CN111738209A - Examination room cheating behavior pre-judging system based on examinee posture recognition - Google Patents
Examination room cheating behavior pre-judging system based on examinee posture recognition Download PDFInfo
- Publication number
- CN111738209A CN111738209A CN202010691828.1A CN202010691828A CN111738209A CN 111738209 A CN111738209 A CN 111738209A CN 202010691828 A CN202010691828 A CN 202010691828A CN 111738209 A CN111738209 A CN 111738209A
- Authority
- CN
- China
- Prior art keywords
- module
- examinee
- recognition
- judgment
- examination room
- 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
Images
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
- G06V40/172—Classification, e.g. identification
-
- 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—Systems or methods specially adapted for 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
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
Abstract
The invention discloses an examination room cheating behavior pre-judging system based on examinee posture recognition, which comprises a picture acquisition module, a data set establishment module and a recognition module, wherein the output end of the picture acquisition module is connected with the input end of the data set establishment module, the output end of the data set establishment module is connected with the input end of the recognition module, the input end of the recognition module is connected with a data input module, and the output end of the recognition module is connected with an examinee marking module. The posture of the pre-judging cheater is judged manually, the wrong pre-judgment is corrected to obtain more judgment data, and the judgment data are transmitted to the recognition module through the judgment updating module and can update the judgment standard of the recognition module in time, so that the recognition module can be continuously improved, the recognition is faster and more accurate, whether the cheater tends to cheat or not is judged, and the influence on the examination of the examinee is avoided.
Description
Technical Field
The invention relates to the technical field of cheating prevention, in particular to a prejudging system for identifying cheating behaviors of an examination room based on postures of examinees.
Background
The examination is a strict knowledge level identification method, the learning ability and other abilities of students can be checked through the examination, in order to ensure the fairness of results, an examination hall must have strong discipline constraints, and is specially provided with a supervision examination process such as a main examination and an invigilation, and any cheating behavior is absolutely prohibited, and in the examination process, the warning of examination violation of students through manual or electronic technology supervision is an important ring of the existing examination checking system.
However, in the prior art, during actual use, the defect of recognition error still exists when examination cheating is judged in advance in an intelligent posture recognition mode, and wrong judgment can be easily caused, so that examination of an examinee is influenced.
Disclosure of Invention
The invention aims to provide a prejudgment system for identifying cheating behaviors of an examination room based on postures of examinees, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: including picture collection module, data set establishment module and identification module, the output of picture collection module is connected with the input of data set establishment module, the output of data set establishment module is connected with identification module's input, identification module's input is connected with data input module, identification module's output is connected with examinee marking module, and examinee marking module's output is connected with early warning module, data set establishment module includes that the position is injectd module and position label module, identification module includes face identification module and gesture recognition module, data input module includes examinee information module and examinee position module, identification module's input is connected with learning module, learning module includes gesture decision module and judges the update module.
Preferably, the picture acquisition module comprises a camera, and the picture acquisition module is used for transmitting classroom picture information in real time.
Preferably, the position limiting module is used for positioning the positions of the examinees in the picture transmitted by the picture acquisition module and setting the moving range of the examinees in the picture, and the position marking module is used for marking the positions of the examinees positioned by the position limiting module.
Preferably, the face recognition module is used for recognizing the examinee through a face recognition technology and acquiring the examinee information.
Preferably, the gesture recognition module comprises a head turning recognition module, a body side shifting recognition module, a hand motion recognition module and an eyeball tracking module.
Preferably, the head turning recognition module is used for monitoring whether the examinee has a cheating action that the head of the examinee looks at copyists to answer questions, the body side moving recognition module is used for detecting whether the examinee has a side moving body to prepare for cheating, the hand action recognition module is used for detecting whether the hand of the examinee has frequent action adjustment, and the eyeball tracking module is used for tracking the eyeball imaging range of the examinee to detect whether the examinee clicks copyists to answer questions.
Preferably, the examinee marking module is used for combining the position information and the identity information of cheating examinees and transmitting the position information and the identity information to the early warning module, and the early warning module is used for displaying and reminding the invigilator of the examination to pay attention to the key observation through the cheating examinees on the platform.
Preferably, the examinee information module is used for inputting examinee information into the system of the identification module before examination, and the examinee position module is used for inputting position information made by the examinee into the system of the identification module.
Preferably, the connecting end of the identification module is bidirectionally connected with a storage module, the storage module is used for recording judgment information of the identification module, the posture judgment module is used for manually judging the posture of the examinee, and the judgment updating module is used for transmitting the judgment information to the identification module and updating the judgment standard of the identification module.
Compared with the prior art, the invention has the beneficial effects that:
1. the posture of the pre-judging cheater is judged manually, the wrong pre-judgment is corrected to obtain more judgment data, and the judgment data are transmitted to the recognition module through the judgment updating module and can update the judgment standard of the recognition module in time, so that the recognition module can be continuously improved, the recognition is faster and more accurate, whether the cheater tends to cheat or not is judged, and the influence on the examination of the examinee is avoided;
2. the invention also transmits classroom picture information to the data set establishing module in real time through the picture collecting module, enables the position limiting module and the position label module in the data set establishing module to establish a data set and label the positions of examinees, and reminds the invigilators of the examinees of cheating tendency signals to pay key observation through the examinee marking module and the early warning module through the head turning recognition module, the body side shifting recognition module and the hand action recognition module in the recognition module, thereby greatly assisting the discipline behaviors of the examination hall, realizing the purposes of reducing the burden of the invigilators, greatly improving the manual operation and improving the invigilating quality and efficiency.
3. The invention also can input various information of the examinee into the system of the identification module through the examinee information module and the examinee position module, and identifies the examinee information through the face identification module, so that the identity of the examinee can be rapidly verified, and the other side of the face identification module can be matched with the position limiting module to identify whether the examinee makes a wrong position or not, so that the data input module is convenient for the identification module to acquire the examinee information and check the position information of the examinee, and the situation that the examinee makes a wrong position is avoided.
Drawings
FIG. 1 is a system block diagram of the overall structure of a pre-judging system for identifying cheating behaviors in an examination room based on postures of examinees;
FIG. 2 is a structural system diagram of a pre-judging system data set establishing module for identifying cheating behaviors in an examination room based on postures of examinees;
FIG. 3 is a structural system diagram of an examination room cheating behavior pre-judgment system identification module based on examinee posture identification;
FIG. 4 is a structural system diagram of a data input module of a pre-judging system for identifying cheating behaviors in an examination room based on postures of examinees;
FIG. 5 is a structural system diagram of a pre-judging system learning module for identifying cheating behaviors in an examination room based on postures of examinees.
FIG. 6 is a block diagram of a human skeleton of an examination room cheating behavior pre-judgment system based on examination room posture recognition.
In the figure: 1. a picture acquisition module; 2. a data set establishing module; 21. a location defining module; 22. a location labeling module; 3. an identification module; 31. a face recognition module; 32. a gesture recognition module; 33. a voice recognition module; 34. a gesture recognition module; 321. a head steering identification module; 322. a body side movement recognition module; 323. a hand motion recognition module; 324. an eye tracking module; 4. a data input module; 41. an examinee information module; 42. an examinee location module; 5. an examinee marking module; 6. an early warning module; 7. a storage module; 8. a learning module; 81. a posture determination module; 82. and judging and updating the module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-5, the present invention provides a technical solution: comprises a picture acquisition module 1, a data set establishment module 2 and an identification module 3, wherein the output end of the picture acquisition module 1 is connected with the input end of the data set establishment module 2, the output end of the data set establishment module 2 is connected with the input end of the identification module 3, the input end of the identification module 3 is connected with a data input module 4, the output end of the identification module 3 is connected with an examinee marking module 5, and the output end of the examinee marking module 5 is connected with the early warning module 6, the data set establishing module 2 comprises a position limiting module 21 and a position marking module 22, the recognition module 3 comprises a face recognition module 31 and a posture recognition module 32, the data input module 4 comprises an examinee information module 41 and an examinee position module 42, the input end of the recognition module 3 is connected with a learning module 8, and the learning module 8 includes a posture determination module 81 and a judgment update module 82.
The picture acquisition module 1 comprises a camera, and the picture acquisition module 1 is used for transmitting classroom picture information in real time.
The position limiting module 21 is configured to position the position of the examinee in the picture transmitted by the picture acquisition module 1, and set a moving range of the examinee in the picture, the position labeling module 22 is configured to label the position of the examinee positioned by the position limiting module 21, position the position of the examinee in the picture transmitted by the picture acquisition module 1 by the position limiting module 21, and set a moving range of the examinee in the picture, so as to provide a basis for evaluation of the identification module 3, when a part of the body of the examinee is beyond the range set by the position limiting module 21 for a long time, the examinee is labeled by the examinee labeling module 5, and the early warning module 6 is configured to transmit early warning information to the teacher to remind the teacher to keep track of the examinee, the position labeling module 22 may extract the student's target by a background difference method, establish a data set n = { n1, n 2. } and label the examinee position positioned by the position limiting module 21, the information of the examinee can be checked, and the situation that the examinee makes a wrong position is avoided.
The gesture recognition module 32 includes a head turn recognition module 321, a body side shift recognition module 322, a hand motion recognition module 323, and an eye tracking module 324.
The head turning recognition module 321 is used for monitoring whether the examinee has cheating actions that the head of the examinee looks at the copyists to answer the questions, the body side moving recognition module 322 is used for detecting whether the examinee has the actions that the body of the examinee can move sideways to implement the cheating, the hand action recognition module 323 is used for detecting whether the hands of the examinee have frequent action adjustment, the eyeball tracking module 324 is used for tracking the eyeball imaging range of the examinee to detect whether the examinee has cheating actions or not, the head turning recognition module 321 is matched with the body side moving recognition module 322, the hand action recognition module 323 and the eyeball tracking module 324 to monitor whether the examinee has cheating actions, once the head turning recognition module 321, the body side moving recognition module 322, the hand action recognition module 323 and the eyeball tracking module 324 detect that the examinee has the actions that the head of the examinee looks sideways, the body of the side moves sideways, the hands of the examinee have frequent action adjustment and focus on the other, the head turning recognition module 321, the body side shifting recognition module 322, the hand action recognition module 323 and the eyeball tracking module 324 transmit signals to the examinee marking module 5 in time to mark the position information of the examinee, and the examinee marking module 5 transmits the information to the early warning module 6, and reminds the invigilator of key observation.
Examinee marking module 5 is used for combining cheating examinee's positional information and identity information, and to early warning module 6 department transmission, early warning module 6 is used for showing through cheating examinee's picture at the podium and reminds the prisoner of invigorating the examination to pay close attention to observing, can combine examinee positional information and identity information who has the tendency of cheating through examinee marking module 5, cooperation early warning module 6 reminds the prisoner to pay close attention to observing, so that the prisoner can fix a position student's position fast, and learn the circumstances such as examinee's name, prevent the cheating action or stop this examinee and continue the examination to the examinee.
The examinee information module 41 is used for inputting examinee information into the system of the identification module 3 before examination, the examinee position module 42 is used for inputting position information made by an examinee into the system of the identification module 3, and various items of information of the examinee can be input into the system of the identification module 3 through the examinee information module 41 and the examinee position module 42, so that the identification module 3 can conveniently acquire the examinee information and check the position information of the examinee.
The connecting end of the recognition module 3 is bidirectionally connected with a storage module 7, the storage module 7 is used for recording the judgment information of the recognition module 3, the posture judgment module 81 is used for manually judging the posture of the examinee, the judgment updating module 82 is used for transmitting the judgment information to the recognition module 3 and updating the judgment standard of the recognition module 3, by arranging the storage module 7, the storage module 7 can record the information judged by the identification module 3, so that the information can be conveniently checked at the later stage, and by arranging the posture judging module 81 and the judgment updating module 82, the posture of the examinee can be manually judged, so as to obtain more evaluation data, and the evaluation data is transmitted to the recognition module 3 through the evaluation updating module 82, which can be updated in time for the evaluation criteria of the recognition module 3, therefore, the recognition module 3 can be continuously perfected, and the recognition can be more quickly and accurately carried out and whether the examinees are cheating or not can be judged.
The working principle is as follows: when the invention is used, classroom picture information is transmitted to the data set establishing module 2 in real time through the picture collecting module 1, the position limiting module 21 and the position labeling module 22 in the data set establishing module 2 can extract an examinee target through a background difference method, a data set n = { n1, n 2. } is established, the examinee position in the position is labeled, a head turning recognition module 321, a body side shifting recognition module 322 and a hand action recognition module 323 in the recognition module 3 timely transmit cheating tendency signals of the examinee to the examinee labeling module 5 to label the examinee position information, the examinee labeling module 5 transmits the information to the early warning module 6 so that the proctor pays attention to the key observation, thereby greatly assisting the test field discipline behavior, reducing the burden of the proctor, greatly improving the manual operation and the proctor quality and efficiency, by arranging the posture judgment module 81 and the judgment updating module 82, the posture of the examinee can be manually judged to obtain more judgment data, and the judgment data are transmitted to the recognition module 3 through the judgment updating module 82 and can be updated in time for the judgment standard of the recognition module 3, so that the recognition module 3 can be continuously improved, and the recognition can be more quickly and accurately carried out and whether the examinee is prone to cheating or not can be judged.
The gesture judgment module extracts key points of a human body by adopting a Mask RCNN-based deep learning algorithm and forms a corresponding skeleton structure to realize detection of human body gestures, and Mask RCNN example segmentation comprises three parts of target positioning, target class classification and Mask segmentation prediction. Firstly, after a picture is input, extracting a feature map of the picture through a series of convolution and pooling operations by using a feature pyramid network FPN, secondly, selecting a candidate target on the feature map by an RPN network, judging whether the candidate target belongs to the background or the foreground by using a softmax classifier, simultaneously correcting the position of the candidate target by using a range frame regressor, generating a candidate target area, finally predicting a corresponding target segmentation mask by using a full convolution network FCN, realizing the detection of the target category by using the feature map and the candidate area generated by the RPN network by the classification network, realizing the pixel-level accurate segmentation of the target by using the feature map by the FCN, extracting the human key point information predicted by the network by using the motion identification technology to obtain { AA ', AB', BC ', CD', EF ', FG' }11 groups of key point information (as shown in figure 6), and then establishing a neck vector AA ', a left shoulder vector AB, a right shoulder vector AB', a left arm vector BC, a right arm vector BC ', a left hand vector CD, a right hand vector CD', a left leg vector EF, a right leg vector EF ', a left foot vector FG and a right foot vector FG', and judging the action according to the angle and direction information threshold conditions.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The utility model provides a pre-judgement system based on examinee's gesture recognition examination room cheating action which characterized in that: comprises a picture acquisition module (1), a data set establishing module (2) and an identification module (3), the output end of the picture acquisition module (1) is connected with the input end of the data set establishment module (2), the output end of the data set establishing module (2) is connected with the input end of the identification module (3), the input end of the identification module (3) is connected with a data input module (4), the output end of the identification module (3) is connected with a examinee marking module (5), the output end of the examinee marking module (5) is connected with an early warning module (6), the data set creation module (2) comprises a location definition module (21) and a location numbering module (22), the recognition module (3) comprises a face recognition module (31), a gesture recognition module (32), a voice recognition module (33) and an expression recognition module (34); the data input module (4) comprises an examinee information module (41) and an examinee position module (42), the input end of the identification module (3) is connected with a learning module (8), and the learning module (8) comprises a posture judgment module (81) and an evaluation updating module (82).
2. The examination room cheating behavior pre-judgment system based on examination room posture recognition of claim 1, wherein: the picture acquisition module (1) comprises a camera, and the picture acquisition module (1) is used for transmitting classroom picture information in real time.
3. The examination room cheating behavior pre-judgment system based on examination room posture recognition of claim 1, wherein: the position limiting module (21) is used for positioning the positions of the examinees in the picture transmitted by the picture acquisition module (1) and setting the moving range of the examinees in the picture, and the position marking module (22) is used for marking the positions of the examinees positioned by the position limiting module (21).
4. The examination room cheating behavior pre-judgment system based on examination room posture recognition of claim 1, wherein: the face recognition module (31) is used for recognizing the examinee through a face recognition technology and acquiring examinee information; the voice recognition module (33) is used for monitoring whether the examinee asks questions or asks the information of classmate answers; the expression recognition module (34) is used for monitoring the expression change of the examinee during the examination, including tension and happy recognition.
5. The examination room cheating behavior pre-judgment system based on examination room posture recognition of claim 1, wherein: the gesture recognition module (32) comprises a head turning recognition module (321), a body side shifting recognition module (322), a hand motion recognition module (323) and an eyeball tracking module (324).
6. The examination room cheating behavior pre-judgment system based on examinee posture recognition is characterized in that: the head turning recognition module (321) is used for monitoring whether the examinee has a cheating action that the head of the examinee looks at copyists to answer questions, the body side moving recognition module (322) is used for detecting whether the examinee has a side moving body to prepare for the cheating action, the hand action recognition module (323) is used for detecting whether the hand of the examinee has frequent action adjustment, and the eyeball tracking module (324) is used for tracking the eyeball focusing range of the examinee and detecting whether the examinee clicks copyists to answer other questions.
7. The examination room cheating behavior pre-judgment system based on examination room posture recognition of claim 1, wherein: the examinee marking module (5) is used for combining the position information and the identity information of cheating examinees and transmitting the position information and the identity information to the early warning module (6), and the early warning module (6) is used for reminding a proctoring teacher to pay attention to key observation through the picture display of the cheating examinees on a platform.
8. The examination room cheating behavior pre-judgment system based on examination room posture recognition of claim 1, wherein: the examinee information module (41) is used for recording examinee information into the system of the identification module (3) before examination, and the examinee position module (42) is used for recording the position information made by the examinee into the system of the identification module (3).
9. The examination room cheating behavior pre-judgment system based on examination room posture recognition of claim 1, wherein: the gesture recognition system is characterized in that a storage module (7) is connected to the connecting end of the recognition module (3) in a two-way mode, the storage module (7) is used for recording judgment information of the recognition module (3), the gesture judgment module (81) is used for judging the gesture of an examinee manually, and the judgment updating module (82) is used for transmitting the judgment information to the recognition module (3) and updating the judgment standard of the recognition module (3).
10. The examination room cheating behavior pre-judgment system based on examination room posture recognition of claim 1, wherein: the posture judgment module (32) adopts a Mask RCNN-based deep learning algorithm to extract key points of the human body and form a corresponding skeleton structure to realize the detection of the posture of the human body; mask RCNN instance segmentation includes: positioning a target, classifying target categories and predicting a segmented mask; firstly, after a picture is input, extracting a feature map of the picture through a series of convolution and pooling operations by using a feature pyramid network FPN; secondly, the RPN network selects a candidate target on the feature map, a softmax classifier is used for judging whether the candidate target belongs to the background or the foreground, meanwhile, a range frame regressor is used for correcting the position of the candidate target to generate a candidate target area, finally, a Full Convolution Network (FCN) is used for predicting a corresponding target segmentation mask, the classification network uses the feature map and the candidate area generated by the RPN network to realize the detection of the target category, and the FCN uses the feature map to realize the pixel-level accurate segmentation of the target; the motion recognition technology comprises the steps of extracting human body key point information predicted by a network to obtain key point information, then respectively establishing a neck vector, a left shoulder vector, a right shoulder vector, a left arm vector, a right arm vector, a left hand vector, a right hand vector, a left leg vector, a right leg vector, a left foot vector and a right foot vector, and judging motion according to angle and direction information threshold conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010691828.1A CN111738209A (en) | 2020-07-17 | 2020-07-17 | Examination room cheating behavior pre-judging system based on examinee posture recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010691828.1A CN111738209A (en) | 2020-07-17 | 2020-07-17 | Examination room cheating behavior pre-judging system based on examinee posture recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111738209A true CN111738209A (en) | 2020-10-02 |
Family
ID=72654897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010691828.1A Pending CN111738209A (en) | 2020-07-17 | 2020-07-17 | Examination room cheating behavior pre-judging system based on examinee posture recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111738209A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140222995A1 (en) * | 2013-02-07 | 2014-08-07 | Anshuman Razden | Methods and System for Monitoring Computer Users |
| CN106791633A (en) * | 2016-12-14 | 2017-05-31 | 北华航天工业学院 | Intelligence invigilator's system and method |
| CN107491717A (en) * | 2016-06-13 | 2017-12-19 | 科大讯飞股份有限公司 | The detection method that cheats at one's exam and device |
| CN109858457A (en) * | 2019-02-18 | 2019-06-07 | 齐鲁工业大学 | Cheating movement based on OpenPose assists in identifying method and system |
| CN109961000A (en) * | 2018-10-22 | 2019-07-02 | 大连艾米移动科技有限公司 | A kind of intelligence examination hall anti-cheating system |
| CN110837784A (en) * | 2019-10-23 | 2020-02-25 | 中山大学 | Examination room peeping cheating detection system based on human head characteristics |
-
2020
- 2020-07-17 CN CN202010691828.1A patent/CN111738209A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140222995A1 (en) * | 2013-02-07 | 2014-08-07 | Anshuman Razden | Methods and System for Monitoring Computer Users |
| CN107491717A (en) * | 2016-06-13 | 2017-12-19 | 科大讯飞股份有限公司 | The detection method that cheats at one's exam and device |
| CN106791633A (en) * | 2016-12-14 | 2017-05-31 | 北华航天工业学院 | Intelligence invigilator's system and method |
| CN109961000A (en) * | 2018-10-22 | 2019-07-02 | 大连艾米移动科技有限公司 | A kind of intelligence examination hall anti-cheating system |
| CN109858457A (en) * | 2019-02-18 | 2019-06-07 | 齐鲁工业大学 | Cheating movement based on OpenPose assists in identifying method and system |
| CN110837784A (en) * | 2019-10-23 | 2020-02-25 | 中山大学 | Examination room peeping cheating detection system based on human head characteristics |
Non-Patent Citations (2)
| Title |
|---|
| 李川: "智能无人监考考试系统设计与研究", 《电脑知识与技术》 * |
| 福建省高等学校招生委员会办公室: "《福建省高考科研论文集 第3辑》", 31 May 2008 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112036299B (en) | Examination cheating behavior detection method and system under standard examination room environment | |
| CN108549876A (en) | The sitting posture detecting method estimated based on target detection and human body attitude | |
| CN105791299A (en) | Unattended monitoring type intelligent on-line examination system | |
| CN109508656A (en) | A kind of dancing grading automatic distinguishing method, system and computer readable storage medium | |
| CN111563452B (en) | Multi-human-body gesture detection and state discrimination method based on instance segmentation | |
| Hu et al. | Research on abnormal behavior detection of online examination based on image information | |
| CN106023516A (en) | Examination monitoring method and system and examination room monitor | |
| CN104133813A (en) | Navy semaphore training method based on Kinect | |
| CN109086708A (en) | A kind of parking space detection method and system based on deep learning | |
| CN108806371A (en) | A kind of intelligent decision method and system based on Driving Test Subject training | |
| Meijer | Outlier detection in high‐stakes certification testing | |
| CN110148092B (en) | Method for analyzing sitting posture and emotional state of teenager based on machine vision | |
| CN107845300A (en) | A kind of safe examination system monitored in real time | |
| CN112990137B (en) | Classroom student sitting posture analysis method based on template matching | |
| CN110309768A (en) | The staff's detection method and equipment of car test station | |
| CN110559639B (en) | Robot teaching method for gymnastics movement and robot | |
| CN113139962A (en) | System and method for scoliosis probability assessment | |
| CN114038062A (en) | Examinee abnormal behavior analysis method and system based on joint key point representation | |
| CN111523445B (en) | Examination behavior detection method based on improved Openpost model and facial micro-expression | |
| CN111738209A (en) | Examination room cheating behavior pre-judging system based on examinee posture recognition | |
| CN107818707A (en) | A kind of examination system of automatic problem building | |
| Yongcun et al. | Online examination behavior detection system for preschool education professional skills competition based on MTCNN | |
| CN115607153B (en) | Psychological scale answer quality assessment system and method based on eye movement tracking | |
| Owings et al. | Transitions experienced by 1988 eighth graders | |
| CN107967660A (en) | A kind of safe examination system of automatic face identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201002 |
|
| RJ01 | Rejection of invention patent application after publication |