CN113516074A - Online examination system anti-cheating method based on pupil tracking - Google Patents
Online examination system anti-cheating method based on pupil tracking Download PDFInfo
- Publication number
- CN113516074A CN113516074A CN202110774658.8A CN202110774658A CN113516074A CN 113516074 A CN113516074 A CN 113516074A CN 202110774658 A CN202110774658 A CN 202110774658A CN 113516074 A CN113516074 A CN 113516074A
- Authority
- CN
- China
- Prior art keywords
- pupil
- cheating
- range
- screen
- points
- 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
- 210000001747 pupil Anatomy 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 44
- 210000001508 eye Anatomy 0.000 claims abstract description 50
- 230000008859 change Effects 0.000 claims description 20
- 238000012360 testing method Methods 0.000 claims description 8
- 210000003128 head Anatomy 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 17
- 230000002159 abnormal effect Effects 0.000 description 16
- 210000000554 iris Anatomy 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000006073 displacement reaction Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000004424 eye movement Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 208000003028 Stuttering Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000004018 waxing Methods 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention discloses an anti-cheating method of an online examination system based on pupil tracking, and belongs to the field of image processing. Aiming at the problem that the on-line invigilation is not in place in the anti-cheating method for the examination in the existing on-line system, the invention provides a pupil tracking invigilation method, which comprises the following steps: 1. acquiring the pupil position; 2. calibrating a screen range; 3. constructing a vector relation between a screen range and a focus position range of two eyes; 4. the pupil is tracked and whether cheating exists is determined. The method judges whether cheating is caused by tracking the pupil and utilizing the image frame difference information, so that the waste of human resources is reduced, and the method is more accurate.
Description
Technical Field
The invention relates to the field of image processing, in particular to an anti-cheating method based on a pupil tracking technology.
Background
Aiming at the problem of cheating prevention of an online examination system, a plurality of methods are provided for dealing with by a plurality of online examination platforms. For example, methods such as locking a screen and shielding a hot key are commonly used to prevent students from cheating by means such as switching search engines during an examination; moreover, double machine positions are erected in front of and behind the students, the behaviors of the students are observed from different angles through the double machine positions, and teachers supervise the whole course to prevent the students from cheating.
In 2008, a paper grouping algorithm is proposed to prevent cheating in pottery summer and old flood, and in order to solve the problem that an examinee can easily see answers of others due to a relatively close seat, the traditional paper grouping mode is changed, and an algorithm is proposed to randomly select test questions. Furthermore, the subject options are also randomly arranged. However, the method is only effective when the examinees are in a unified place and the teachers invigilate the examination, and good anti-cheating effect is difficult to achieve when examination environments are different and the teachers can invigilate the examination only in a video mode.
In 2017, in the morning and the like, a network examination system is provided, in order to solve the problem that examinees concentrate on a semi-closed environment of one or more examination points, a C/S + B/S hybrid architecture is adopted, and a client side is responsible for controlling a window, shielding hot keys, monitoring evidence obtaining and other functions. However, the system cannot monitor the examination process of the examinees in real time, and the anti-cheating effect is not ideal.
In 2020, the Liujuan and Dong dong propose a paperless examination cheating-preventing method and a supervision method of a paperless examination system, and whether cheating behaviors exist is comprehensively judged by combining eye movement data with manual data and a current answer area. However, when the method is used for acquiring the eye movement data, the abnormal sight line range is recorded through the time stamp, so that the pupil information on a time unit is easily lost, the change of the pupil cannot be monitored in real time, and the error rate is large.
In 2021, Sunzhongdan and Waxing propose a dispersive network examination anti-cheating system based on a panoramic intelligent method, and an anti-cheating information examination system with unmanned supervision and deployment, dead-angle-free teaching and examination environment monitoring, remote automatic anti-cheating behavior monitoring, cheating auxiliary judgment and reminding, field review and evidence persistence is designed by combing a dispersive network examination business process and utilizing the advantages of a panoramic intelligent technology. However, this method requires the examinee to be equipped with a panoramic intelligent device, which is not practical for most examinees. In addition, before the examination, the method needs a patrol inspector to assist in adjusting the angle of the equipment and other series of examination work, which is complicated.
Disclosure of Invention
The invention provides an anti-cheating method of an online examination system based on pupil tracking.
The technical scheme of the invention mainly comprises the following steps: step 1: acquiring the pupil position; step 2: calibrating a screen range; and step 3: constructing a vector relation between a screen range and a focus position range of two eyes; and 4, step 4: the pupil is tracked and whether cheating exists is determined.
In particular, the implementation method of step 1 is as follows: preprocessing the acquired image, removing noise in the image, and performing gray level conversion; roughly positioning a human face and a human eye area in the gray level image, finely positioning the position of a pupil in the human eye image, and respectively recording as (P) according to the left eye and the right eyeLx,PLy)、(PRx,PRy)。
In particular, the implementation method of step 2 is as follows: four points A1, A2, A3 and A4 with equal size are respectively displayed at the upper left corner, the upper right corner, the lower left corner and the lower right corner of the screen area; keeping the head of the student still at a position which is a distance D relative to the screen, and looking at the screen to obtain a point A5; then points of fixation a1, a2, A3, a4, respectively.
In particular, the implementation method of step 3 is as follows: obtaining coordinates when the pupil watches the upper left corner, the upper right corner, the lower left corner and the lower right corner of the screen area according to the four marked points A1, A2, A3 and A4, taking the point A5 as an origin, and drawing a line to obtain the maximum change rectangular RANGE of the PUPIL, and recording as PUPIL _ RANGE.
In particular, the implementation method of step 4 is as follows: obtaining the pupil change position C (C) of the student in the examination in real timex,Cy) Comparing with PUPIL _ RANGE obtained in claim 3, if C (C)x,Cy) Being outside the PUPIL RANGE means the line of sight is moving outside the screen, whereas it is inside the screen. And setting a protection mechanism to judge the cheating behavior, judging the cheating behavior if 30 continuous points are outside the PUPIL _ RANGE and the watching frequency exceeds the specified frequency, and forcibly submitting the test paper by the system, otherwise, judging the test is in a normal state.
The invention has the following effects: an effective anti-cheating method of an online examination system is provided. The method comprises the steps of obtaining a pupil watching position, finding out the maximum range of a pupil watching device screen, judging whether pupil change is within the range to obtain abnormal sight points, and judging whether cheating behaviors exist or not according to whether frame difference abnormal sight points are continuous or not and the watching times. According to the invention, the screen range corresponds to the pupil change range through inward projection, and compared with a method for searching a fixation point through outward projection, the method is simpler; compared with the anti-cheating technology of the existing online education system, the anti-cheating method provided by the invention is more flexible and effective, and a large amount of human resources are saved.
Drawings
FIG. 1 is a block diagram
FIG. 2 pupil location chart
FIG. 3 is a schematic diagram of a calibration screen range
FIG. 4 is a diagram illustrating pupil variation range
FIG. 5 is a diagram of a non-cheating action sight-line trajectory
FIG. 6 is a diagram of a line-of-sight trajectory for cheating
Detailed Description
The invention will now be described in more detail with reference to the drawings in the following description.
The specific implementation of the invention is divided into 4 steps, which are respectively as follows: step 1: acquiring the pupil position; step 2: calibrating a screen range; and step 3: constructing a vector relation between a screen range and a focus position range of two eyes; and 4, step 4: the pupil is tracked and whether cheating exists is determined. The structure of the method is shown in figure 1 in the description of the attached drawings.
An anti-cheating method of an online examination system based on pupil tracking comprises the following specific steps:
(1) obtaining pupil position
After the frame image of the video is obtained, the image is preprocessed, and the color image is converted into a single-channel gray image. The gray level image is beneficial to the identification of the eyes and the pupils by a subsequent algorithm, the data volume is reduced, and the identification efficiency is improved. And carrying out median filtering on the gray level image, removing the noise of the image and clearing the edge of the image.
The human face and the human eyes are positioned, the interference of the video background to the pupil identification can be eliminated, and only one target circle, namely the iris, is found.
Using opencv software library to perform face recognition to obtain the coordinates (F) of the upper left corner point of the target face region positionx,Fy) And width and height values Fw、Fh. From the coordinates (F) of four pointsx,Fy)、(Fx+Fw,Fy)、(Fx,Fy+Fh)、(Fx+Fw,Fy+Fh) The position of the target eye is circled on the image. The four points are respectively the upper left corner, the upper right corner, the lower left corner and the lower right corner of the human face area.
Positioning human eyes in the target human face area to obtain the coordinates (E) of the upper left corner point of the position of the target human eye areax,Ey) And a width and height value Ew、Eh. From the coordinates of four points (E)x,Ey),(Ex+Ew,Ey),(Ex,Ey+Eh),(Ex+Ew,Ey+Eh) The position of the target eye is circled on the image. The four points are respectively the upper left corner, the upper right corner, the lower left corner and the lower right corner of the human eye region.
The human face features are natural and proportional. According to the conventional face features, on the assumption that a person is facing the screen, the eyes have structural features similar to the mouth, and the eyes are located in the upper half of the face region. The left and right eyes are located on the left and right sides of the face region, respectively. According to this feature, with eye _ TAG as the eye flag, eye _ TAG as the left eye flag, and eye _ TAG as the right eye flag, there are:
S1:(Ey+Eh)÷2<Fhwhen 2 is TRUE, EYES _ TAG is TRUE.
Description of S1: the target whose eye height center is above the face height center is treated as the eye, otherwise, the target is judged as the mouth, and the area is discarded.
S2:(Ex+Ew)÷2<FwWhen 2 is TRUE, LEYES _ TAG is TRUE;
(Ex+Ew)÷2>Fwwhen 2 is TRUE, REYES _ TAG is TRUE.
Description of S2: and judging the target with the width midpoint of the eye area smaller than the width center position of the face as a left eye, otherwise, judging the target as a right eye. The height midpoint and the width midpoint of the eye area are taken as threshold values to be compared, so that the position of the eye can be accurately represented, and the identification accuracy is improved.
The position of the center of the pupil is actually the center of the iris. Under normal conditions, when the human eye looks upright, the iris is a regular perfect circle, and when the eye rotates, the shape of the iris is an ellipse.
And carrying out binarization processing on the gray human eye image to clearly and respectively obtain the shape of the iris.
According to the difference of the iris shape, different algorithms are used for solving the central position of the pupil, and the method specifically comprises the following steps:
s1: when the eyes look at the screen, the irises are regular circles, and the center positions of the circles are detected through Hough gradient circle transformation.
opencv supports Hough gradient circle transformation to detect the circle center. The general equation for a circle is as follows:
(x-a)2+(y-b)2=r2
wherein (a, b) are coordinates of the center of a circle, and r is a radius. The maximum range and the minimum range of the radius are specified, the calculation of the three-dimensional space is converted into the calculation on the two-dimensional plane, and the calculation amount is reduced.
Firstly, edge detection is carried out on the human eye area by using a canny algorithm to obtain boundary points of an image; calculating the gradient of each non-zero point on the edge image by using a sobel operator; drawing line segments in the gradient direction x and the opposite direction y of the circular arc; and (4) each point in the line segment is sent into an accumulator, all points in the accumulator are sorted finally, and the point with the largest vote number is the center of the circle.
S2: the iris shape of the video acquisition is generally elliptical as the eye rotates. And fitting the ellipse by adopting a least square algorithm, and solving the center of the ellipse, namely the center position of the pupil. Firstly, extracting edge information of an image, storing possible boundary points in a sample set, and then constructing a loss function, wherein the general equation of an ellipse is as follows:
Ax2+Bxy+Cy2+Dx+Ey+1=0
the loss function is then:
the conversion into a matrix is as follows:
is recorded as:
An upward and downward drawing line is displayed in the human eye region image with the obtained pupil coordinate point as a center. As shown in fig. 2 in the description of the drawings, a diagram (a) is a pupil position in a grayscale human eye image, and a diagram (b) is a pupil position in a morphologically transformed image.
(2) Demarcating the scope of a screen
As shown in 3 in the figure description, four equal-size points a1, a2, A3 and a4 are respectively displayed at the upper left corner, the upper right corner, the lower left corner and the lower right corner of the screen area; keeping the head of the student still at a position which is a distance D relative to the screen, and looking at the screen to obtain a point A5; then, in order to accurately obtain the range, the students must click the fixation points a1, a2, A3 and a4, respectively, and after clicking, the fixation points disappear, which means that the fixation of the points is completed, and the calibration is completed. Obtaining coordinates of the pupil when gazing at the upper left corner, the upper right corner, the lower left corner and the lower right corner of the screen area according to four gazing points A1, A2, A3 and A4, and recording the coordinates of the pupil of the left eye as the coordinatesThe locus of the right eye pupil is markedWherein: i is 1, 2, 3, 4, 5. Respectively represent the coordinates of the pupil when looking at the upper left corner, the upper right corner, the lower left corner, the lower right corner and the front view screen. When the left eye and the right eye watch a point, two similar and different images are seen, in order to simulate brain image fusion and well reflect the displacement vector change when the pupils rotate, the midpoint of the connecting line of the pupils of the two eyes is used as a sight line point and is marked as a point 1, 2, 3, 4, 5, then:
(3) constructing a vector relationship between a screen range and a binocular focus position range
As shown in figure 4 of the accompanying drawings: at point C5Establishing a rectangular coordinate system for the origin, the maximum variation rectangular RANGE of the PUPIL, denoted PUPIL _ RANGE, is obtained by drawing lines connecting points C1, C2, C3, and C4.
Will point CiThe displacement change of the screen is displayed in a coordinate axis, and the range of the pupil center position change is obtained when the screen is at a fixed distance relative to human eyes. This range defines the maximum displacement of the pupil change when the person looks at the screen by eyeball rotation on a head-motionless basis.
(4) Determining whether there is a cheating action
And after the fixation point is calibrated, the maximum displacement of the pupil which can be changed in the fixation screen range is obtained. The student keeps the head still and the equipment camera in the examination processAcquiring the position change of the pupil in real time, and processing and analyzing the position of the pupil in the frame image to obtain the position C (C) of the pupil change of the student in the examinationx,Cy). The locus of point C is shown in the RANGE of PUPIL variation, which can be clearly compared to PUPIL _ RANGE if C (C)x,Cy) When the point belongs to one point in the PUPIL _ RANGE, the sight line is not moved out of the screen; if the sight line is moved out of the screen, then C (C)x,Cy) And also out of the PUPIL RANGE.
A protection mechanism is used to judge whether the current behavior belongs to a cheating behavior and give a corresponding anti-cheating processing result. By taking the watching time and the number of times of moving out of the range as judgment conditions, cheating behaviors can be better expressed.
(1) When the pupil change point in the current frame image moves out of the range, the current frame is recorded, and the position 1 is marked.
(2) When the pupil change point in the current frame image is out of range, mark position 0, and clear the record in (1).
(3) And circularly judging the position of the pupil change point in the next frame of image.
(4) And if the sight point beyond the range exists in the records of the continuous 30 frames of images, adding 1 to the abnormal number record, and setting a bullet frame for reminding.
(5) And (4) limiting the abnormal times, if the abnormal times exceed a specified value, judging the cheating behavior, forcibly submitting test paper by the online education system, and ending the current test.
Recording abnormal sight points in the frame images, if the abnormal sight points exist in the continuous 30 frames of images, the time for the sight to fall outside the screen exceeds 1s, and the cheating behavior can be judged; if abnormal points exist in the 30 discontinuous images, the abnormal points represent the conditions that the time outside the watching screen is too short, the sight point in a certain image deviates out of the range due to the error of pupil positioning, and the like, the influence on the examination state is small, and the cheating behavior is not formed.
The maximum allowable abnormal times is set by combining the abnormal times, so that the wrong judgment that the sight line leaves the screen unconsciously due to the reasons of student stutter or thinking and the like is reduced. When the abnormal times exceed the set specified value, the current behavior is judged to belong to the cheating behavior, and the examination paper can be submitted through the mandatory behavior of the online examination system, so that the aim of preventing cheating of the system is fulfilled.
The first embodiment is as follows:
in this example, a simulation experiment of system anti-cheating was performed, and the experiment was performed to perform pupil monitoring analysis on cheating behaviors and non-cheating behaviors respectively. The specific process is as follows:
the head is horizontally 30 centimeters away from the screen, under the condition of keeping the head still, the fixation points of the upper left corner, the upper right corner, the lower left corner and the lower right corner of the screen are clicked in sequence for marking, and the time difference between the two points is more than 1 s. After clicking, the point of regard disappears, representing that the point mark is complete. In the marking process, according to the position change of the pupil, the midpoint C of the connecting line of the pupils of the two eyes is taken as a sight point, and the coordinate positions of the sight point when the sight point respectively watches four corners of the screen are obtained. To be provided withLine is drawn, wherein(i ═ 1, 2, 3, 4) represents the coordinate values when the gaze point is looking at the top left, top right, bottom left, and bottom right of the screen, respectively, and the maximum change RANGE PUPIL _ RANGE of the PUPIL is obtained. A new window is created, as well as blank pictures, and PUPIL _ RANGE is displayed in the pictures and saved.
The line of sight is held within the screen for a period of time and the eye quickly sweeps out of the screen and falls back into the screen. The sight line locus is shown in figure 5 in the description of the drawing, the rectangular box is the PUPIL change RANGE PUPIL _ RANGE, and the irregular line is the locus of the PUPIL change in the fixation process. Only two points in the figure fall outside the PUPIL _ RANGE, and the exception flag position 1 clears the exception record when the next point returns to the inside of the PUPIL _ RANGE, so that the examination can be continued without cheating.
The gaze is directed into the screen for a period of time, the gaze moves out of the screen and is directed to an object outside the screen. The sight line track is as shown in figure 6 in the description of the attached drawings, track points of 50 frames of images are recorded, more than 30 continuous track points are out of the PUPIL _ RANGE, cheating is judged, and the number of abnormal times is added by 1.
Setting the maximum abnormal times of the examination system to be 5, monitoring and recording pupil displacement information in real time, moving the sight line out of the screen for many times, and when the abnormal times exceed the maximum limit value, submitting test paper by the system and ending the examination.
The above examples are merely illustrative of the present invention and should not be construed as limiting the scope of the invention, which is intended to be covered by the claims as well as any design similar or equivalent to the scope of the present invention.
Claims (5)
1. An anti-cheating method of an online examination system based on pupil tracking is characterized by comprising the following steps:
step 1: acquiring the pupil position;
step 2: calibrating a screen range;
and step 3: constructing a vector relation between a screen range and a focus position range of two eyes;
and 4, step 4: the pupil is tracked and whether cheating exists is determined.
2. The online anti-cheating system based on sight tracking according to claim 1, wherein the method comprises the following steps: the implementation method of the step 1 comprises the following steps: preprocessing the acquired image, removing noise in the image, and performing gray level conversion; roughly positioning a human face and a human eye area in the gray level image, finely positioning the position of a pupil in the human eye image, and respectively recording as (P) according to the left eye and the right eyeLx,PLy)、(PRx,PRy)。
3. The online anti-cheating system based on sight tracking according to claim 1, wherein the method comprises the following steps: the implementation method of the step 2 is as follows: four points A1, A2, A3 and A4 with equal size are respectively displayed at the upper left corner, the upper right corner, the lower left corner and the lower right corner of the screen area; keeping the head of the student still at a position which is a distance D relative to the screen, and looking at the screen to obtain a point A5; then points of fixation a1, a2, A3, a4, respectively.
4. The online anti-cheating system based on sight tracking according to claim 1, wherein the method comprises the following steps: the implementation method of the step 3 is as follows: obtaining coordinates of the upper left corner, the upper right corner, the lower left corner and the lower right corner of the pupil watching screen area according to the four watching calibration points A1, A2, A3 and A4, taking the point A5 as an origin,and drawing a line to obtain the maximum change rectangular RANGE of the PUPIL, and recording as PUPIL _ RANGE.
5. The online anti-cheating system based on sight tracking according to claim 1, wherein the method comprises the following steps: the implementation method of the step 4 is as follows: obtaining the pupil change position C (C) of the student in the examination in real timex,Cy) Comparing with PUPIL _ RANGE obtained in claim 4, if C (C)x,Cy) Being outside the PUPIL RANGE means the line of sight is moving outside the screen, whereas it is inside the screen. And setting a protection mechanism to judge the cheating behavior, judging the cheating behavior if 30 continuous points are outside the PUPIL _ RANGE and the watching frequency exceeds the specified frequency, and forcibly submitting the test paper by the system, otherwise, judging the test is in a normal state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110774658.8A CN113516074A (en) | 2021-07-08 | 2021-07-08 | Online examination system anti-cheating method based on pupil tracking |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110774658.8A CN113516074A (en) | 2021-07-08 | 2021-07-08 | Online examination system anti-cheating method based on pupil tracking |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113516074A true CN113516074A (en) | 2021-10-19 |
Family
ID=78066669
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110774658.8A Pending CN113516074A (en) | 2021-07-08 | 2021-07-08 | Online examination system anti-cheating method based on pupil tracking |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113516074A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016177475A (en) * | 2015-03-19 | 2016-10-06 | 京セラドキュメントソリューションズ株式会社 | Monitor system |
CN110874585A (en) * | 2019-11-28 | 2020-03-10 | 西安云海信息技术有限责任公司 | Peeping cheating behavior identification method based on attention area |
CN112070024A (en) * | 2020-09-09 | 2020-12-11 | 常州纺织服装职业技术学院 | Anti-cheating method for paperless examination and invigilating method for paperless examination system |
WO2021098454A1 (en) * | 2019-11-21 | 2021-05-27 | 深圳云天励飞技术股份有限公司 | Region of concern detection method and apparatus, and readable storage medium and terminal device |
CN113011278A (en) * | 2021-02-25 | 2021-06-22 | 深圳市讯方技术股份有限公司 | Online examination anti-cheating method and device and electronic equipment |
-
2021
- 2021-07-08 CN CN202110774658.8A patent/CN113516074A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016177475A (en) * | 2015-03-19 | 2016-10-06 | 京セラドキュメントソリューションズ株式会社 | Monitor system |
WO2021098454A1 (en) * | 2019-11-21 | 2021-05-27 | 深圳云天励飞技术股份有限公司 | Region of concern detection method and apparatus, and readable storage medium and terminal device |
CN110874585A (en) * | 2019-11-28 | 2020-03-10 | 西安云海信息技术有限责任公司 | Peeping cheating behavior identification method based on attention area |
CN112070024A (en) * | 2020-09-09 | 2020-12-11 | 常州纺织服装职业技术学院 | Anti-cheating method for paperless examination and invigilating method for paperless examination system |
CN113011278A (en) * | 2021-02-25 | 2021-06-22 | 深圳市讯方技术股份有限公司 | Online examination anti-cheating method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108427503B (en) | Human eye tracking method and human eye tracking device | |
EP3355104B1 (en) | Method and device and computer program for determining a representation of a spectacle glass rim | |
CN110197169B (en) | Non-contact learning state monitoring system and learning state detection method | |
WO2023011339A1 (en) | Line-of-sight direction tracking method and apparatus | |
CN105224285A (en) | Eyes open and-shut mode pick-up unit and method | |
CN107656619A (en) | A kind of intelligent projecting method, system and intelligent terminal | |
CN109782902A (en) | A kind of operation indicating method and glasses | |
CN105243386A (en) | Face living judgment method and system | |
CN112101123B (en) | Attention detection method and device | |
CN110543848B (en) | Driver action recognition method and device based on three-dimensional convolutional neural network | |
CN111898553B (en) | Method and device for distinguishing virtual image personnel and computer equipment | |
CN111563449A (en) | Real-time classroom attention detection method and system | |
CN111382672A (en) | Cheating monitoring method and device for online examination | |
EP3819815A1 (en) | Human body recognition method and device, as well as storage medium | |
CN111898552B (en) | Method and device for distinguishing person attention target object and computer equipment | |
CN107256375A (en) | Human body sitting posture monitoring method before a kind of computer | |
CN113221815A (en) | Gait identification method based on automatic detection technology of skeletal key points | |
CN116453198B (en) | Sight line calibration method and device based on head posture difference | |
CN110598635B (en) | Method and system for face detection and pupil positioning in continuous video frames | |
CN113516074A (en) | Online examination system anti-cheating method based on pupil tracking | |
CN113569594A (en) | Method and device for labeling key points of human face | |
Sahay et al. | Webcam based eye gaze tracking using a landmark detector | |
CN113920563A (en) | Online examination cheating identification method and device, computer equipment and storage medium | |
CN116894978B (en) | Online examination anti-cheating system integrating facial emotion and behavior multi-characteristics | |
CN111241870A (en) | Terminal device and face image recognition method and system thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211019 |