CN104915590A - Human face recognition system and method applied to computer encryption - Google Patents
Human face recognition system and method applied to computer encryption Download PDFInfo
- Publication number
- CN104915590A CN104915590A CN201510385118.5A CN201510385118A CN104915590A CN 104915590 A CN104915590 A CN 104915590A CN 201510385118 A CN201510385118 A CN 201510385118A CN 104915590 A CN104915590 A CN 104915590A
- Authority
- CN
- China
- Prior art keywords
- module
- face
- image
- picture quality
- human 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.)
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/70—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
- G06F21/81—Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer by operating on the power supply, e.g. enabling or disabling power-on, sleep or resume operations
-
- 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
Abstract
The present invention discloses a human face recognition system and human face recognition method applied to computer encryption. The human face recognition system applied to the computer encryption comprises an image acquisition module, an image quality judgment module, an image code generation module, a storage module, a human face identification module and a display screen, all of which are sequentially connected; the image acquisition module is connected with a real person identification module; the real person identification module is connected with the display screen; the image quality judgment module is connected with an image quality regulation module; and the image code generation module is an image code generation module based on elastic bundle drawing matching. An image code generation process comprises the steps of: establishing a human face shape model; aligning calibrated human face images; and extracting expression characteristics of a human face by utilizing Gabor wavelet transform. The image code generation module is based on an elastic bundle image matching technology, can resist the changes of light rays, facial expressions and posture actions, and has higher applicability. Furthermore, the real person identification module is used for recognizing whether the human face image belongs to a real person or not, so that the reliability is improved.
Description
Technical field
The present invention relates to a kind of computer encipher system and encryption method, particularly relate to a kind of recognition of face encryption system for computing machine and face identification method thereof.
Background technology
Along with progress and the socioeconomic development of science and technology, computing machine has been widely used in the every field of work, study, life, as one of instrument that modern society is indispensable, usually various important personal information is store in computing machine, once generation information leakage, all immeasurable loss will be caused to the work of computing machine holder, studying and living.Therefore, the encryption of computing machine is most important to guarantee personal information security.
Traditional computer encipher technology mainly relies on keyboard password to encrypt, and this encryption technology exists keyboard password and is easily stolen, or cannot open the defect of computing machine when user forgets Password, both dumb also dangerous.The appearance of fingerprint recognition encryption technology improves cryptographic security, but fingerprint recognition is contact, user needs to contact with the fingerprint collecting district of computing machine just can carry out fingerprint recognition, easily fingerprint capturer polluted and damage, and the fingerprint collecting time is also longer, cause computer booting to slow, use very inconvenient.In addition, fingerprint characteristic is static, and along with the progress of science and technology, fingerprint can be extracted, copy and reverse mould, and this makes fingerprint recognition encryption technology still there is potential safety hazard, can not meet the user demand of present stage.
Relative to fingerprint recognition encryption technology, face recognition technology has more reliable security, be the focus of research at present, played important effect in fields such as banking system, entrance guard's supervisory system, intelligent anti-theft door systems, but be used in the also rare of computer encipher field.Existing face identification method has following several: a kind of is face identification method based on geometric properties, this geometric properties can be the shape of eye, nose, mouth etc. and the geometric relationship between them, such as distance each other, this recognition methods speed is fast, the internal memory needed is little, but discrimination is lower; A kind of is face identification method based on gray level image, this method places one's entire reliance upon the statistical property of face gray level image, not only need in Sample Storehouse, to store a large amount of training samples in advance, and recognition effect is bad when illumination condition, attitude or expression change; Another kind is the face identification method based on neural network, the input of neural network can be the facial image of low resolution, regional area or local grain, this method has good dirigibility, but same need a large amount of training samples, its application in computer encipher field is restricted.
Summary of the invention
The object of the invention is for deficiency of the prior art, a kind of recognition of face encryption system for computing machine and face identification method thereof are provided, not only can differentiate that caught facial image is static photo or true man, can also when illumination condition, facial expression or or attitude action changes keep higher discrimination, improve reliability and the dirigibility of encryption system of the present invention on the one hand, do not need to take a large amount of internal memories on the other hand, cause too large impact can not to computer booting speed.
In order to realize foregoing invention object, the present invention takes following technical scheme:
A kind of recognition of face encryption system for computing machine, comprise the image capture module, picture quality judge module, Image Coding generation module, memory module, face recognition module and the display screen that connect successively, described image capture module is connected with true man's identification module, described true man's identification module is also connected with display screen, described picture quality judge module is connected with picture quality adjusting module, described Image Coding generation module is the Image Coding generation module based on elastic bunch graph coupling, and the process of its synthetic image coding is: a. sets up face shape model; The facial image alignment of b. will demarcate; C. Gabor wavelet conversion is used to extract the expressive features of face.
Preferably, the described process setting up face shape model is: by marking the coordinate of the face feature point of facial image, using it as primary data, and the coordinate of multiple face feature point is mutually corresponding, then sets up face shape model by principal component analysis (PCA).
Preferably, described process of being alignd by the facial image of demarcation is: choose a shape vector as initial sample, that other vector and initial sample are carried out on shape vector is mutual corresponding, average shape vector is obtained after calculating, carry out normalization process again, and as sample, then by with initial sample mutual corresponding after shape vector mutual corresponding with described average shape vector, repeat this process, until the difference of the average shape vector of adjacent twice is less than predetermined value.
Preferably, the process that the expressive features of face is extracted in described use Gabor wavelet conversion is: by using the calculating of Gabor wavelet kernel function and sampling, thus obtain the meticulous location of the face feature point of the unique point of a different set of frequency and phase place.
The face identification method of the described computer encipher system based on face recognition technology, comprises the steps: to press computer power supply, starts image capture module; Image capture module detects the position of face from external environment condition, is separated by face from external environment condition, and real-time Transmission is to true man's identification module; Whether true man's identification module is that true man differentiate to the face detected, if identification result is true man, then identification result is fed back to image capture module, image capture module converts the face detected to facial image and transfers to picture quality judge module, if testing result is not true man, then identification result is fed back to display screen, show recognition of face failure on a display screen, shut down computer subsequently; Picture quality judge module judges whether captured quality of human face image reaches predetermined standard, if reach predetermined standard, is directly sent to Image Coding generation module, if do not reach predetermined standard, is sent to picture quality adjusting module and adjusts; The quality of picture quality adjusting module to the facial image not reaching preassigned adjusts, and the facial image after adjustment is fed back to picture quality judge module, if the quality of the facial image after adjustment reaches predetermined standard, then by picture quality judge module, the facial image after adjustment is sent to Image Coding generation module, if the quality of the facial image after adjustment does not still reach predetermined standard, then send instruction by picture quality judge module to image capture module, re-start image acquisition; Image Coding generation module extracts the face characteristic reached in the facial image of preassigned, and the face characteristic extracted is converted to face line coding, if be encrypted operation to computing machine, then complete ciphering process by Image Coding generation module by this face line code storage to memory module, if carry out computer booting operation after encryption, then by Image Coding generation module, this face line coding is sent to face recognition module; The face line prestored in the face line received coding and memory module is encoded and is carried out contrast and identify by face recognition module, and comparing result is fed back to display screen with the numeric form of similarity, if the numerical value of similarity is more than preset value, then show recognition of face success on a display screen, open computing machine subsequently, if the numerical value of similarity is less than preset value, then shows recognition of face failure on a display screen, shut down computer subsequently.
Preferably, the preset value of described similarity is more than 80%.
The present invention has following beneficial effect:
(1) contactless face recognition technology is applied to computer encipher by the present invention, and relative to fingerprint identification technology, the present invention does not need to contact with image capture module, avoids pollution and the damage of image capture module.
(2) whether the present invention is that true man differentiate by true man's identification module to the facial image in external environment condition, has stopped the possibility using still photo, has improve the reliability of encryption system of the present invention.
(3) the present invention adopts the Image Coding generation module based on elastic bunch graph coupling to generate face line coding, and this line coding can resist the change of light, skin color, facial hair, hair style, glasses, expression and attitude, has stronger applicability.
accompanying drawing illustrates:
Fig. 1 is the principle of work schematic diagram of the computer encipher system based on face recognition technology of the present invention.
embodiment:
As shown in Figure 1, computer encipher system based on face recognition technology of the present invention comprises the image capture module connected successively, picture quality judge module, Image Coding generation module, memory module, face recognition module and display screen, described image capture module is connected with true man's identification module, described true man's identification module is also connected with display screen, described picture quality judge module is connected with picture quality adjusting module, described Image Coding generation module is the Image Coding generation module based on elastic bunch graph coupling, the process of its synthetic image coding is: a. sets up face shape model, by marking the coordinate of the face feature point of facial image, using it as primary data, and the coordinate of multiple face feature point is mutually corresponding, face shape model is set up again by principal component analysis (PCA), the facial image alignment of b. will demarcate, choose a shape vector as initial sample, that other vector and initial sample are carried out on shape vector is mutual corresponding, average shape vector is obtained after calculating, carry out normalization process again, and as sample, then by with initial sample mutual corresponding after shape vector mutual corresponding with described average shape vector, repeat this process, until the difference of the average shape vector of adjacent twice is less than predetermined value, c. use Gabor wavelet conversion to extract the expressive features of face, by using the calculating of Gabor wavelet kernel function and sampling, thus obtain the meticulous location of the face feature point of the unique point of a different set of frequency and phase place.
As shown in Figure 1, the principle of work of the computer encipher system based on face recognition technology of the present invention is: press computer power supply, starts image capture module; Image capture module detects the position of face from external environment condition, is separated by face from external environment condition, and real-time Transmission is to true man's identification module; Whether true man's identification module is that true man differentiate to the face detected, if identification result is true man, then identification result is fed back to image capture module, image capture module converts the face detected to facial image and transfers to picture quality judge module, if testing result is not true man, then identification result is fed back to display screen, show recognition of face failure on a display screen, shut down computer subsequently; Picture quality judge module judges whether captured quality of human face image reaches predetermined standard, if reach predetermined standard, is directly sent to Image Coding generation module, if do not reach predetermined standard, is sent to picture quality adjusting module and adjusts; The quality of picture quality adjusting module to the facial image not reaching preassigned adjusts, and the facial image after adjustment is fed back to picture quality judge module, if the quality of the facial image after adjustment reaches predetermined standard, then by picture quality judge module, the facial image after adjustment is sent to Image Coding generation module, if the quality of the facial image after adjustment does not still reach predetermined standard, then send instruction by picture quality judge module to image capture module, re-start image acquisition; Image Coding generation module extracts the face characteristic reached in the facial image of preassigned, and the face characteristic extracted is converted to face line coding, if be encrypted operation to computing machine, then complete ciphering process by Image Coding generation module by this face line code storage to memory module, if carry out computer booting operation after encryption, then by Image Coding generation module, this face line coding is sent to face recognition module; The face line prestored in the face line received coding and memory module is encoded and is carried out contrast and identify by face recognition module, and comparing result is fed back to display screen with the numeric form of similarity, if the numerical value of similarity is more than 80%, then show recognition of face success on a display screen, open computing machine subsequently, if the numerical value of similarity is less than 80%, then shows recognition of face failure on a display screen, shut down computer subsequently.
The explanation of above example just understands core concept of the present invention for helping; Meanwhile, for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (6)
1. the face identification system for computer encipher, it is characterized in that, comprise the image capture module connected successively, picture quality judge module, Image Coding generation module, memory module, face recognition module and display screen, described image capture module is connected with true man's identification module, described true man's identification module is also connected with display screen, described picture quality judge module is connected with picture quality adjusting module, described Image Coding generation module is the Image Coding generation module based on elastic bunch graph coupling, the process of its synthetic image coding is: a. sets up face shape model, the facial image alignment of b. will demarcate, c. Gabor wavelet conversion is used to extract the expressive features of face.
2. as claimed in claim 1 for the face identification system of computer encipher, it is characterized in that, the described process setting up face shape model is: by marking the coordinate of the face feature point of facial image, using it as primary data, and the coordinate of multiple face feature point is mutually corresponding, then set up face shape model by principal component analysis (PCA).
3. as claimed in claim 1 for the face identification system of computer encipher, it is characterized in that, described process of being alignd by the facial image of demarcation is: choose a shape vector as initial sample, that other vector and initial sample are carried out on shape vector is mutual corresponding, average shape vector is obtained after calculating, carry out normalization process again, and as sample, again by with initial sample mutual corresponding after shape vector mutually corresponding with described average shape vector, repeat this process, until the difference of the average shape vector of adjacent twice is less than predetermined value.
4. as claimed in claim 1 for the face identification system of computer encipher, it is characterized in that, the process that the expressive features of face is extracted in described use Gabor wavelet conversion is: by using the calculating of Gabor wavelet kernel function and sampling, thus obtain the meticulous location of the face feature point of the unique point of a different set of frequency and phase place.
5. as claimed in claim 1 for a face identification method for the face identification system of computer encipher, it is characterized in that, comprise the steps: to press computer power supply, start image capture module; Image capture module detects the position of face from external environment condition, is separated by face from external environment condition, and real-time Transmission is to true man's identification module; Whether true man's identification module is that true man differentiate to the face detected, if identification result is true man, then identification result is fed back to image capture module, image capture module converts the face detected to facial image and transfers to picture quality judge module, if testing result is not true man, then identification result is fed back to display screen, show recognition of face failure on a display screen, shut down computer subsequently; Picture quality judge module judges whether captured quality of human face image reaches predetermined standard, if reach predetermined standard, is directly sent to Image Coding generation module, if do not reach predetermined standard, is sent to picture quality adjusting module and adjusts; The quality of picture quality adjusting module to the facial image not reaching preassigned adjusts, and the facial image after adjustment is fed back to picture quality judge module, if the quality of the facial image after adjustment reaches predetermined standard, then by picture quality judge module, the facial image after adjustment is sent to Image Coding generation module, if the quality of the facial image after adjustment does not still reach predetermined standard, then send instruction by picture quality judge module to image capture module, re-start image acquisition; Image Coding generation module extracts the face characteristic reached in the facial image of preassigned, and the face characteristic extracted is converted to face line coding, if be encrypted operation to computing machine, then complete ciphering process by Image Coding generation module by this face line code storage to memory module, if carry out computer booting operation after encryption, then by Image Coding generation module, this face line coding is sent to face recognition module; The face line prestored in the face line received coding and memory module is encoded and is carried out contrast and identify by face recognition module, and comparing result is fed back to display screen with the numeric form of similarity, if the numerical value of similarity is more than preset value, then show recognition of face success on a display screen, open computing machine subsequently, if the numerical value of similarity is less than preset value, then shows recognition of face failure on a display screen, shut down computer subsequently.
6., as claimed in claim 5 for the face identification method of the face identification system of computer encipher, it is characterized in that, the preset value of described similarity is more than 80%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510385118.5A CN104915590A (en) | 2015-07-05 | 2015-07-05 | Human face recognition system and method applied to computer encryption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510385118.5A CN104915590A (en) | 2015-07-05 | 2015-07-05 | Human face recognition system and method applied to computer encryption |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104915590A true CN104915590A (en) | 2015-09-16 |
Family
ID=54084652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510385118.5A Pending CN104915590A (en) | 2015-07-05 | 2015-07-05 | Human face recognition system and method applied to computer encryption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104915590A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704806A (en) * | 2017-09-01 | 2018-02-16 | 深圳市唯特视科技有限公司 | A kind of method that quality of human face image prediction is carried out based on depth convolutional neural networks |
| CN109347620A (en) * | 2018-08-10 | 2019-02-15 | 深圳前海微众银行股份有限公司 | Sample alignment schemes, system and computer readable storage medium |
| CN110367932A (en) * | 2019-07-11 | 2019-10-25 | 福州数据技术研究院有限公司 | Tongue based on Android handheld terminal and built-in terminal is as acquisition system and its method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101393598A (en) * | 2007-09-21 | 2009-03-25 | 希姆通信息技术（上海）有限公司 | Starting and unblock method decided by human face identification by utilizing mobile phone cam |
| CN201667042U (en) * | 2009-07-22 | 2010-12-08 | 东莞慧盈塑胶有限公司 | Notebook computer with face detection function |
| CN103678984A (en) * | 2013-12-20 | 2014-03-26 | 湖北微模式科技发展有限公司 | Method for achieving user authentication by utilizing camera |
| CN104182669A (en) * | 2013-05-21 | 2014-12-03 | 鸿富锦精密工业（深圳）有限公司 | Mobile terminal starting system and mobile terminal starting method |
| CN104750168A (en) * | 2013-12-25 | 2015-07-01 | 陕西平杰科工贸有限公司 | All-in-one personal computer with face recognition function |
-
2015
- 2015-07-05 CN CN201510385118.5A patent/CN104915590A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101393598A (en) * | 2007-09-21 | 2009-03-25 | 希姆通信息技术（上海）有限公司 | Starting and unblock method decided by human face identification by utilizing mobile phone cam |
| CN201667042U (en) * | 2009-07-22 | 2010-12-08 | 东莞慧盈塑胶有限公司 | Notebook computer with face detection function |
| CN104182669A (en) * | 2013-05-21 | 2014-12-03 | 鸿富锦精密工业（深圳）有限公司 | Mobile terminal starting system and mobile terminal starting method |
| CN103678984A (en) * | 2013-12-20 | 2014-03-26 | 湖北微模式科技发展有限公司 | Method for achieving user authentication by utilizing camera |
| CN104750168A (en) * | 2013-12-25 | 2015-07-01 | 陕西平杰科工贸有限公司 | All-in-one personal computer with face recognition function |
Non-Patent Citations (1)
| Title |
|---|
| 章毓晋: "《基于子空间的人脸识别》", 30 December 2009 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704806A (en) * | 2017-09-01 | 2018-02-16 | 深圳市唯特视科技有限公司 | A kind of method that quality of human face image prediction is carried out based on depth convolutional neural networks |
| CN109347620A (en) * | 2018-08-10 | 2019-02-15 | 深圳前海微众银行股份有限公司 | Sample alignment schemes, system and computer readable storage medium |
| CN110367932A (en) * | 2019-07-11 | 2019-10-25 | 福州数据技术研究院有限公司 | Tongue based on Android handheld terminal and built-in terminal is as acquisition system and its method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fathy et al. | Face-based active authentication on mobile devices | |
| CN103914686B (en) | A kind of face alignment authentication method and system shone based on certificate photo with collection | |
| CN104751040A (en) | Fingerprint detection method based on intelligent mobile information equipment | |
| CN103902979B (en) | A kind of face characteristic is extracted and sorting technique | |
| CN103886283A (en) | Method for fusing multi-biometric image information for mobile user and application thereof | |
| CN104751113A (en) | Fingerprint recognition method based on intelligent mobile information device | |
| CN107480586B (en) | Face characteristic point displacement-based biometric photo counterfeit attack detection method | |
| Lai et al. | Towards gesture-based user authentication | |
| CN108074303A (en) | A kind of scheme that can expand recognition of face number of users | |
| Paul et al. | Extraction of facial feature points using cumulative histogram | |
| CN110599187A (en) | Payment method and device based on face recognition, computer equipment and storage medium | |
| Meenakshi | Real-Time Facial Recognition System—Design, Implementation and Validation | |
| CN204143555U (en) | The Certificate of House Property printing terminal of identification self-aided terminal and correspondence | |
| CN104915590A (en) | Human face recognition system and method applied to computer encryption | |
| CN201698456U (en) | Real-time face detecting and recognizing device | |
| CN105184236A (en) | Robot-based face identification system | |
| CN205644823U (en) | Social security self -service terminal device | |
| CN104217504A (en) | Identity recognition self-service terminal and corresponding certificate of house property printing terminal | |
| Dhruva et al. | Novel algorithm for image processing based hand gesture recognition and its application in security | |
| Deng et al. | Attention-aware dual-stream network for multimodal face anti-spoofing | |
| KR20080073598A (en) | Method of real time face recognition, and the apparatus thereof | |
| KR20160042646A (en) | Method of Recognizing Faces | |
| CN101739571A (en) | Block principal component analysis-based device for confirming face | |
| Sharma et al. | Face recognition using haar cascade and local binary pattern histogram in opencv | |
| CN111428670B (en) | Face detection method, face detection device, storage medium and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150916 |