CN109508526A - A kind of machine solution locking device based on recognition of face - Google Patents
A kind of machine solution locking device based on recognition of face Download PDFInfo
- Publication number
- CN109508526A CN109508526A CN201811528816.6A CN201811528816A CN109508526A CN 109508526 A CN109508526 A CN 109508526A CN 201811528816 A CN201811528816 A CN 201811528816A CN 109508526 A CN109508526 A CN 109508526A
- Authority
- CN
- China
- Prior art keywords
- user
- characteristic information
- face characteristic
- user images
- 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.)
- Withdrawn
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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of machine solution locking device based on recognition of face, comprising: camera on computers is installed, for obtaining user images；Database module, for establishing the database including the first face characteristic information；Image processing module, the user images for obtaining to the camera are handled, to obtain the second face characteristic information of the user images；Judgment module, unlock instruction is issued for judging whether the similarity of second face characteristic information and first face characteristic information is greater than the threshold value of setting, and when the similarity of second face characteristic information and the first face characteristic information is greater than the threshold value of setting；Unlocked state, for being unlocked according to the unlock instruction to the computer.The foundation that the present invention is unlocked by the face characteristic of identification user as computer, can effectively improve the security performance of computer, and easy to use, adapt to the use of office and public arena computer.
Description
Technical field
The present invention relates to field of computer technology, especially a kind of machine solution locking device based on recognition of face.
Background technique
With the continuous development of society, computer has become people's work and sets with essential one kind in life
Standby, computer can help people to store mass data, but also bring great information security hidden danger simultaneously, in Working Life
In, it will usually data stored by oneself is stolen by others because the security performance of computer is bad, usual people can be to meter
Calculation machine designs a numerical ciphers to be protected, but is likely to occur due to password and forgets and bring unnecessary trouble, because
We need a kind of scheme to solve the above problems this.
Summary of the invention
In view of the above-mentioned problems, the present invention is intended to provide a kind of machine solution locking device based on recognition of face.
The purpose of the present invention is realized using following technical scheme:
A kind of machine solution locking device based on recognition of face, comprising:
The camera of installation on computers, for obtaining user images；
Database module, for establishing the database including the first face characteristic information；
Image processing module, the user images for obtaining to the camera are handled, to obtain the user images
The second face characteristic information；
Judgment module, for judging the first face characteristic information described in second face characteristic information and database
Whether similarity is greater than the threshold value of setting, and big in the similarity of second face characteristic information and the first face characteristic information
Unlock instruction is issued when the threshold value of setting；
Unlocked state, for being unlocked according to the unlock instruction to the computer.
The invention has the benefit that obtaining user images by the camera for being mounted on computer, and by image
Reason module is analyzed and processed the user images of acquisition, obtains the characteristic information of the user images, and the feature letter that will acquire
It ceases and is compared with the face characteristic information for prestoring in the database, when the two similarity is greater than the threshold value of setting, Yong Hushen
Part is proved to be successful, and control computer is unlocked for user's normal use, by identifying the face characteristic of user as computer
The foundation of unlock can effectively improve the security performance of computer, and easy to use, adapt to office and public arena calculates
The use of machine.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is frame construction drawing of the invention；
Fig. 2 is the frame construction drawing of image processing module of the present invention.
Appended drawing reference:
Camera 1, Database module 2, image processing module 3, judgment module 4, unlocked state 5, pretreatment unit
31, edge detection unit 32, feature extraction unit 33
Specific embodiment
In conjunction with following application scenarios, the invention will be further described.
Referring to Fig. 1, a kind of machine solution locking device based on recognition of face is shown, comprising:
The camera 1 of installation on computers, for obtaining user images；
Database module 2, for establishing the database including the first face characteristic information；
Image processing module 3, the user images for obtaining to the camera 1 are handled, to obtain user figure
Second face characteristic information of picture；
Judgment module 4, for judging the first face characteristic information described in second face characteristic information and database
Similarity whether be greater than the threshold value of setting, and in the similarity of second face characteristic information and the first face characteristic information
Greater than setting threshold value when issue unlock instruction；
Unlocked state 5, for being unlocked according to the unlock instruction to the computer.
Above embodiment of the present invention, the camera 1 by being mounted on computer obtain user images, and by image
The user images of 3 pairs of module acquisitions of reason are analyzed and processed, and obtain the characteristic information of the user images, and the feature letter that will acquire
It ceases and is compared with the face characteristic information for prestoring in the database, when the two similarity is greater than the threshold value of setting, Yong Hushen
Part is proved to be successful, and control computer is unlocked for user's normal use, by identifying the face characteristic of user as computer
The foundation of unlock can effectively improve the security performance of computer, and easy to use, adapt to office and public arena calculates
The use of machine.
In one embodiment, further include wake-up module, obtained for receiving to wake up the camera 1 after user instruction
Take the user images.
In a kind of scene, user wakes up camera 1 by input arbitrary instruction to obtain user images.
In a kind of scene, user carrys out annular camera 1 and obtains user images, to user by clicking " login " button
Identity is verified.
In one embodiment, according to the user images in backstage typing, user of the image processing module to the typing
Image carries out processing analysis and extracts face characteristic information therein as the first face characteristic information, by the Database
Module 2 constructs database according to the first face characteristic information of acquisition.
In one embodiment, computer administrator can control computer camera and obtain user images, and should
The face characteristic information is entered into data by the Database module 2 by the corresponding face characteristic information of user images
In library.
In one embodiment, referring to fig. 2, described image processing module 3, including sequentially connected:
Pretreatment unit 31, the user images for obtaining to the camera 1 carry out enhancing denoising, obtain pre- place
User images after reason；
Edge detection unit 32 is partitioned into use for carrying out edge detection process to the pretreated user images
Family facial image；
Feature extraction unit 33 obtains the binary conversion treatment for carrying out binary conversion treatment to user's facial image
The characteristic parameter of user's facial image afterwards, using this feature parameter as second face characteristic information.
Above embodiment of the present invention, image processing module 3 carry out enhancing denoising to the user images of acquisition first,
It can be effectively reduced the interference because of noise present in use environment to user images, improve the reliable of image processing module 3
Property；Then edge detection process is carried out to pretreated user images, the human face region of user is partitioned into from image, removed
Remaining background area can concentrate and carry out identifying processing to user's human face region, and further increase image processing module 3 can
By property and accuracy；Feature extraction processing finally is carried out to user's human face region, obtains the characteristic parameter of the facial image of user
As the face characteristic information of user, lay a good foundation to be subsequent to face characteristic information is compared.
In one embodiment, in the judgment module 4, the similarity threshold that sets as 99%, 98%, 95%,
90%, 85% or any other numerical value.
In one embodiment, the pretreatment unit 31, the user images for obtaining to the camera 1 carry out
Enhance denoising, obtain pretreated user images, specifically include:
Initial phase initializes the number of iterations D=0, iteration step length Δ T, carries out gray scale to the user images are received
Change processing obtains user's gray level image and is denoted as A0
The iterative processing stage carries out enhancing processing to user's gray level image, wherein the custom images enhancing function used
Are as follows:
In formula, AD+1And ADUser's gray level image when D+1 and D iteration enhancing processing is respectively indicated, G indicates split window
Number, wherein window size is z × z, and image size is a × b, then G=(a-z+1) × (b-z+1), CDIndicate current time second order
The tangential spread function of Partial Differential Equation Model, whereinY(A
(i)D) indicate D iteration when the i-th window in normalization histogram, K (i)maxWith K (i)minIt respectively indicates in the i-th window most
High-gray level value and minimum gradation value, Δ T indicate iteration step length, 0 < Δ T≤1, V1With the tangential smooth adjustment factor of expression, V2It indicates
Enhance proportionality coefficient；UxAnd UyRespectively indicate the forwardly and rearwardly difference value of partial derivative, Uxx、Uxy、UyyRespectively indicate second order local derviation
Several finite-difference approximation values, R indicate regulatory factor,Indicate that image gradient vector, v indicate the edge regulatory factor of setting, S
Indicate the gray scale impact factor of setting；
The judgement stage updates the number of iterations D=D+1, if the number of iterations is greater than the maximum number of iterations of setting, exports AD
As pretreated user images；Otherwise, return processing stage is for further processing.
In a kind of scene, z=3, Δ T=0.5；
Above embodiment of the present invention adopts and carries out enhancing denoising to user images in manner just described, changes each
For in the period, by setting processing window, successively traverse user image carries out enhancing and denoising, can be effectively to user
Noise in image carries out smoothly, while playing a very good protection to marginal portion therein, and denoising and reinforcing effect are aobvious
It writes, significantly reduces noise jamming present in use environment, user images are done into one to be subsequent in image processing module 3
The identifying processing of step is laid a good foundation.
In one embodiment, feature extraction unit 33, for carrying out binary conversion treatment to user's facial image,
User's facial image after the binary conversion treatment is obtained, is specifically included:
Gray scale adjusting processing is carried out to user's facial image, wherein the gray scale adjustment function of use are as follows:
In formula, F (a, b) indicates the gray value of user's facial image pixel (a, b), fdIndicate the image slices of setting
Plain mean value adjustment parameter, wdIndicate the image pixel variance adjustment parameter of setting,Indicate the ash of all pixels point in original image
Mean value is spent, w indicates that the gray variance of all pixels point in user's facial image, F ' (a, b) indicate the user people after gray scale adjusting
Face image pixel (a, b) gray value；
Treated image is adjusted to gray scale and carries out binary conversion treatment, binaryzation user facial image is obtained, wherein using
Customized binaryzation function are as follows:
In formula, j (a, b) indicates the gray value of pixel (a, b) in binaryzation user's facial image after binary conversion treatment, F '
(a, b) indicates that pixel (a, b) gray value in user's facial image after gray scale adjusting, P (a, b) indicate adaptive judgement threshold value,
Wherein,μ
Indicate that established standards difference dynamic factor, σ indicate the adjusting threshold value regulatory factor of setting, f (i, j) expression is with pixel (a, b)
The gray value of pixel (i, j) in c × c neighborhood at center, m (a, b) indicate c × c neighborhood centered on pixel (a, b)
The gray average of interior pixel.
Above embodiment of the present invention adopts and carries out binary conversion treatment to user's facial image in manner just described, right first
User's facial image carries out gray scale adjusting processing, the luminance difference in user's facial image can be effectively adjusted, so that user
The intensity profile of facial image is in maintenance level；Then treated user's facial image is adjusted to gray scale to carry out at binaryzation
Reason further removes the luminance information in image, can adapt to different background, brightness case, and strong robustness, stability is high, is
Subsequent image processing module 3 further carries out feature extraction to user's facial image and lays a good foundation.
In one embodiment, feature extraction unit 33 carry out feature to user's facial image after the binary conversion treatment
Parameter extraction, the characteristic parameter that will acquire are specifically included as second face characteristic information:
The Gradient Features for calculating pixel in binaryzation user facial image, wherein the customized Gradient Features function used
Are as follows:
In formula, J ' (a, b) indicates that the gray value of pixel (a, b) in binaryzation user facial image, L (a, b) indicate picture
The Gradient Features of vegetarian refreshments (a, b)；
Binaryzation user's facial image is divided into 8 × 8 pixel size cells, according to binaryzation user's face figure of acquisition
The Gradient Features of pixel calculate the Gradient Features histogram of all pixels point in each cell as in；
2 × 2 adjacent two-by-two cells are formed into a sub-block, Gradient Features corresponding to cells all in sub-block
Histogram cascade and it is normalized according to its L2 norm rule, obtains the normalized gradient feature of the sub-block
Histogram；
The normalized gradient feature histogram of all sub-blocks in binaryzation user's facial image is cascaded, form this two
The characteristic parameter of value user's facial image.
Above embodiment of the present invention carries out feature extraction to user's facial image after binary conversion treatment using aforesaid way
Processing, the gradient using each pixel in user's facial image after customized gray feature function extraction binary conversion treatment are special
Sign, is then divided into different cells for user's facial image after binary conversion treatment, and according to the gray scale of pixel in cell
The histogram of adjacent cells lattice is normalized to construct the histogram of sub-block for feature construction histogram, then simultaneously will
The histogram of all sub-blocks carries out cascading the characteristic parameter as user's facial image after binary conversion treatment, wherein in characteristic parameter
Dimension is higher, can accurately describe the feature of user's face, and recognition effect is good.
In the description of the present invention, term " first ", " second " etc. be only used for distinguish description, and should not be understood as instruction or
Imply relative importance.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as analysis, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (4)
1. a kind of machine solution locking device based on recognition of face characterized by comprising
The camera of installation on computers, for obtaining user images；
Database module, for establishing the database including the first face characteristic information；
Image processing module, the user images for obtaining to the camera are handled, to obtain the of the user images
Two face characteristic informations；
Judgment module, for judging that second face characteristic information is similar to the first face characteristic information described in database
Whether degree is greater than the threshold value of setting, and is greater than in the similarity of second face characteristic information and the first face characteristic information and sets
Unlock instruction is issued when fixed threshold value；
Unlocked state, for being unlocked according to the unlock instruction to the computer.
2. a kind of machine solution locking device based on recognition of face according to claim 1, which is characterized in that further include calling out
Awake module, for waking up the camera acquisition user images after receiving user instruction.
3. a kind of machine solution locking device based on recognition of face according to claim 1, described image processing module, packet
It includes:
Pretreatment unit, the user images for obtaining to the camera carry out enhancing denoising, obtain pretreated
User images；
Edge detection unit is partitioned into user's face for carrying out edge detection process to the pretreated user images
Image；
Feature extraction unit obtains user after the binary conversion treatment for carrying out binary conversion treatment to user's facial image
The characteristic parameter of facial image, using this feature parameter as second face characteristic information.
4. a kind of machine solution locking device based on recognition of face according to claim 1, the pretreatment unit are used for
The user images obtained to the camera carry out enhancing denoising, obtain pretreated user images, specifically include:
Initial phase initializes the number of iterations D=0, iteration step length Δ T, carries out at gray processing to the user images are received
Reason obtains user's gray level image and is denoted as A0
The iterative processing stage carries out enhancing processing to user's gray level image, wherein the custom images enhancing function used are as follows:
In formula, AD+1And ADUser's gray level image when D+1 and D iteration enhancing processing is respectively indicated, G indicates split window number,
Middle window size is z × z, and image size is a × b, then G=(a-z+1) × (b-z+1), CDIndicate that current time Second Order Partial is micro-
The tangential spread function of sub-model, whereinY(A(i)D)
Indicate normalization histogram when D iteration in the i-th window, K (i)maxWith K (i)minRespectively indicate the maximum ash in the i-th window
Angle value and minimum gradation value, Δ T indicate iteration step length, 0 < Δ T≤1, V1With the tangential smooth adjustment factor of expression, V2Indicate enhancing
Proportionality coefficient；UxAnd UyRespectively indicate the forwardly and rearwardly difference value of partial derivative, Uxx、Uxy、UyyRespectively indicate second-order partial differential coefficient
Finite-difference approximation value, R indicate regulatory factor,Indicate that image gradient vector, v indicate the edge regulatory factor of setting, S table
Show the gray scale impact factor of setting；
The judgement stage updates the number of iterations D=D+1, if the number of iterations is greater than the maximum number of iterations of setting, exports AD conduct
Pretreated user images；Otherwise, return processing stage is for further processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811528816.6A CN109508526A (en) | 2018-12-13 | 2018-12-13 | A kind of machine solution locking device based on recognition of face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811528816.6A CN109508526A (en) | 2018-12-13 | 2018-12-13 | A kind of machine solution locking device based on recognition of face |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109508526A true CN109508526A (en) | 2019-03-22 |
Family
ID=65753465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811528816.6A Withdrawn CN109508526A (en) | 2018-12-13 | 2018-12-13 | A kind of machine solution locking device based on recognition of face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109508526A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081383A (en) * | 2020-01-20 | 2020-04-28 | 罗晖 | Epidemic disease monitoring system based on cloud computing |
-
2018
- 2018-12-13 CN CN201811528816.6A patent/CN109508526A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081383A (en) * | 2020-01-20 | 2020-04-28 | 罗晖 | Epidemic disease monitoring system based on cloud computing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shi et al. | Normalised gamma transformation‐based contrast‐limited adaptive histogram equalisation with colour correction for sand–dust image enhancement | |
| CN105760859B (en) | Reticulate pattern facial image recognition method and device based on multitask convolutional neural networks | |
| Mahalakshmi et al. | Digital image forgery detection and estimation by exploring basic image manipulations | |
| WO2020233000A1 (en) | Facial recognition method and apparatus, and computer-readable storage medium | |
| JP2003317101A (en) | Method for verifying face using method for automatically updating database and system therefor | |
| CN102163283A (en) | Method for extracting face characteristic based on local three-value mode | |
| CN110909636B (en) | Face recognition method based on non-uniform distribution | |
| CN108537143B (en) | A kind of face identification method and system based on key area aspect ratio pair | |
| Tao et al. | Biometric authentication for a mobile personal device | |
| Wang et al. | Fusion of LDB and HOG for Face Recognition | |
| CN102867176B (en) | A kind of facial image method for normalizing | |
| Yuan | A system of clothes matching for visually impaired persons | |
| CN115512399A (en) | Face fusion attack detection method based on local features and lightweight network | |
| CN104217503A (en) | Self-service terminal identity identification method and corresponding house property certificate printing method | |
| CN109508526A (en) | A kind of machine solution locking device based on recognition of face | |
| CN113642003B (en) | Security detection method of face recognition system based on generation of highly robust adversarial samples | |
| Reddy et al. | Comparison of HOG and fisherfaces based face recognition system using MATLAB | |
| CN113743231B (en) | Video target detection avoidance system and method | |
| CN109446988A (en) | Face identification method | |
| Li et al. | Research of face detection based on skin color feature | |
| Wang et al. | Adaptive bright and dark channel combined with defogging algorithm based on depth of field | |
| Hongo et al. | Personal authentication with an iris image captured under visible-light condition | |
| CN115565210A (en) | A Lightweight Face Fusion Attack Detection Method Based on Feature Cascading | |
| Zhang et al. | Industrial Image Enhancement Method Based on Cloud Edge Fusion | |
| Wang et al. | Research on image feature extraction method fusing hog and canny algorithm |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190322 |