above-mentioned midpoint B and midpoint C, are determined according to above-mentioned midpoint B and midpoint D
Tie point H can determine the corresponding connecting line of the first vertical direction according to tie point E, tie point F, tie point G and tie point H.
103:Determine the first angle between first vertical direction and the length direction of electronic equipment.
In this application, as shown in Figure 1 C, the length direction of electronic equipment is parallel to the corresponding side of long side of electronic equipment
To, length direction is translated, can obtain the first angle between the first vertical direction and length direction, the first angle it is big
The small acute angle chosen between the first vertical direction and length direction.If the upper angle position between the first vertical direction and length direction
In the left side of length direction, direction of rotation is clockwise, and otherwise, direction of rotation is counterclockwise;If its lower angle is located at length side
To right side, direction of rotation is clockwise, and otherwise, direction of rotation is counterclockwise.
Optionally, when first angle is less than predetermined angle threshold value, the target facial image is preset with described
Facial image is matched;When it fails to match for the target facial image and the default facial image, step 104 is performed.
Learnt according to the statistical data of recognition of face, when the angle of face and electronic equipment be less than 45 degree when, can succeed into
Row unlock, if beyond certain angle, such as:90 degree are arrived 180 degree, then are difficult to recognition of face, so as to unlock.
In this application, the maximum value of an angle, i.e. predetermined angle threshold value are preset, when the first angle is greater than or equal in advance
If during angle threshold, the success rate of recognition of face is low, then performs step 104, target facial image is carried out according to the first angle
Rotation is obtained with reference to facial image, and recognition of face is carried out by reference to facial image;When the first angle is less than predetermined angle threshold value
When, recognition of face operation is just carried out, so as to save power consumption, improves the cruise duration of electronic equipment.
104:The target facial image is rotated to obtain with reference to facial image according to first angle.
In this application, according to the size of the first angle and the corresponding direction of rotation of the first angle to target facial image into
Row rotation, so as to obtain with reference to facial image.Wherein, with reference to facial image for recognition of face operate, i.e., with default face figure
As being matched, if successful match can be unlocked.And second vertical direction with reference to facial image and the length side
The second angle between is less than the predetermined angle threshold value, i.e., when the second angle is less than predetermined angle threshold value, just into pedestrian
Face identification operation;When the second angle is greater than or equal to predetermined angle threshold value, the success rate of recognition of face is low, then without face
Identification operation, so as to save power consumption, improves the cruise duration of electronic equipment.
105:It is matched described with reference to facial image with default facial image, and be unlocked in successful match.
The application is not construed as limiting the matching process with reference to facial image and default facial image, can refer to target face
The matching process of image and default facial image obtains multiple second organs to described with reference to facial image progress recognition of face
Image;To in one second organic image every in the multiple second organic image and the default facial image with second organ
The corresponding default organic image of image is matched to obtain multiple matching values;According in the multiple second organic image every 1
The corresponding preset weights of two organic images and the multiple matching value obtain object matching value;It is more than the in the object matching value
During one threshold value, the reference facial image and the default facial image successful match are determined, details are not described herein.
In method as shown in Figure 1, the target facial image in image to be verified is extracted, is obtained in target facial image
Multiple first organic images, the first vertical direction of target facial image is determined according to multiple first organic images, determines
The first angle between one vertical direction and the length direction of electronic equipment revolves target facial image according to the first angle
Turn to obtain with reference to facial image, will match with default facial image with reference to facial image, and if successful match, be solved
Lock.That is, when target facial image is there are during certain angular error, by carrying out angle adjustment to target facial image
It obtains with reference to facial image, and the second angle between the second vertical direction and length direction of reference facial image is less than default
Angle threshold can improve the accuracy rate of recognition of face, and angle adjustment is repeatedly carried out without user and resurveys figure to be verified
Picture, so as to improve the flexibility of unlock.
It is consistent with embodiment shown in FIG. 1, Fig. 2 is please referred to, Fig. 2 is another solution lock control provided by the embodiments of the present application
Device, applied to the described electronic equipments of such as Figure 1A.As shown in Fig. 2, the solution lock control device 200 includes:
Recognition unit 201 carries out recognition of face for treating authentication image, obtains target facial image and the target person
Multiple first organic images in face image;
Determination unit 202, for determining that the first of the target facial image erects according to the multiple first organic image
Nogata to;Determine the first angle between first vertical direction and the length direction of electronic equipment;
Rotary unit 203 for being rotated according to first angle to the target facial image, obtains reference man
Face image, second angle with reference between the second vertical direction of facial image and the length direction are less than predetermined angle
Threshold value;
Matching unit 204, for being matched described with reference to facial image with default facial image;
Unlocking unit 205, in 204 successful match of matching unit, being unlocked.
In a possible example, the recognition unit 201 is specifically used for carrying out face to the target facial image
Identification, obtains multiple characteristic points;The determination unit 202 is specifically used for determining that multiple peripheries are taken turns according to the multiple characteristic point
It is wide;The multiple first organic image is determined according to the multiple circumference.
In a possible example, the determination unit 202 is specifically used for selecting from the multiple first organic image
Target organ image is taken, obtains multiple target organ images;Obtain each target organ figure in the multiple target organ image
The midpoint of picture obtains multiple midpoints;The multiple midpoint is grouped, obtains multigroup midpoint;It obtains in multigroup midpoint
The corresponding tie point of each class mid point, obtains multiple tie points;First vertical direction is determined according to the multiple tie point.
In a possible example, the matching unit 204 is additionally operable to be less than the preset angle in first angle
When spending threshold value, the target facial image is matched with the default facial image;In the target facial image and institute
When stating default facial image it fails to match, the rotary unit 203 is called.
In a possible example, the recognition unit 201 is additionally operable to carry out face knowledge with reference to facial image to described
Not, multiple second organic images are obtained;The matching unit 204 is specifically used for in the multiple second organic image every 1 the
Default organic image corresponding with second organic image is matched in two organic images and the default facial image, is obtained
Multiple matching values;According to corresponding preset weights of one second organic image every in the multiple second organic image and the multiple
Matching value obtains object matching value;When the object matching value is more than first threshold, determine described with reference to facial image and institute
State default facial image successful match.
In device as shown in Figure 2, the target facial image in image to be verified is extracted, is obtained in target facial image
Multiple first organic images, the first vertical direction of target facial image is determined according to multiple first organic images, determines
The first angle between one vertical direction and the length direction of electronic equipment revolves target facial image according to the first angle
Turn to obtain with reference to facial image, will match with default facial image with reference to facial image, and if successful match, be solved
Lock.That is, when target facial image is there are during certain angular error, by carrying out angle adjustment to target facial image
It obtains with reference to facial image, and the second angle between the second vertical direction and length direction of reference facial image is less than default
Angle threshold can improve the accuracy rate of recognition of face, and angle adjustment is repeatedly carried out without user and resurveys figure to be verified
Picture, so as to improve the flexibility of unlock.
It is consistent with embodiment shown in FIG. 1, Fig. 3 is please referred to, Fig. 3 is set for another electronics provided by the embodiments of the present application
It is standby.As shown in figure 3, above-mentioned electronic equipment 300 includes processor 310 and the memory 320 and Image Acquisition that are connect with processor
Device 330.
In the present embodiment, described image harvester 330 is used to acquire image to be verified;The memory 320 is used for
The default facial image of storage and predetermined angle threshold value;The processor 310 is used to carry out recognition of face to the image to be verified
Obtain multiple first organic images in target facial image and the target facial image;According to the multiple first organ figure
The first vertical direction as determining the target facial image;Determine the length of first vertical direction and electronic equipment 300
The first angle between direction;The target facial image is rotated to obtain with reference to face figure according to first angle
Picture, second angle with reference between the second vertical direction of facial image and the length direction are less than the predetermined angle
Threshold value;It is matched described with reference to facial image with the default facial image, and be unlocked in successful match.
In a possible example, the processor 310 is specifically used for carrying out face knowledge to the target facial image
Not, multiple characteristic points are obtained;Multiple circumferences are determined according to the multiple characteristic point;It is determined according to the multiple circumference
The multiple first organic image.
In a possible example, the processor 310 is specifically used for choosing from the multiple first organic image
Target organ image obtains multiple target organ images;Obtain each target organ image in the multiple target organ image
Midpoint obtains multiple midpoints;The multiple midpoint is grouped to obtain multigroup midpoint;Each group is obtained in multigroup midpoint
The corresponding tie point in midpoint obtains multiple tie points;First vertical direction is determined according to the multiple tie point.
In a possible example, the processor 310 is additionally operable to be less than the predetermined angle in first angle
During threshold value, the target facial image is matched with the default facial image;The target facial image with it is described
Default facial image is when it fails to match, perform it is described the target facial image is rotated according to first angle, obtain
To with reference to the step of facial image.
In a possible example, the memory 320 is additionally operable to store every one second in multiple second organic images
The corresponding preset weights of organic image and first threshold;The processor 310 is specifically used for carrying out with reference to facial image to described
Recognition of face obtains the multiple second organic image;To one second organic image every in the multiple second organic image and institute
Default organic image corresponding with second organic image in default facial image is stated to be matched to obtain multiple matching values;According to
Every corresponding preset weights of one second organic image and the multiple matching value obtain target in the multiple second organic image
Matching value;When the object matching value is more than the first threshold, the reference facial image and the default face are determined
Images match success.
In electronic equipment as shown in Figure 3, the target facial image in image to be verified is extracted, obtains target face figure
Multiple first organic images as in determine the first vertical direction of target facial image according to multiple first organic images, really
The first angle between fixed first vertical direction and the length direction of electronic equipment, according to the first angle to target facial image into
Row rotation obtains, with reference to facial image, to match with default facial image with reference to facial image, and if successful match, carrying out
Unlock.That is, when target facial image is there are during certain angular error, by carrying out angle tune to target facial image
It is whole to obtain with reference to facial image, and the second angle between the second vertical direction and length direction of reference facial image is less than in advance
If angle threshold, the accuracy rate of recognition of face can be improved, repeatedly carried out without user angle adjustment resurvey it is to be verified
Image, so as to improve the flexibility of unlock.
It is consistent with embodiment shown in FIG. 1, Fig. 4 is please referred to, Fig. 4 is another solution lock control provided by the embodiments of the present application
Method, applied to electronic equipment as described in Figure 3.As shown in figure 4, the solution lock control method includes:
401:Image acquisition device image to be verified;
402:The default facial image of memory storage and predetermined angle threshold value;
403:Processor carries out recognition of face to the image to be verified and obtains target facial image and the target face
Multiple first organic images in image;Determine the target facial image according to the multiple first organic image first is erected
Nogata to;Determine the first angle between first vertical direction and the length direction of electronic equipment;According to the described first folder
Angle is rotated to obtain with reference to facial image to the target facial image;By the reference facial image and the default face
Image is matched, and is unlocked in successful match.
Wherein, second angle with reference between the second vertical direction of facial image and the length direction is less than institute
State predetermined angle threshold value.
In a possible example, the processor carries out recognition of face to the image to be verified and obtains target face
Multiple first organic images in image and the target facial image include:
The processor carries out recognition of face to the target facial image and obtains multiple characteristic points;According to the multiple spy
Sign point determines multiple circumferences;The multiple first organic image is determined according to the multiple circumference.
In a possible example, the processor determines the target face according to the multiple first organic image
First vertical direction of image includes:
The processor chooses target organ image from the multiple first organic image, obtains multiple target organ figures
Picture;The midpoint of each target organ image in the multiple target organ image is obtained, obtains multiple midpoints;In the multiple
Point is grouped, and obtains multigroup midpoint;The corresponding tie point of each class mid point in multigroup midpoint is obtained, obtains multiple connections
Point;First vertical direction is determined according to the multiple tie point.
In a possible example, the target facial image is carried out according to first angle in the processor
Rotation is obtained with reference to before facial image, and the method further includes:
The processor is when first angle is less than the predetermined angle threshold value, by the target facial image and institute
Default facial image is stated to be matched;When it fails to match for the target facial image and the default facial image, institute is performed
It states and the target facial image is rotated according to first angle, obtain with reference to the step of facial image.
In a possible example, the processor is carried out described with reference to facial image and the default facial image
Matching, including:
The memory stores the corresponding preset weights of every one second organic image in multiple second organic images and first
Threshold value;
The processor carries out recognition of face to described with reference to facial image, obtains the multiple second organic image;It is right
In the multiple second organic image in every one second organic image and the default facial image with second organic image pair
The default organic image answered is matched, and obtains multiple matching values;According to one second device every in the multiple second organic image
The corresponding preset weights of official's image and the multiple matching value obtain object matching value;It is more than described the in the object matching value
During one threshold value, the reference facial image and the default facial image successful match are determined.
In method as shown in Figure 4, the target facial image in image to be verified is extracted, is obtained in target facial image
Multiple first organic images, the first vertical direction of target facial image is determined according to multiple first organic images, determines
The first angle between one vertical direction and the length direction of electronic equipment revolves target facial image according to the first angle
Turn to obtain with reference to facial image, will match with default facial image with reference to facial image, and if successful match, be solved
Lock.That is, when target facial image is there are during certain angular error, by carrying out angle adjustment to target facial image
It obtains with reference to facial image, and the second angle between the second vertical direction and length direction of reference facial image is less than default
Angle threshold can improve the accuracy rate of recognition of face, and angle adjustment is repeatedly carried out without user and resurveys figure to be verified
Picture, so as to improve the flexibility of unlock.
It is consistent with the embodiment of Fig. 1, Fig. 2, Fig. 3 and Fig. 4, Fig. 5 is please referred to, Fig. 5 is provided by the embodiments of the present application another
The structure diagram of kind electronic equipment, as shown in figure 5, the electronic equipment 500 includes, processor 510, memory 520, communicating connects
Mouthfuls 530 and one or more programs 540, wherein, one or more programs 540 are stored in memory 520, and by with
It puts and is performed by processor 510, program 540 includes the instruction for performing following steps:
It treats authentication image and carries out recognition of face, obtain multiple the in target facial image and the target facial image
One organic image;
The first vertical direction of the target facial image is determined according to the multiple first organic image;
Determine the first angle between first vertical direction and the length direction of electronic equipment;
The target facial image is rotated according to first angle, is obtained with reference to facial image, the reference
The second angle between the second vertical direction and the length direction of facial image is less than predetermined angle threshold value;
It is matched described with reference to facial image with default facial image, and in successful match, be unlocked.
It in a possible example, is identified in the authentication image for the treatment of, obtains target facial image and described
In terms of multiple first organic images in target facial image, above procedure 540 is specifically used for performing the instruction of following steps:
Recognition of face is carried out to the target facial image, obtains multiple characteristic points;
Multiple circumferences are determined according to the multiple characteristic point;
The multiple first organic image is determined according to the multiple circumference.
In a possible example, the target facial image is determined according to the multiple first organic image described
The first vertical direction in terms of, above procedure 540 be specifically used for perform following steps instruction:
Target organ image is chosen from the multiple first organic image, obtains multiple target organ images;
The midpoint of each target organ image in the multiple target organ image is obtained, obtains multiple midpoints;
The multiple midpoint is grouped, obtains multigroup midpoint;
The corresponding tie point of each class mid point in multigroup midpoint is obtained, obtains multiple tie points;
First vertical direction is determined according to the multiple tie point.
In a possible example, the target facial image is rotated according to first angle described,
It obtains with reference to before facial image, above procedure 540 is additionally operable to perform the instruction of following steps:
When first angle is less than the predetermined angle threshold value, by the target facial image and the default face
Image is matched;
When it fails to match for the target facial image and the default facial image, perform described according to the described first folder
Angle rotates the target facial image, obtains with reference to the step of facial image.
In a possible example, match party is carried out with reference to facial image and default facial image described by described
Face, above procedure 540 are specifically used for performing the instruction of following steps:
Recognition of face is carried out with reference to facial image to described, obtains multiple second organic images;
To in one second organic image every in the multiple second organic image and the default facial image with this second
The corresponding default organic image of organic image is matched, and obtains multiple matching values;
According to the corresponding preset weights of one second organic image every in the multiple second organic image and the multiple
Object matching value is obtained with value;
When the object matching value is more than first threshold, the reference facial image and the default facial image are determined
Successful match.
In electronic equipment as shown in Figure 5, the target facial image in image to be verified is extracted, obtains target face figure
Multiple first organic images as in determine the first vertical direction of target facial image according to multiple first organic images, really
The first angle between fixed first vertical direction and the length direction of electronic equipment, according to the first angle to target facial image into
Row rotation obtains, with reference to facial image, to match with default facial image with reference to facial image, and if successful match, carrying out
Unlock.That is, when target facial image is there are during certain angular error, by carrying out angle tune to target facial image
It is whole to obtain with reference to facial image, and the second angle between the second vertical direction and length direction of reference facial image is less than in advance
If angle threshold, the accuracy rate of recognition of face can be improved, repeatedly carried out without user angle adjustment resurvey it is to be verified
Image, so as to improve the flexibility of unlock.
The embodiment of the present application also provides a kind of computer storage media, wherein, which stores to deposit
Computer program is stored up, which causes computer to perform the part or complete of the either method as described in embodiment of the method
Portion's step, computer include electronic equipment.
The embodiment of the present application also provides a kind of computer program product, and computer program product includes storing computer journey
The non-transient computer readable storage medium of sequence, computer program are operable to that computer is made to perform as in embodiment of the method remembered
The part or all of step of the either method of load.The computer program product can be a software installation packet, and computer includes
Electronic equipment.
It should be noted that for aforementioned each method embodiment, in order to be briefly described, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should know, the application is not limited by described sequence of movement because
According to the application, certain steps may be used other sequences or be carried out at the same time.Secondly, those skilled in the art should also know
It knows, embodiment described in this description belongs to preferred embodiment, involved action and module not necessarily the application
It is necessary.
In embodiment, it all emphasizes particularly on different fields to the description of each embodiment, there is no the part being described in detail in some embodiment, it can
With referring to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, such as the division of unit, only a kind of logic
Function divides, and can have other dividing mode in actual implementation, such as multiple units or component can be combined or can be collected
Into to another system or some features can be ignored or does not perform.Another point, shown or discussed mutual coupling
Close or direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING or communication connection of device or unit, can be with
It is electrical or other forms.
The unit illustrated as separating component may or may not be physically separate, be shown as unit
Component may or may not be physical unit, you can be located at a place or can also be distributed to multiple networks
On unit.Some or all of unit therein can be selected according to the actual needs to realize the purpose of this embodiment scheme.
In addition, each functional unit in each embodiment of the application can be integrated in a processing unit, it can also
That each unit is individually physically present, can also two or more units integrate in a unit.Integrated unit was both
The form that hardware may be used is realized, can also be realized in the form of SFU software functional unit.
If integrated unit realized in the form of SFU software functional unit and be independent product sale or in use, can
To be stored in a computer-readable access to memory.Based on such understanding, the technical solution of the application is substantially in other words
The part contribute to the prior art or all or part of the technical solution can be embodied in the form of software product
Come, which is stored in a memory, is used including some instructions so that a computer equipment (can be
Personal computer, server or network equipment etc.) perform each embodiment method of the application all or part of step.It is and preceding
The memory stated includes:USB flash disk, read-only memory (read-only memory, ROM), random access memory (random
Access memory, RAM), mobile hard disk, the various media that can store program code such as magnetic disc or CD.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer-readable memory, memory
It can include:Flash disk, ROM, RAM, disk or CD etc..
The embodiment of the present application is described in detail above, specific case used herein to the principle of the application and
Embodiment is expounded, and the explanation of above example is only intended to help to understand the present processes and its core concept;
Meanwhile for those of ordinary skill in the art, according to the thought of the application, can in specific embodiments and applications
There is change part, to sum up, the content of the present specification should not be construed as the limitation to the application.
Claims (14)
1. a kind of solution lock control method, which is characterized in that including:
It treats authentication image and carries out recognition of face, obtain multiple first devices in target facial image and the target facial image
Official's image;
The first vertical direction of the target facial image is determined according to the multiple first organic image;
Determine the first angle between first vertical direction and the length direction of electronic equipment;
The target facial image is rotated according to first angle, is obtained with reference to facial image, it is described to refer to face
The second angle between the second vertical direction and the length direction of image is less than predetermined angle threshold value;
It is matched described with reference to facial image with default facial image, and in successful match, be unlocked.
2. according to the method described in claim 1, it is characterized in that, the authentication image for the treatment of is identified, target person is obtained
Multiple first organic images in face image and the target facial image, including:
Recognition of face is carried out to the target facial image, obtains multiple characteristic points;
Multiple circumferences are determined according to the multiple characteristic point;
The multiple first organic image is determined according to the multiple circumference.
3. method according to claim 1 or 2, which is characterized in that described to be determined according to the multiple first organic image
First vertical direction of the target facial image, including:
Target organ image is chosen from the multiple first organic image, obtains multiple target organ images;
The midpoint of each target organ image in the multiple target organ image is obtained, obtains multiple midpoints;
The multiple midpoint is grouped, obtains multigroup midpoint;
The corresponding tie point of each class mid point in multigroup midpoint is obtained, obtains multiple tie points;
First vertical direction is determined according to the multiple tie point.
4. according to claim 1-3 any one of them methods, which is characterized in that it is described according to first angle to described
Target facial image is rotated, and is obtained with reference to before facial image, the method further includes:
When first angle is less than the predetermined angle threshold value, by the target facial image and the default facial image
It is matched;
When it fails to match for the target facial image and the default facial image, perform described according to first angle pair
The target facial image is rotated, and is obtained with reference to the step of facial image.
5. according to claim 1-4 any one of them methods, which is characterized in that the facial image that described will refer to is with presetting
Facial image is matched, including:
Recognition of face is carried out with reference to facial image to described, obtains multiple second organic images;
To in one second organic image every in the multiple second organic image and the default facial image with second organ
The corresponding default organic image of image is matched, and obtains multiple matching values;
According to every corresponding preset weights of one second organic image and the multiple matching value in the multiple second organic image
Obtain object matching value;
When the object matching value is more than first threshold, determine that the facial image that refers to is matched with the default facial image
Success.
6. a kind of electronic equipment, which is characterized in that including processor, the memory and image collector that are connected to the processor
It puts, wherein:
Described image harvester, for acquiring image to be verified;
The memory, for storing default facial image and predetermined angle threshold value;
The processor for carrying out recognition of face to the image to be verified, obtains target facial image and the target person
Multiple first organic images in face image;The first of the target facial image is determined according to the multiple first organic image
Vertical direction;Determine the first angle between first vertical direction and the length direction of electronic equipment;According to described first
Angle rotates the target facial image, obtains with reference to facial image, the second vertical side with reference to facial image
The second angle between the length direction is less than the predetermined angle threshold value;By it is described with reference to facial image with it is described pre-
If facial image is matched, and in successful match, is unlocked.
7. electronic equipment according to claim 6, which is characterized in that the processor is specifically used for the target face
Image carries out recognition of face, obtains multiple characteristic points;Multiple circumferences are determined according to the multiple characteristic point;According to described more
A circumference determines the multiple first organic image.
8. the electronic equipment described according to claim 6 or 7, which is characterized in that the processor is specifically used for from the multiple
Target organ image is chosen in first organic image, obtains multiple target organ images;Obtain the multiple target organ image
In each target organ image midpoint, obtain multiple midpoints;The multiple midpoint is grouped, obtains multigroup midpoint;It obtains
The corresponding tie point of each class mid point in multigroup midpoint is taken, obtains multiple tie points;It is determined according to the multiple tie point
First vertical direction.
9. according to claim 6-8 any one of them electronic equipments, which is characterized in that the processor is additionally operable to described
When one angle is less than the predetermined angle threshold value, the target facial image is matched with the default facial image;
The target facial image and the default facial image be when it fails to match, perform it is described according to first angle to the mesh
Mark facial image is rotated, and is obtained with reference to the step of facial image.
10. according to claim 6-9 any one of them electronic equipments, which is characterized in that it is more to be additionally operable to storage for the memory
The corresponding preset weights of every one second organic image and first threshold in a second organic image;
The processor is specifically used for carrying out recognition of face with reference to facial image to described, obtains the multiple second organ figure
Picture;To in one second organic image every in the multiple second organic image and the default facial image with the second organ figure
As corresponding default organic image is matched, multiple matching values are obtained;According in the multiple second organic image every 1
The corresponding preset weights of two organic images and the multiple matching value obtain object matching value;It is more than institute in the object matching value
When stating first threshold, the reference facial image and the default facial image successful match are determined.
11. a kind of solution lock control device, which is characterized in that including:
Recognition unit carries out recognition of face for treating authentication image, obtains target facial image and the target facial image
In multiple first organic images;
Determination unit, for determining the first vertical direction of the target facial image according to the multiple first organic image;
Determine the first angle between first vertical direction and the length direction of electronic equipment;
Rotary unit for being rotated according to first angle to the target facial image, is obtained with reference to facial image,
Second angle with reference between the second vertical direction of facial image and the length direction is less than predetermined angle threshold value;
Matching unit, for being matched described with reference to facial image with default facial image;
Unlocking unit, in the matching unit successful match, being unlocked.
12. a kind of solution lock control method, which is characterized in that applied to including processor, the memory being connected to the processor
With the electronic equipment of image collecting device, wherein:
Described image harvester acquires image to be verified;
Facial image and predetermined angle threshold value are preset in the memory storage;
The processor carries out recognition of face to the image to be verified, obtains target facial image and the target facial image
In multiple first organic images;The first vertical side of the target facial image is determined according to the multiple first organic image
To;Determine the first angle between first vertical direction and the length direction of electronic equipment;According to first angle pair
The target facial image is rotated, and is obtained with reference to facial image, second vertical direction and institute with reference to facial image
The second angle stated between length direction is less than the predetermined angle threshold value;By the reference facial image and the default face
Image is matched, and in successful match, is unlocked.
13. a kind of electronic equipment, which is characterized in that including processor, memory, communication interface and one or more program,
Wherein, one or more of programs are stored in the memory, and are configured to be performed by the processor, the journey
Sequence is included for the instruction of the step in any one of perform claim requirement 1-5 methods.
14. a kind of computer readable storage medium, which is characterized in that it is used to store computer program, wherein, the computer
Program causes computer to perform such as claim 1-5 any one of them methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810100940.6A CN108268765A (en) | 2018-01-31 | 2018-01-31 | Solve lock control method and Related product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810100940.6A CN108268765A (en) | 2018-01-31 | 2018-01-31 | Solve lock control method and Related product |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108268765A true CN108268765A (en) | 2018-07-10 |
Family
ID=62777218
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810100940.6A Pending CN108268765A (en) | 2018-01-31 | 2018-01-31 | Solve lock control method and Related product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108268765A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109241942A (en) * | 2018-09-29 | 2019-01-18 | 佳都新太科技股份有限公司 | Image processing method, device, face recognition device and storage medium |
CN110766839A (en) * | 2018-11-01 | 2020-02-07 | 上海掌门科技有限公司 | Entrance guard device and using method thereof |
CN113657379A (en) * | 2021-08-09 | 2021-11-16 | 杭州华橙软件技术有限公司 | Image processing method, image processing device, computer-readable storage medium and processor |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103885611A (en) * | 2014-04-22 | 2014-06-25 | 锤子科技(北京)有限公司 | Method and device for adjusting image |
CN103970259A (en) * | 2013-01-31 | 2014-08-06 | 华为技术有限公司 | Screen mode switching method and terminal equipment |
CN105760836A (en) * | 2016-02-17 | 2016-07-13 | 厦门美图之家科技有限公司 | Multi-angle face alignment method based on deep learning and system thereof and photographing terminal |
CN106303029A (en) * | 2016-08-15 | 2017-01-04 | 广东欧珀移动通信有限公司 | The method of controlling rotation of a kind of picture, device and mobile terminal |
CN107358207A (en) * | 2017-07-14 | 2017-11-17 | 重庆大学 | A kind of method for correcting facial image |
CN107423678A (en) * | 2017-05-27 | 2017-12-01 | 电子科技大学 | A kind of training method and face identification method of the convolutional neural networks for extracting feature |
CN107423712A (en) * | 2017-07-28 | 2017-12-01 | 南京华捷艾米软件科技有限公司 | A kind of 3D face identification methods |
CN107506702A (en) * | 2017-08-08 | 2017-12-22 | 江西高创保安服务技术有限公司 | Human face recognition model training and test system and method based on multi-angle |
CN107527046A (en) * | 2017-09-21 | 2017-12-29 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
CN107590474A (en) * | 2017-09-21 | 2018-01-16 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
CN107622243A (en) * | 2017-09-21 | 2018-01-23 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
-
2018
- 2018-01-31 CN CN201810100940.6A patent/CN108268765A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103970259A (en) * | 2013-01-31 | 2014-08-06 | 华为技术有限公司 | Screen mode switching method and terminal equipment |
CN103885611A (en) * | 2014-04-22 | 2014-06-25 | 锤子科技(北京)有限公司 | Method and device for adjusting image |
CN105760836A (en) * | 2016-02-17 | 2016-07-13 | 厦门美图之家科技有限公司 | Multi-angle face alignment method based on deep learning and system thereof and photographing terminal |
CN106303029A (en) * | 2016-08-15 | 2017-01-04 | 广东欧珀移动通信有限公司 | The method of controlling rotation of a kind of picture, device and mobile terminal |
CN107423678A (en) * | 2017-05-27 | 2017-12-01 | 电子科技大学 | A kind of training method and face identification method of the convolutional neural networks for extracting feature |
CN107358207A (en) * | 2017-07-14 | 2017-11-17 | 重庆大学 | A kind of method for correcting facial image |
CN107423712A (en) * | 2017-07-28 | 2017-12-01 | 南京华捷艾米软件科技有限公司 | A kind of 3D face identification methods |
CN107506702A (en) * | 2017-08-08 | 2017-12-22 | 江西高创保安服务技术有限公司 | Human face recognition model training and test system and method based on multi-angle |
CN107527046A (en) * | 2017-09-21 | 2017-12-29 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
CN107590474A (en) * | 2017-09-21 | 2018-01-16 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
CN107622243A (en) * | 2017-09-21 | 2018-01-23 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109241942A (en) * | 2018-09-29 | 2019-01-18 | 佳都新太科技股份有限公司 | Image processing method, device, face recognition device and storage medium |
CN109241942B (en) * | 2018-09-29 | 2022-05-03 | 佳都科技集团股份有限公司 | Image processing method and device, face recognition equipment and storage medium |
CN110766839A (en) * | 2018-11-01 | 2020-02-07 | 上海掌门科技有限公司 | Entrance guard device and using method thereof |
CN113657379A (en) * | 2021-08-09 | 2021-11-16 | 杭州华橙软件技术有限公司 | Image processing method, image processing device, computer-readable storage medium and processor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108345779A (en) | Solve lock control method and Related product | |
CN108830211A (en) | Face identification method and Related product based on deep learning | |
CN104573652B (en) | Determine the method, apparatus and terminal of the identity of face in facial image | |
CN107622243A (en) | Solve lock control method and Related product | |
CN107590474B (en) | Unlocking control method and related product | |
CN108268765A (en) | Solve lock control method and Related product | |
CN107527046B (en) | Unlocking control method and related product | |
CN107506629B (en) | Unlocking control method and related product | |
CN107330316B (en) | Unlocking processing method and related product | |
CN108319837A (en) | Electronic equipment, face template input method and Related product | |
CN109214337A (en) | A kind of Demographics' method, apparatus, equipment and computer readable storage medium | |
WO2016183937A1 (en) | Identity authentication method, device and system, and user terminal | |
CN108415560A (en) | Electronic device, method of controlling operation thereof and Related product | |
CN110119608A (en) | A kind of biological information processing method, biological information store method and device | |
CN103729622B (en) | A kind of finger vein three-dimensional point cloud acquisition methods, device and a kind of terminal | |
CN104036266A (en) | Fingerprint registration method, fingerprint recognition method, fingerprint recognition device and terminal device | |
CN107463813A (en) | Condition control method and Related product | |
CN109816543A (en) | A kind of image lookup method and device | |
CN107015745A (en) | Screen operation method and device, terminal equipment and computer readable storage medium | |
CN110321791A (en) | Portrait data arrangement method, device and storage medium based on recognition of face | |
CN112613435A (en) | Face image generation method, device, equipment and medium | |
CN107454251B (en) | Unlocking control method and related product | |
CN107945102A (en) | A kind of picture synthetic method and device | |
CN108415564A (en) | Electronic device, apparatus control method and Related product | |
CN107451451A (en) | Solve lock control method and Related product |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180710 |