CN109508685A - Power communication dispatching method based on face recognition technology - Google Patents
Power communication dispatching method based on face recognition technology Download PDFInfo
- Publication number
- CN109508685A CN109508685A CN201811406000.6A CN201811406000A CN109508685A CN 109508685 A CN109508685 A CN 109508685A CN 201811406000 A CN201811406000 A CN 201811406000A CN 109508685 A CN109508685 A CN 109508685A
- Authority
- CN
- China
- Prior art keywords
- face
- facial image
- feature
- recognition technology
- face recognition
- 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
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/141—Systems for two-way working between two video terminals, e.g. videophone
Abstract
The present invention relates to communicating for power information technical fields, and in particular to a kind of power communication dispatching method based on face recognition technology.It is identified including skin detection Database and facial image, specific steps are as follows: acquisition facial image;The facial image that acquisition is handled using method for detecting human face, obtains Face pattern feature;Facial image is pre-processed according to the Face pattern feature;Feature extraction is carried out to pretreated facial image, carries out facial Feature Modeling;Facial Feature Modeling is concluded and is stored, and constructs the feature database comprising personage's essential information, obtains skin detection database;The characteristic of facial image to be identified is scanned for matching with skin detection database, when similarity is more than threshold value, output matching result.The seamless insertion face identification functions in existing scheduling system, by perfect database technology, for customization need identity information details to be shown, increase the convenience of communication, improve work efficiency.
Description
Technical field
The present invention relates to communicating for power information technical fields, and in particular to a kind of power communication based on face recognition technology
Dispatching method.
Background technique
Electric power dispatching system is only able to carry out common video calling and remote scheduling at present.It can not show that video is logical in time
Talk about the identity information of both sides.
Multiple mobile phone APP at present, the terminals such as bank self-help sales counter, which have, increases system safety using face recognition technology.From
Technical standpoint, this kind of soft/hard terminal are embedded into face recognition module in original terminal, and the function that recognition of face compares is increased
Energy.To provide new mode and thinking for secure authentication, expand original such as password, the secured fashions such as fingerprint.Simultaneously
Compensate for the technology drawback of original mode.The primary structure of its technology is the installation video human face identification function in original terminal,
And face verification is carried out by the face alignment algorithm that server is surveyed, to reach the effect for correctly identifying identity by facial image
Fruit.
Face recognition products be widely used to finance, the administration of justice, army, public security, frontier inspection, government, space flight, electric power, factory,
The fields such as education, medical treatment and numerous enterprises and institutions.With further mature and Social Agree the raising of technology, face is known
Other technology is applied in more fields.
1) enterprise, house safety and management.Such as recognition of face access control and attendance system, recognition of face security door etc..
2) E-Passport and identity card.The E-Passport plan Ministry of Public Security one of China is stepping up planning and implementation.
3) public security, the administration of justice and criminal investigation.Face identification system and network are such as utilized, tracks down and arrests runaway convict in China.
4) Self-Service.
5) information security.
Summary of the invention
The purpose of the present invention is to provide a kind of power communication dispatching method based on face recognition technology, it is above-mentioned to solve
Technical problem.Technical problem solved by the invention can be realized using following technical scheme:
Power communication dispatching method based on face recognition technology, including skin detection Database and face figure
As identification, specific steps are as follows:
Step 1) acquires facial image;
Step 2) obtains Face pattern feature using the facial image of method for detecting human face processing acquisition;
Step 3) pre-processes facial image according to the Face pattern feature;
Step 4) carries out feature extraction to pretreated facial image, carries out facial Feature Modeling;
Facial Feature Modeling is concluded and is stored by step 5), and constructs the feature database comprising personage's essential information, obtains face
Feature templates database;
The characteristic of facial image to be identified is scanned for matching by step 6) with skin detection database, works as phase
It is more than threshold value like degree, exports matching result, when similarity is lower than threshold value, matching result is not found in output.
Preferably, in the step 1) acquisition facial image include still image, dynamic image, different location image,
The image of different expressions.
Preferably, method for detecting human face uses Adaboost algorithm in the step 2).
Preferably, in the step 3) pretreatment include light compensation, it is greyscale transformation, histogram equalization, normalization, several
What correction, sharpens filtering.
Preferably, personage's essential information in the step 5) includes name, department, position, region within the jurisdiction.
Preferably, the step 1), step 2), step 3), step 4) be by power scheduling terminal processes, the step 5),
Step 6) is handled by central processing unit and is completed.
Preferably, the step 1) is by power scheduling terminal processes, the step 2), step 3), step 4), step 5),
Step 6) is handled by central processing unit and is completed.
Advantages of the present invention
The present invention seamless insertion face identification functions in existing scheduling system, and can by perfect database technology
To there is the customization being directed to need identity information details to be shown.To increase the convenience of communication, improve work efficiency.
Detailed description of the invention
Attached drawing 1 is local terminal embedded model figure in power communication dispatching method;
Attached drawing 2 is individual server end embedded model figure in power communication dispatching method.
Specific embodiment
Embodiment 1:
Power communication dispatching method mainly by including that skin detection Database and facial image identify, passes through
Following steps are realized:
The different facial image of step 1) man face image acquiring can be transferred through pick-up lens and collect, such as static map
It can be acquired well in terms of picture, dynamic image, different positions, different expressions, when user is in the bat of acquisition equipment
When taking the photograph in range, acquisition equipment can search for automatically and shoot the facial image of user.
The detection of step 2) facial image
Face datection is mainly used for the pretreatment of recognition of face in practice, i.e., accurate calibration goes out the position of face in the picture
It sets and size;The pattern feature very abundant for including in facial image, such as histogram feature, color characteristic, template characteristic, structure
Feature and Haar feature etc.;Face datection is exactly Face pattern feature useful among these to be picked out, and utilize these faces
Pattern feature realizes Face datection.
The method for detecting human face of the application is based on features above using Adaboost learning algorithm, and Adaboost algorithm is
A method of for classifying, it is combined some weaker classification methods, is combined into new very strong classification method;
Some rectangular characteristics (Weak Classifier) that can most represent face are picked out using Adaboost algorithm during Face datection, according to
Weak Classifier is configured to a strong classifier by the mode of Nearest Neighbor with Weighted Voting, then several strong classifiers that training obtains are composed in series
The cascade filtering of one cascade structure effectively improves the detection speed of classifier.
So-called Weak Classifier is exactly by the rectangular characteristic after facial image pixelation, is the technology of Computer Image Processing
Noun, can illustrate understanding are as follows: the length accounting of nose in face, nose wing of nose both ends width accounting, the relevant data of nose
Constitute the Weak Classifier of nose;And the strong classifier and cascade filtering of weighting and series system composition will be it is to be understood that will
The each Weak Classifier of nose, eyes, mouth, which is put together, to be considered to analyze obtained more comprehensive feature.
The pretreatment of step 3) facial image
Image preprocessing for face is based on Face datection as a result, carrying out processing to image and finally serving feature
The process of extraction;The original image that system obtains tends not to directly make due to being limited by various conditions and random disturbances
With, it is necessary to gray correction, noise filtering image preprocessing are carried out to it in the early stage of image procossing.
For the facial image in the application, preprocessing process mainly includes the light compensation of facial image, ash
Spend transformation, histogram equalization, normalization, geometric correction, filtering and sharpening.
Step 4) facial image feature extraction
Feature workable for face identification system is generally divided into visual signature, pixels statistics feature, facial image transformation series
Number feature, facial image algebraic characteristic;Face characteristic extraction is carried out aiming at certain features of face;Face characteristic mentions
It takes, also referred to as face characterizes, it is the process that feature modeling is carried out to face;The method that face characteristic extracts, which is summed up, is divided into two
Major class: one is Knowledge based engineering characterizing methods;Another is the characterizing method based on algebraic characteristic or statistical learning.
Knowledge based engineering characterizing method mainly according to the shape description of human face and they the distance between characteristic
The characteristic for facilitating face classification is obtained, characteristic component generally includes Euclidean distance, curvature and angle between characteristic point
Degree;Face is locally made of eyes, nose, mouth, chin, can to these local and structural relation between them geometric descriptions
As the important feature of identification face, these features are referred to as geometrical characteristic;Knowledge based engineering face characterization mainly includes being based on
The method and template matching method of geometrical characteristic.
The application uses Knowledge based engineering characterization method, and extracted characteristic type all relates to, and each characteristic type can
Above Weak Classifier is formed, various features type, which combines, to be judged.
Step 5) face template property data base is established
Extracted facial Feature Modeling is subjected to the conclusion storage as unit of personage, and big data technology is combined to construct
Skin detection database comprising who object items essential information;In this, as comparison, inquiry, the basis for retrieving work
Database.
These information are inputted according to user itself, such as name, department, position, and region within the jurisdiction personnel believe substantially
Breath.
The matching of step 6) face and identification
The skin detection stored in the characteristic of the facial image of extraction and database scans for matching, and passes through
A threshold value is set, when similarity is more than this threshold value, then result matching obtained exports.
Parameter when threshold value is System Programming, without concrete meaning;Selected numerical value is matched face as needed
Total quantity and the matching result correctness of actual test phase are adjusted in real time;When similarity is lower than threshold value, system is indicated
It face characteristic library can not matched face;That is, that be compared is a new person this moment, system can prompt not find matching knot
Fruit, this prompt, which can according to need, is voluntarily inputted setting by system manager;If actual conditions are not new person, this situation probability
It is extremely low, it needs to adjust system parameter;It if it is new person, then needs to acquire the face information of this person, and is entered into face characteristic
Library;This step is it is understood that allow computer to recognize and remember this new person, the i.e. letter of exportable new person in compare next time
Breath.
Recognition of face is exactly to be compared face characteristic to be identified with obtained skin detection, according to similar
Degree judges the identity information of face;This process is divided into two classes again: one kind is confirmation, is one-to-one progress image ratio
Compared with process, it is another kind of be identification, be it is one-to-many carry out images match comparison process.
According to the use scale of practical electric power dispatching system, the application devises two kinds of terminal embedded models:
1) local terminal embedded model, such as Fig. 1:
Face recognition module is respectively embedded in each power scheduling terminal;Identification is responsible for by power scheduling terminal, and
Identification and inquiry content are called and shown into central processing unit according to result.
Advantage: the extra duty that central processing unit generates is minimum;The identification and processing of image are all whole in local power scheduling
End is completed, and additional real time picture information transmission is not needed;Therefore, network data load can also be ignored substantially.
Disadvantage: because each power scheduling terminal requires the module of load face identification functions, early period lays and software
The disposable cost of labor of upgrading is higher.
2) individual server end embedded model, such as Fig. 2:
Face picture is only acquired from power scheduling terminal and is sent to central processing unit, is known in central processing unit comprising face
Other server and database call from the unified identification of central processing unit and into database corresponding information according to result;Later by
Central processing unit sends recognition result to power scheduling terminal and shows content accordingly.
Advantage: it to existing net electric power dispatching system terminal substantially without add-on module and content, needs to establish and know comprising face
The central processing unit of other server, corresponding disposable cost of labor are extremely low.
Disadvantage: larger to network transmission loading effects since all image datas are all by electric power dispatching system network transmission;
Simultaneously because central server uniformly carries out identification calculating, when identification peak phase, to central server system configuration requirement compared with
Height, and there is synchronous calculation processing number bottleneck, to influence recognition efficiency.
Claims (7)
1. the power communication dispatching method based on face recognition technology, it is characterised in that: built including skin detection database
The identification of vertical and facial image, specific steps are as follows:
Step 1) acquires facial image;
Step 2) obtains Face pattern feature using the facial image of method for detecting human face processing acquisition;
Step 3) pre-processes facial image according to the Face pattern feature;
Step 4) carries out feature extraction to pretreated facial image, carries out facial Feature Modeling;
Facial Feature Modeling is concluded and is stored by step 5), and constructs the feature database comprising personage's essential information, obtains face characteristic
Template database;
The characteristic of facial image to be identified is scanned for matching by step 6) with skin detection database, works as similarity
More than threshold value, matching result is exported, when similarity is lower than threshold value, matching result is not found in output.
2. the power communication according to claim 1 based on face recognition technology dispatches system, it is characterised in that: the step
It is rapid 1) in acquisition facial image include still image, dynamic image, the image of different location, different expression image.
3. the power communication according to claim 1 based on face recognition technology dispatches system, it is characterised in that: the step
It is rapid 2) in method for detecting human face use Adaboost algorithm.
4. the power communication according to claim 1 based on face recognition technology dispatches system, it is characterised in that: the step
Rapid 3) middle pretreatment includes light compensation, greyscale transformation, histogram equalization, normalization, geometric correction, filtering, sharpening.
5. the power communication according to claim 1 based on face recognition technology dispatches system, it is characterised in that: the step
It is rapid 5) in personage's essential information include name, department, position, region within the jurisdiction.
6. the power communication according to claim 1 based on face recognition technology dispatches system, it is characterised in that: the step
It is rapid 1), step 2), step 3), step 4) by power scheduling terminal processes, the step 5), step 6) are handled by central processing unit
It completes.
7. the power communication according to claim 1 based on face recognition technology dispatches system, it is characterised in that: the step
It is rapid 1) by power scheduling terminal processes, the step 2), step 3), step 4), step 5), step 6) are handled by central processing unit
It completes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811406000.6A CN109508685A (en) | 2018-11-23 | 2018-11-23 | Power communication dispatching method based on face recognition technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811406000.6A CN109508685A (en) | 2018-11-23 | 2018-11-23 | Power communication dispatching method based on face recognition technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109508685A true CN109508685A (en) | 2019-03-22 |
Family
ID=65750340
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811406000.6A Pending CN109508685A (en) | 2018-11-23 | 2018-11-23 | Power communication dispatching method based on face recognition technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109508685A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111598867A (en) * | 2020-05-14 | 2020-08-28 | 国家卫生健康委科学技术研究所 | Method, apparatus, and computer-readable storage medium for detecting specific facial syndrome |
CN113128334A (en) * | 2021-03-03 | 2021-07-16 | 广州朗国电子科技有限公司 | AI intelligent image recognition method, electronic equipment and storage medium |
CN115037560A (en) * | 2022-08-10 | 2022-09-09 | 广州海普网络科技有限公司 | Information technology safety communication method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101276408A (en) * | 2008-04-24 | 2008-10-01 | 长春供电公司 | Method for recognizing human face based on electrical power system network safety |
CN105022994A (en) * | 2015-06-30 | 2015-11-04 | 国网山东省电力公司日照供电公司 | Identity authentication method of network safety access of power system |
CN105095715A (en) * | 2015-06-30 | 2015-11-25 | 国网山东莒县供电公司 | Identity authentication method of electric power system network |
CN105184238A (en) * | 2015-08-26 | 2015-12-23 | 广西小草信息产业有限责任公司 | Human face recognition method and system |
US20160307027A1 (en) * | 2015-01-12 | 2016-10-20 | Yutou Technology (Hangzhou) Co., Ltd. | A system and a method for image recognition |
CN107967458A (en) * | 2017-12-06 | 2018-04-27 | 宁波亿拍客网络科技有限公司 | A kind of face identification method |
CN107977439A (en) * | 2017-12-07 | 2018-05-01 | 宁波亿拍客网络科技有限公司 | A kind of facial image base construction method |
CN108162915A (en) * | 2017-12-25 | 2018-06-15 | 四川长虹电器股份有限公司 | Vehicle-mounted middle control personalized configuration system based on recognition of face |
-
2018
- 2018-11-23 CN CN201811406000.6A patent/CN109508685A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101276408A (en) * | 2008-04-24 | 2008-10-01 | 长春供电公司 | Method for recognizing human face based on electrical power system network safety |
US20160307027A1 (en) * | 2015-01-12 | 2016-10-20 | Yutou Technology (Hangzhou) Co., Ltd. | A system and a method for image recognition |
CN105022994A (en) * | 2015-06-30 | 2015-11-04 | 国网山东省电力公司日照供电公司 | Identity authentication method of network safety access of power system |
CN105095715A (en) * | 2015-06-30 | 2015-11-25 | 国网山东莒县供电公司 | Identity authentication method of electric power system network |
CN105184238A (en) * | 2015-08-26 | 2015-12-23 | 广西小草信息产业有限责任公司 | Human face recognition method and system |
CN107967458A (en) * | 2017-12-06 | 2018-04-27 | 宁波亿拍客网络科技有限公司 | A kind of face identification method |
CN107977439A (en) * | 2017-12-07 | 2018-05-01 | 宁波亿拍客网络科技有限公司 | A kind of facial image base construction method |
CN108162915A (en) * | 2017-12-25 | 2018-06-15 | 四川长虹电器股份有限公司 | Vehicle-mounted middle control personalized configuration system based on recognition of face |
Non-Patent Citations (1)
Title |
---|
陈亚芳 等: "调度自动化访问安全控制系统", 《电力信息化》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111598867A (en) * | 2020-05-14 | 2020-08-28 | 国家卫生健康委科学技术研究所 | Method, apparatus, and computer-readable storage medium for detecting specific facial syndrome |
CN113128334A (en) * | 2021-03-03 | 2021-07-16 | 广州朗国电子科技有限公司 | AI intelligent image recognition method, electronic equipment and storage medium |
CN115037560A (en) * | 2022-08-10 | 2022-09-09 | 广州海普网络科技有限公司 | Information technology safety communication method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106650693A (en) | Multi-feature fusion identification algorithm used for human face comparison | |
CN104700094B (en) | A kind of face identification method for intelligent robot and system | |
CN109359548A (en) | Plurality of human faces identifies monitoring method and device, electronic equipment and storage medium | |
CN108009482A (en) | One kind improves recognition of face efficiency method | |
CN109508685A (en) | Power communication dispatching method based on face recognition technology | |
CN104183029A (en) | Portable quick crowd attendance method | |
CN107833306A (en) | The intelligent check class attendance system of face and iris feature fusion recognition | |
Kiran et al. | Pca based facial recognition for attendance system | |
CN110443181A (en) | Face identification method and device | |
CN204143555U (en) | The Certificate of House Property printing terminal of identification self-aided terminal and correspondence | |
CN104217503A (en) | Self-service terminal identity identification method and corresponding house property certificate printing method | |
CN105184236A (en) | Robot-based face identification system | |
Menezes et al. | Automatic attendance management system based on deep one-shot learning | |
CN104217504A (en) | Identity recognition self-service terminal and corresponding certificate of house property printing terminal | |
CN114218543A (en) | Encryption and unlocking system and method based on multi-scene expression recognition | |
Baytamouny et al. | AI-based home security system with face recognition | |
Murugan et al. | Fragmented iris recognition system using BPNN | |
Rosy et al. | An enhanced intelligent attendance management system for smart campus | |
CN109359579A (en) | A kind of face identification system based on machine deep learning algorithm | |
Kandan et al. | Smart voting system using face detection and recognition algorithms | |
CN114065163A (en) | Display mainboard and terminal with face identification and identity verification functions | |
Charishma et al. | Smart Attendance System with and Without Mask using Face Recognition | |
Devi et al. | Attendance Management System using Face Recognition | |
Liashenko et al. | Investigation of the influence of image quality on the work of biometric authentication methods | |
Marutotamtama et al. | Face Recognition and Face Spoofing Detector for Attendance System |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190322 |
|
WD01 | Invention patent application deemed withdrawn after publication |