CN107967660B - Automatic facial recognition's safe examination system - Google Patents
Automatic facial recognition's safe examination system Download PDFInfo
- Publication number
- CN107967660B CN107967660B CN201711175592.0A CN201711175592A CN107967660B CN 107967660 B CN107967660 B CN 107967660B CN 201711175592 A CN201711175592 A CN 201711175592A CN 107967660 B CN107967660 B CN 107967660B
- Authority
- CN
- China
- Prior art keywords
- examinee
- examination
- subject group
- image
- information
- 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.)
- Active
Links
- 230000001815 facial effect Effects 0.000 title claims abstract description 59
- 238000012360 testing method Methods 0.000 claims abstract description 59
- 238000012544 monitoring process Methods 0.000 claims abstract description 35
- 238000004891 communication Methods 0.000 claims abstract description 6
- 230000004069 differentiation Effects 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 37
- 210000000056 organ Anatomy 0.000 claims description 21
- 239000013598 vector Substances 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 7
- 238000013523 data management Methods 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 238000009827 uniform distribution Methods 0.000 claims 2
- 238000005315 distribution function Methods 0.000 claims 1
- 238000012986 modification Methods 0.000 claims 1
- 230000004048 modification Effects 0.000 claims 1
- 238000012549 training Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 12
- 239000000126 substance Substances 0.000 description 12
- 238000002474 experimental method Methods 0.000 description 8
- 238000011160 research Methods 0.000 description 7
- KRHYYFGTRYWZRS-UHFFFAOYSA-N Fluorane Chemical compound F KRHYYFGTRYWZRS-UHFFFAOYSA-N 0.000 description 6
- QAOWNCQODCNURD-UHFFFAOYSA-N Sulfuric acid Chemical compound OS(O)(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-N 0.000 description 6
- 238000007689 inspection Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- HJTAZXHBEBIQQX-UHFFFAOYSA-N 1,5-bis(chloromethyl)naphthalene Chemical compound C1=CC=C2C(CCl)=CC=CC2=C1CCl HJTAZXHBEBIQQX-UHFFFAOYSA-N 0.000 description 3
- 238000010171 animal model Methods 0.000 description 3
- GOLCXWYRSKYTSP-UHFFFAOYSA-N arsenic trioxide Inorganic materials O1[As]2O[As]1O2 GOLCXWYRSKYTSP-UHFFFAOYSA-N 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 244000000010 microbial pathogen Species 0.000 description 3
- 244000045947 parasite Species 0.000 description 3
- NNFCIKHAZHQZJG-UHFFFAOYSA-N potassium cyanide Chemical compound [K+].N#[C-] NNFCIKHAZHQZJG-UHFFFAOYSA-N 0.000 description 3
- VQTUBCCKSQIDNK-UHFFFAOYSA-N Isobutene Chemical compound CC(C)=C VQTUBCCKSQIDNK-UHFFFAOYSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000383 hazardous chemical Substances 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 238000002715 modification method Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000009666 routine test Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- G06V40/169—Holistic features and representations, i.e. based on the facial image taken as a whole
-
- 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)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Human Computer Interaction (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a safety examination system capable of automatically identifying faces, which comprises a monitoring camera and an examination device, wherein the monitoring camera and the examination device are both in communication connection with a cloud server; the monitoring camera is used for shooting the face of the examinee at regular time to obtain facial feature data of the examinee and transmitting the facial feature data to the cloud server; the facial feature data correspond to the examinee information one by one; the cloud server is used for searching the examinee identification according to the face data information of the examinee and automatically acquiring the examination question keywords according to the examinee identification, so that the examination questions which are issued to the examinee are constructed. The invention solves the problems that the current laboratory safety examination can not realize 'due to the laboratory condition', individuation and differentiation, and can pertinently and more specifically organize the safety examination training; the problems that the monitoring performance of the online safety examination is poor, the examinee is easy to take a test for replacement, cheating and the like are solved.
Description
Technical Field
The invention relates to the field of systems for laboratory safety examinations in colleges and universities or scientific research institutions, in particular to a safety examination system with automatic facial recognition.
Background
The laboratory is an important base for scientific and technological innovation and talent culture in colleges and universities or scientific research institutions, but safety accidents in the laboratory frequently occur all the time, so that a lot of personal and property losses are caused, and the safety and stability of the society are seriously harmed. Therefore, colleges and scientific research institutes increasingly attach importance to laboratory safety education and management, many colleges and universities in China set up safety training and guidance, and carry out examination on safety knowledge of newborn and new students, but the contents of safety examination are old, outdated and uniform; the form is relatively single, and a large amount of manpower and material resources are consumed for organizing the examination; some so-called online security examinations can answer only by logging in an account, so that the alternative examinations and cheating lines of examination personnel are difficult to avoid, and the examination flows. At present, the laboratory safety examination generally cannot realize the education effects of 'due to the condition of the room', individuation and differentiation, and meanwhile, the monitoring strength of the online examination is far from insufficient.
Disclosure of Invention
In order to solve the technical problem, the invention provides a safe examination system with automatic facial recognition. The invention has two main purposes, firstly, the problems that the 'due-to-the-room condition', individuation and differentiation cannot be realized in the current laboratory safety examination are solved, and the invention can be used for targeted and more specific safety examination training; secondly, the problems that the monitoring performance of the online safety examination is poor, the examinees are easy to take alternative examinations, cheating and the like are solved, the examinees can be remotely examined anytime and anywhere through identity recognition and real-time monitoring, and the monitoring strictness is improved.
To achieve the above object, the present invention provides the following.
A safety examination system with automatic facial recognition comprises a monitoring camera and an examination device, wherein the monitoring camera and the examination device are both in communication connection with a cloud server; the monitoring camera is used for shooting the face of the examinee at regular time to obtain facial feature data of the examinee and transmitting the facial feature data to the cloud server; the facial feature data correspond to the examinee information one by one;
the cloud server is used for searching the examinee identification according to the face data information of the examinee and automatically acquiring the examination question keywords according to the examinee identification, so that the examination questions which are issued to the examinee are constructed.
Further, the cloud server executes the following test taker identification method:
step 1: preprocessing the preset picture, positioning the facial organ in the preset picture, and constructing a feature vector corresponding to the preset picture according to a positioning result, wherein the feature vector is a known feature vector.
Step 2: and acquiring an image shot by a monitoring camera, preprocessing the image, positioning a facial organ, and constructing a feature vector to be matched.
And step 3: and carrying out similarity matching on the known feature vector and the feature vector to be matched.
And 4, step 4: if the matching value is higher than the identification threshold, the matching is successful; otherwise, the matching fails.
Further, the face preprocessing stage comprises: image enhancement, binarization processing, edge detection and image size normalization.
Furthermore, the cloud server positions the face contour by utilizing a gray difference projection algorithm, the eyes are the main positioned organs and then position the nose tip and the mouth in the process of positioning the face organs, and in the positioning process, an integral projection method is adopted to combine with the prior knowledge of the face, and the positioned geometric position relation is utilized to construct a feature vector.
Further, the image enhancement comprises changing the gray level histogram of the original image from a certain gray level interval in the comparison set to be uniformly distributed in the whole gray level range, so as to carry out nonlinear stretching on the image, and redistributing the pixel values of the image to enable the number of pixels in a certain gray level range to be approximately the same.
Further, the image enhancement method is a histogram modification method of accumulating a function-based transform.
Further, the size normalization includes scaling the image according to a scaling coefficient to obtain a calibration image with a uniform size; for image scaling, firstly, the addition, deletion and movement of pixel points are completed according to the size of a required image, and meanwhile, a gray level interpolation algorithm is required to be used to keep the image from being distorted as much as possible.
The invention has the beneficial effects that: the problems that 'due-to-the-room conditions', individuation and differentiation cannot be realized in the current laboratory safety examination are solved, and safety examination training can be specifically organized; the problems that the monitoring performance of the online safety examination is poor, the examinees can easily take alternative examinations, cheating and the like are solved, the examinees can be identified and monitored in real time, the remote examinations can be carried out anytime and anywhere, and the monitoring strictness is improved.
Drawings
Fig. 1 is a schematic diagram of a secure examination system for automatic face recognition provided in the present embodiment 1;
FIG. 2 is a schematic diagram of a method for acquiring examination question keywords provided in this embodiment 1;
fig. 3 is a schematic diagram of a cloud server provided in this embodiment 1;
FIG. 4 is a schematic diagram of the test question assignment module provided in this embodiment 1;
fig. 5 is a schematic diagram of a secure examination method provided in the present embodiment 1;
fig. 6 is a schematic diagram of the automatic face recognition security examination system provided in the embodiment 2;
fig. 7 is a schematic diagram of the execution flow of the admission test provided in this embodiment 2;
fig. 8 is a schematic diagram illustrating the flow of execution of the end-of-term test provided in embodiment 2;
fig. 9 is a schematic diagram illustrating the execution flow of the examination before the procurement and the acceptance of the hazardous chemical/special equipment provided in embodiment 2;
fig. 10 is a schematic diagram illustrating the execution flow of the examination for missing and filling up the problem existing in the examination after the security check provided in embodiment 2;
fig. 11 is a schematic diagram illustrating an execution flow of the examination of related knowledge to be passed before the new item is developed according to the embodiment 2;
fig. 12 is a schematic diagram of the examinee identification method provided in this embodiment 3;
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings.
Example 1:
the embodiment of the invention provides a safety examination system with automatic facial recognition, which consists of hardware equipment and matched software.
Among the automatic facial discernment's safe examination system, as shown in fig. 1, including a plurality of examination rooms 1, every examination room 1 has set one or more examination station 2, has set surveillance camera head 4 and examination device 3 on every examination station 2, surveillance camera head 4 is used for regularly shooting examinee's face in order to obtain examinee's facial feature data, and will facial feature data transmission to cloud server 5, examination device is used for showing examination questions to the examinee, obtains examinee's answer result, and with the answer result transmission extremely cloud server.
The monitoring camera 4 and the examination device 3 on each examination station are in communication connection with the cloud server 5. Each examination station is provided with an ID identification corresponding to the examination station, and the identification of the monitoring camera and the identification of the examination device are in one-to-one correspondence with the ID identifications, so that the cloud server manages each examination station conveniently. Specifically, in the examination process, the cloud server 5 acquires facial feature data of an examinee on a certain examination station, automatically constructs an examination question, and transfers the examination question to the examination device 3 to accept the examination question uploaded by the examination device 3, and automatically scores the examinee according to the examination question.
In order to realize the functions, the embodiment of the invention is further provided with a database, the database stores examination question banks and examinee information, and the database is in communication connection with the cloud server 5.
The design of the database is one of the key contents of the embodiment of the invention, and the following details are set forth:
firstly, the database records the information of the examinees in a database table of the examinee information. The examinee information database table comprises six fields of examinee identification, examinee face data information, examinee professional category, examinee social identity, danger factors needing to be contacted and remarks. The examinee identification is a main key, the examinee professional category can contain one or more professional contents, the examinee social identity shows the academic information or employment information of the examinee, remarks are special marks of the examinee, and the remarks play a role in automatically constructing examination questions. For example, the professional categories of examinees are: chemical, biological and/or medical, the identity of the test taker: "Master graduate", "Ben Ke" or "instructor"; risk factors for contact: sulfuric acid, arsenic trioxide, hexa-fu isobutene, and the like.
In addition, the remarks are used for indicating whether the test taker has entered a subject group, and if the test taker has performed a certain subject group, the remarks also include a subject group identification. If the examinee enters the subject group, the subject group data management table and the subject group data table are also needed to be used in the link of automatically constructing the examination subject. The topic group management table records a topic group identifier and a relationship between the topic group identifier and a topic group database table. The database stores a topic group data management table and a plurality of topic group data tables, so that the topic group data tables can be quickly positioned according to the topic group identification.
The contents of the subject group database table comprise subject group member identification, subject group member identity, risk factors which need to be contacted by the subject group, first-level test information of the subject group and second-level test information of the subject group. The identity of the subject group member is used for representing the position of the examinee in the subject group, namely a 'responsible person' or a 'common team member', if the person is the responsible person, the requirement of the primary test information of the subject group needs to be met, and if the person is the common team member, the requirement of the secondary test information of the subject group only needs to be met.
The database content has an effect in automatically constructing examination questions, and examination question keywords are automatically acquired according to the information of examinees, wherein the acquisition method of the examination question keywords is shown in fig. 2 and comprises the following steps:
s1, searching the identification of the examinee according to the facial data information of the examinee.
S2, searching the examinee information database table according to the examinee identification to obtain the corresponding examinee professional category, the examinee social identity, the danger factors needing to be contacted and the remarks.
And S3, if the remark content is empty, taking the professional category of the examinee, the social identity of the examinee and the risk factors needing to be contacted as examination question keywords.
And S4, if the remark content is not empty, positioning a subject group database table corresponding to the examinee according to the remark.
And S5, obtaining the identity of the subject group members, the danger factors to be contacted by the subject group, the first-level test taking information of the subject group and the second-level test taking information of the subject group in the subject group database table.
And S6, if the examinee is a responsible person, taking the professional category of the examinee, the social identity of the examinee, the risk factors needing to be contacted by the subject group and the first-level examination information of the subject group as examination question keywords.
And S7, if the examinee is a member of the common team, taking the professional category of the examinee, the social identity of the examinee, the risk factors needing to be contacted by the subject group and the second-level test taking information of the subject group as the keywords of the examination questions.
Secondly, the database comprises an examination question bank, the examination question bank stores all possible examination questions in the examination and corresponding relations between the examination questions and examination question keywords, all the examination questions corresponding to the examination question keywords can be automatically screened according to the examination question keywords, and a cloud server can screen the examination questions to construct examination questions for being issued to examinees.
In the question bank, the social identity of the examinee is used for identifying the difficulty level of the examinee's question, for example, if the social identity of the examinee is a student, the difficulty level of the screened test question is lower; if the examinee is a master, the difficulty of the selected test questions is high. The risk factors needing to be contacted, the risk factors needing to be contacted by the subject group, the first-level test taking information of the subject group and/or the second-level test taking information of the subject group represent knowledge points needing to be tested by the examinee in the test. For example, if the risk factors to be contacted include "arsenic trioxide", the risk factors to be contacted by the subject group include "six-blestone", and the subject group first-level test taking information includes the grasp of "sulfuric acid", the knowledge points related to the examination should include the contents of "arsenic trioxide", "six-blestone", and/or "sulfuric acid".
On the premise that a database is constructed, a cloud server realizes a fully-automatic safe examination system for automatic face recognition based on the database and the support of examination stations, and the cloud server comprises the following contents as shown in fig. 3:
and the comprehensive control module 51 is used for controlling the monitoring cameras and the examination devices on the examination stations.
And the examinee identification module 52 is used for acquiring facial feature data of the examinee and acquiring examinee information according to the facial feature data.
In order to realize the content of the examinee identification module, the facial feature of the examinee and related professional fields, experimental equipment, experimental consumables and/or dangerous chemical factors which can be contacted with the examinee need to be input into a database in advance.
The method comprises the following steps that experiment equipment and/or experiment consumables are selectable entry items, examination question keywords are automatically obtained according to the method shown in figure 2 if the experiment equipment and/or the experiment consumables are empty, the experiment equipment and/or the experiment consumables are added on the basis of the examination question keywords obtained in figure 2 if the experiment equipment and/or the experiment consumables are not empty, and an additional result is used as a final examination question keyword; correspondingly, examination questions corresponding to the experimental equipment and/or the experimental consumables are recorded in the question bank.
Further, the cloud server further includes:
and the examination question allocation module is used for acquiring examination question keywords of the examinees, constructing examination questions and transferring the examination questions to the examination device of the examination station where the examinees are located.
And the real-time monitoring module is used for shooting the face of the examinee periodically so as to realize the whole-course monitoring in the examination process.
And the test paper judging and modifying module is used for judging and modifying the answer paper of the examinee and calculating the score.
The test paper judging and modifying module may be configured to perform the following steps: step one, after the examination time is over, the system automatically recovers the test paper answered by the examinee; step two, the system compares the answered test paper answers with the standard answers in the question bank to judge whether the answers are correct or incorrect; and step three, calculating the final score of the examinee according to the examination result.
Specifically, the test question assignment module is shown in fig. 4, and includes:
and the information extraction module 61 is used for acquiring the examination question keywords.
And the degree judging module 62 is used for judging the difficulty of the examination questions according to the social identities of the examinees in the examination question keywords.
The question obtaining and test paper generating module 63 screens out corresponding test questions from the question bank according to the test question difficulty judging result and the test question key words, and extracts a part of the test papers to generate the test paper.
Specifically, one or more question banks in the database may be provided, and the question acquisition and test paper generation module may extract a certain number of examination questions from different question banks, and combine the questions into a test paper in a random order.
Specifically, the automatic facial recognition security examination system executes a security examination method as shown in fig. 5 during the working process:
firstly, acquiring facial images of examinees through a monitoring camera on an examination station before an examination.
Step two, automatically comparing the picture with a preset picture, and when the picture is not matched with the preset picture, prompting a comparison error by a system and stopping the examination; when the comparison matches, the test taker begins to enter the test.
Specifically, the preset photo may be only one or multiple.
And step three, carrying out remote real-time monitoring on the examinees in the examination process, and carrying out photographing comparison on the examinees at specified time intervals.
The examinee can be remotely monitored in real time through the monitoring camera, the examinee is photographed and compared at specified time intervals, such as 2-3 seconds, and cheating or examination taking over in the midway of the examinee is prevented.
To more specifically illustrate the specific implementation of the embodiments of the present invention, the following are given as examples:
the examinee Li Ming, the personal information is pre-input into the database: chemical specialty, Master's research, frequently exposed risk factors: potassium cyanide and hydrofluoric acid. And uploads the individual one-inch corona-free electronic photograph to the database. He applied for 9/11/9 in 2017: 00 begin taking a safety exam. And at 8:50 of the day, the monitoring camera shoots a facial feature picture of the patient and transmits the facial feature picture to the cloud server through the network, and after the facial feature picture is compared by the computer, the comparison matching is found, and the examination is started. The cloud server firstly extracts keywords according to personal information: "chemistry specialty", "major research", "potassium cyanide", "hydrofluoric acid", the safety examination degree suitable for plum "was judged as: chemical, medium difficulty, "potassium cyanide" and "hydrofluoric acid" knowledge points. Therefore, the system selects an appropriate question from the question bank based on these conditions, generates a test paper, and transmits the test paper to the Li Ming's examination terminal. In the examination process, the camera takes facial feature pictures once every 2-3 seconds and transmits the facial feature pictures to the main server, and the examination person in charge can monitor the examination condition in real time through the main server. After the examination is finished, the system automatically recovers the plum answering result, corrects the test paper and calculates the score.
The examinee Liu Ming inputs its personal information in advance: biological specialty, professor/subject group responsible for human, laboratory animal research subject group, frequently exposed risk factors: pathogenic microorganism and parasite. And the personal one-inch corona-free electronic photograph is uploaded to a cloud server. She applied for 10 months, 10 days 12 in 2017: 00 begin taking a safety exam. At 11:50 of the day, she enters the examination system, takes a picture of his facial features by the monitoring camera and transmits the picture to the cloud server through the network, and after the comparison is carried out by the computer, the comparison matching is found, and the examination is started. The system first extracts keywords from her personal information: "biology", "experimental animal research topic group" (further may be related information of the topic group), "instructor", "pathogenic microorganism", and "parasite", and the safety examination degree suitable for Liu Ming is judged as follows: biology, experimental animal correlation, higher difficulty, "pathogenic microorganism" and "parasite" knowledge points. Therefore, the system selects proper questions from the question bank according to the conditions, generates test paper and sends the test paper to the Liu Min computer terminal for the examination. In the examination process, the camera takes facial feature pictures every 2-3 seconds and transmits the facial feature pictures to the cloud server. After the examination is finished, the system automatically recovers the Liu-Ming answer results, corrects the test paper and calculates the score.
Example 2:
as shown in fig. 6, the embodiment of the present invention uses the automatic facial recognition security examination system shown in embodiment 1, and describes in detail the manner of using the automatic facial recognition security examination system.
The automatic facial recognition safety examination system in the embodiment of the invention can be used for executing two examination modes of a conventional examination 7 and a dynamic examination 8, wherein the conventional examination 7 is a unified and centralized examination mode, and the dynamic examination 8 is a customized and remote examination mode. The routine tests include an admission test 71 and an associated professional end-of-term test 72. The dynamic examination 8 includes an examination 81 before the procurement of dangerous chemicals/special equipment and the acceptance, an examination 82 after the safety inspection and the omission of the examination for the problems in the examination, and an examination 83 for developing the related knowledge which the new item needs to pass at present.
In the conventional examination, the mode of centralized examination in a unified place is adopted, the identity information of examinees is checked before the examination, test papers are automatically distributed according to the information of the examinees, the question banks extracted by the examinees in the same profession are the same, but the specific questions are not necessarily the same, and cheating can be effectively avoided.
The execution flow of the admission test is shown in fig. 7, and includes:
a1: registering an account and filling personal information.
The account number corresponds to the examinee identification in the database, and personal information also needs to be input into the database so as to facilitate subsequent automatic question setting.
A2: according to the laboratory where the examinee is and the subject group, the system automatically selects the corresponding professional and difficult exercise problems, and the examinee self-learns and simulates.
A3: the school arranges admission examinations at uniform time and uniform place, and examinees take online examinations. The test paper is distributed by the examination system according to the information of the examinees.
A4: after the examination is completed, the system automatically scores and counts the qualified/unqualified people.
The execution flow of the end-of-term test is shown in fig. 8, and includes:
b1: the special profession sets a safe course as a necessary or optional course, and 0.5 or 1 credit can be set.
B2: the school arranges admission examinations at uniform time and uniform place, and examinees take online examinations. The test paper is distributed by the examination system according to the information of the examinees.
B3: after the examination is completed, the system automatically scores and counts the qualified/unqualified people. Students eligible for the exam obtain a credit.
The dynamic examination adopts a form of independent customization and remote monitoring, and the test paper is automatically distributed according to the information of the examinees only aiming at partial needs of partial examinees. The invigilator can perform facial recognition and identity authentication on the examinee through online monitoring, and complete the remote examination. The burden of organizing large-scale examination rooms and a large number of invigilators is reduced, the examination time is flexible, and safe examination can be performed at any time and any place.
The execution flow of the examination before the procurement and the adoption of the hazardous chemical substance/special equipment is shown in fig. 9 and comprises the following steps:
C1. and (4) purchasing dangerous chemicals or special equipment, firstly purchasing the dangerous chemicals or the special equipment on a purchasing mall, and sending the dangerous chemicals or the special equipment to a special storehouse for temporary storage.
C2. The buyer applies to the on-line report of the application for getting up, the examination system dials the special subject about the safety knowledge related to the dangerous chemical or special equipment, and the buyer can obtain the qualification for getting up after the examination.
C3. The users related to the dangerous chemical substances or the special equipment should take special examinations, and if the later-period finds that the personnel who do not pass the examinations use the dangerous chemical substances or the special equipment by themselves, the personnel shall immediately take the examinations and perform criticizing education.
As shown in fig. 10, the execution flow of an examination for which missing and missing are checked for a problem existing in the examination after the security check includes:
D1. after each safety check, the problems and the defects of each laboratory are respectively gathered and published on the related website.
D2. Related staff in a published laboratory should apply to participate in a special examination for missing and filling before the next examination, and an examination system dials related questions about problems occurring in the safety examination.
D3. All the related personnel in each laboratory with problems pass the examination of checking omission and filling, and the safety examination is ended. If the safety inspection fails or is not applied, the next safety inspection directly judges that the safety inspection is unqualified, and the safety inspection is continuously supervised to be rectified and improved.
Fig. 11 shows an execution flow of an examination of related knowledge to be passed before a new item is developed, which includes:
E1. when new security knowledge is involved, it is necessary to report to the security department of the school before a new project is developed, on the premise that a new project or a new project is applied to a certain project group.
E2. The school safety management department carries out safety evaluation and analysis on the new subject to be developed and re-determines the safety examination level which needs to be passed by the subject group member.
E3. If the re-evaluated examination level is higher than before, the experimenter of the subject group is required to re-take the safety examination, and the subject is automatically called by the examination system.
Further, the examinee can also perform simulation exercises and the like again before the examination.
Example 3:
in the above two embodiments, the examinee needs to be monitored or the examinee information needs to be identified based on facial recognition, and in order to improve the recognition rate and improve the recognition speed, the embodiment of the present invention provides an examinee identification method, as shown in fig. 12, including:
step 1: preprocessing the preset picture, positioning the facial organ in the preset picture, and constructing a feature vector corresponding to the preset picture according to a positioning result, wherein the feature vector is a known feature vector.
Step 2: and acquiring an image shot by a monitoring camera, preprocessing the image, positioning a facial organ, and constructing a feature vector to be matched.
And step 3: and carrying out similarity matching on the known feature vector and the feature vector to be matched.
And 4, step 4: if the matching value is higher than the identification threshold, the matching is successful; otherwise, the matching fails.
The face preprocessing stage comprises the following steps: face image enhancement, binarization processing, edge detection and image size normalization.
The facial organ positioning module determines the facial contour from the original image, the facial contour is positioned by utilizing a gray difference projection algorithm in the embodiment of the invention, the boundary lines of two sides of the face are determined by utilizing a gray difference accumulated value, the calculated amount is small, the positioning speed is high, and the accuracy is high. In the process of positioning facial organs, eyes are the main organs for positioning, the subsequent organ positioning is influenced by the positioning accuracy of the eyes, and then the nose tip and the mouth are positioned by adopting an integral projection method and combining with the prior knowledge of the face. And constructing a proper feature vector by using the positioned geometric position relation.
Specifically, the image enhancement method in the embodiment of the present invention mainly includes:
the gray level histogram of the original image is changed from a certain gray level interval in the comparative set to be uniformly distributed in the whole gray level range, so that the image is subjected to nonlinear stretching, and the pixel values of the image are redistributed, so that the number of pixels in a certain gray level range is approximately the same. Specifically, the image enhancement method is a histogram modification method in which a cumulative reliability function is transformed into a base. If the original gray level of the pixel point is R, the converted gray level is S, S is the normalized gray level, and the gray level conversion function T (R) is as follows:
Before feature extraction, image preprocessing is usually performed, and for face recognition, the primary work is face image segmentation and main organ positioning, and face image scale normalization is performed. Scaling of the image by the scaling factor results in a calibration image of uniform size. For image scaling, firstly, an algorithm is needed to define spatial transformation itself, that is, adding, deleting and moving of pixel points are completed according to the size of a required image. Meanwhile, an algorithm of gray level interpolation is also needed to keep the image as undistorted as possible.
After normalization, the positions of the eyes, the nose tip, the mouth and other organs are further determined through the projection curve. The method is fast and simple and can meet the requirement of weak real-time application.
In the organ identification process, the eye is first positioned. The gray values of the eye parts in the face image are usually smaller than those of the surrounding area, and with this feature, the eye is often positioned by using an integral projection method. The integral projection function can reflect the overall gray value condition of the image in the horizontal or vertical direction, so that the position of the pupil can be judged by integral projection of the eye area. In order to further increase the accuracy of eye positioning, on the basis of the integral projection method, the consideration of the horizontal gray scale is fused, namely the gray scale of the eye in the horizontal direction is changed greatly. Differentiation at abrupt changes in gray scale will produce high values, which are accumulated in absolute values, with the accumulated value being larger for the row with larger gray scale changes. Thereby positioning the eye.
On the basis that the eyes are accurately positioned, each other organ is subsequently positioned, and thus facial recognition can be performed.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (6)
1. A safety examination system with automatic facial recognition is characterized by comprising a monitoring camera and an examination device, wherein the monitoring camera and the examination device are both in communication connection with a cloud server; the monitoring camera is used for shooting the face of the examinee at regular time to obtain facial feature data of the examinee and transmitting the facial feature data to the cloud server; the facial feature data correspond to the examinee information one by one; the cloud server is used for searching examinee identifications according to the face data information of the examinees and automatically acquiring examination question keywords according to the examinee identifications so as to construct examination questions to be issued to the examinees;
the cloud server executes the following test taker identification method:
step 1: preprocessing a preset photo, positioning a facial organ in the preset photo, and constructing a feature vector corresponding to the preset photo according to a positioning result, wherein the feature vector is a known feature vector;
step 2: acquiring an image shot by a monitoring camera, preprocessing the image, positioning a facial organ, and constructing a feature vector to be matched;
and step 3: carrying out similarity matching on the known characteristic vector and the characteristic vector to be matched;
and 4, step 4: if the matching value is higher than the identification threshold, the matching is successful; otherwise, the matching fails;
the system is also provided with a database, wherein the database stores examination question banks and examinee information, and is in communication connection with the cloud server; the database records examinee information in an examinee information database table, wherein the examinee information database table comprises six fields of examinee identification, examinee facial data information, examinee professional category, examinee social identity, danger factors needing to be contacted and remarks; the examinee identification is a main key, the examinee professional category comprises one or more professional contents, and the examinee social identity indicates the academic information or the employment information of the examinee; the remarks are used for indicating whether the examinee enters a subject group or not, and if the examinee carries out a certain subject group, the remarks also comprise a subject group identifier; if the examinee enters the subject group, a subject group data management table and a subject group data table are needed to be used in the link of automatically constructing the examination subject; the problem group data management table records a problem group identifier and a relation between the problem group identifier and a problem group database table; a subject group data management table and a plurality of subject group data tables are stored in the database so as to be convenient for rapidly positioning the subject group data tables according to the subject group identification; the contents of the subject group database table comprise subject group member identification, subject group member identity, risk factors which need to be contacted by the subject group, first-level test information of the subject group and second-level test information of the subject group; the identity of the subject group member is used for representing the position of an examinee in the subject group, namely a 'responsible person' or a 'common team member', if the person is the responsible person, the requirement of primary test information of the subject group needs to be met, and if the person is the common team member, the requirement of secondary test information of the subject group only needs to be met;
the cloud server includes: the comprehensive control module is used for controlling the monitoring cameras and the examination devices on the examination stations;
the examinee identification module is used for acquiring facial feature data of the examinee and acquiring examinee information according to the facial feature data;
the examination question allocation module is used for acquiring examination question keywords of an examinee, constructing an examination question and transferring the examination question to an examination device of an examination station where the examinee is located;
the real-time monitoring module is used for shooting the face of the examinee periodically so as to realize the whole-course monitoring in the examination process;
the test paper judging and modifying module is used for judging and modifying the answer paper of the examinee and calculating the score;
the method for acquiring the examination question keywords comprises the following steps: searching the identification of the examinee according to the facial data information of the examinee;
searching the examinee information database table according to the examinee identification to obtain the corresponding examinee professional category, examinee social identity, danger factors needing to be contacted and remarks;
if the remark content is empty, taking the professional category of the examinee, the social identity of the examinee and the risk factor needing to be contacted as examination question keywords;
if the remark content is not empty, positioning a subject group database table corresponding to the examinee according to the remark;
obtaining the identity of a subject group member, danger factors to be contacted by the subject group, first-level test information of the subject group and second-level test information of the subject group in the subject group database table; if the examinee is a responsible person, taking the professional category of the examinee, the social identity of the examinee, the risk factors needing to be contacted by the subject group and the first-level examination information of the subject group as examination question keywords; if the examinee is a member of the common team, taking the professional category of the examinee, the social identity of the examinee, the risk factors needing to be contacted by the subject group and the secondary examination taking information of the subject group as the key words of the examination questions;
in the monitoring process, examinees are required to be identified based on facial feature positioning, facial contours are positioned by utilizing a gray difference projection algorithm, boundary lines of two sides of a face are determined by utilizing an accumulated value of gray differences, and eyes are main organs for positioning in the process of positioning facial organs; extracting facial features through image enhancement, changing a gray level histogram of an original image from a certain concentrated gray level interval into uniform distribution in a whole gray level range so as to perform nonlinear stretching on the image, redistributing image pixel values to enable the number of pixels in a preset gray level range to be approximately the same, and if the original gray level of a pixel point is R, the converted gray level is S, the S is a normalized gray level value, and a gray level conversion function T (R) is as follows:
2. The automated facial recognition security testing system of claim 1, wherein: the face preprocessing stage comprises the following steps: image enhancement, binarization processing, edge detection and image size normalization.
3. The automatic face recognition safety examination system according to claim 2, wherein the cloud server locates the face contour by using a gray difference projection algorithm, the eyes are the main organs to be located in the process of locating the face organs, and then the nose tip and the mouth are located, and in the process of locating, an integral projection method is adopted to combine with the face priori knowledge, and feature vectors are constructed by using the located geometric position relation.
4. A security exam system according to claim 3, wherein said image enhancement comprises changing the intensity histogram of the original image from a certain intensity interval in the comparison set to a uniform distribution over the entire intensity range, so as to non-linearly stretch the image and redistribute the image pixel values so that the number of pixels in a certain intensity range is approximately the same.
5. The automatic face recognition security exam system according to claim 4, wherein the image enhancement method is histogram modification based on cumulative distribution function transform.
6. A secure examination system for automatic face recognition according to claim 3, wherein the size normalization includes scaling of the image by a scaling factor, resulting in a calibration image having a uniform size; for image scaling, firstly, the addition, deletion and movement of pixel points are completed according to the size of a required image, and meanwhile, a gray level interpolation algorithm is required to be used to keep the image from being distorted as much as possible.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711175592.0A CN107967660B (en) | 2017-11-22 | 2017-11-22 | Automatic facial recognition's safe examination system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711175592.0A CN107967660B (en) | 2017-11-22 | 2017-11-22 | Automatic facial recognition's safe examination system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107967660A CN107967660A (en) | 2018-04-27 |
| CN107967660B true CN107967660B (en) | 2020-10-27 |
Family
ID=62001451
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711175592.0A Active CN107967660B (en) | 2017-11-22 | 2017-11-22 | Automatic facial recognition's safe examination system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107967660B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084206B (en) * | 2019-04-30 | 2021-06-25 | 浙江国显科技有限公司 | Intelligent examination room monitoring system and method thereof |
| CN113515976B (en) * | 2020-04-10 | 2023-08-29 | 华中科技大学 | Intelligent experiment investigation system based on multi-scene video analysis |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010026630A (en) * | 2008-07-16 | 2010-02-04 | Seiko Epson Corp | Image retrieval device and image retrieval method |
| CN106384320A (en) * | 2016-10-30 | 2017-02-08 | 安徽省艾佳信息技术有限公司 | Test method based on random test questions |
| CN106448308A (en) * | 2016-10-13 | 2017-02-22 | 佛山市炫鲸科技有限公司 | Experiment safety examination method and system |
-
2017
- 2017-11-22 CN CN201711175592.0A patent/CN107967660B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010026630A (en) * | 2008-07-16 | 2010-02-04 | Seiko Epson Corp | Image retrieval device and image retrieval method |
| CN106448308A (en) * | 2016-10-13 | 2017-02-22 | 佛山市炫鲸科技有限公司 | Experiment safety examination method and system |
| CN106384320A (en) * | 2016-10-30 | 2017-02-08 | 安徽省艾佳信息技术有限公司 | Test method based on random test questions |
Non-Patent Citations (1)
| Title |
|---|
| 基于特征脸的面部识别技术研究;郝立涛;《中国优秀硕士学位论文全文数据库 信息科技辑》;20100815(第8期);第8、18、25-30、39-41、46段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107967660A (en) | 2018-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107845300B (en) | Real-time monitoring safety examination system | |
| CN109740446A (en) | Classroom students ' behavior analysis method and device | |
| US20180308107A1 (en) | Living-body detection based anti-cheating online research method, device and system | |
| CN107818707B (en) | Examination system capable of automatically setting questions | |
| CN111353921A (en) | Examination management method and system and electronic equipment | |
| CN107967660B (en) | Automatic facial recognition's safe examination system | |
| CN107240050A (en) | A kind of student instruction method for managing security based on cloud platform | |
| Alburaiki et al. | Mobile based attendance system: face recognition and location detection using machine learning | |
| CN113313168A (en) | Intelligent anti-cheating self-service examination system for unmanned invigilation | |
| CN111523445B (en) | Examination behavior detection method based on improved Openpost model and facial micro-expression | |
| Deniz et al. | Computer vision for attendance and emotion analysis in school settings | |
| Ray et al. | Design and implementation of technology enabled affective learning using fusion of bio-physical and facial expression | |
| Dimitriadou et al. | Using Student Action Recognition to Enhance the Efficiency of Tele-education. | |
| CN113486744B (en) | Student learning state evaluation system and method based on eye movement and facial expression paradigm | |
| KR100937923B1 (en) | Operation system sham examination of practical technique. | |
| CN109118512A (en) | A kind of classroom based on machine vision is come to work late and leave early detection method | |
| CN107818531B (en) | Safety examination system | |
| CN109711263B (en) | Examination system and processing method thereof | |
| CN110298301A (en) | A kind of establishment officer's phychology prediction technique | |
| CN116090999A (en) | Training examination system based on image AI and universe | |
| CN110084109A (en) | A kind of low-resolution face image recognition methods, device, electronic equipment and storage medium | |
| CN115050075A (en) | Cross-granularity interactive learning micro-expression image labeling method and device | |
| CN113542668A (en) | Monitoring system and method based on 3D camera | |
| Guan et al. | Evaluation of classroom teaching quality based on video processing technology | |
| Santoso et al. | Development of an online exam security system using ensemble method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |