KR20220051515A - An on-line sensing system for identifing examinees and students - Google Patents

Abstract

The present invention relates to an online sensing system, and more specifically, to an online detection system for examinee and student identification, which applies an object recognition function in a CCTV and an analysis function of A.I to an online class/evaluation system, so that the system automatically checks a face shape of the examinee and student, the arrangement of surrounding objects, the flow of time, etc, and thus the system can be used for online and non-face-to-face remote lectures, tests, evaluations, etc., and can be utilized for identification and fraud verification.

Description

{AN ON-LINE SENSING SYSTEM FOR IDENTIFING EXAMINEES AND STUDENTS}

The present invention relates to an online detection system, and more particularly, to an online detection system for examining and student identification that can be used for online and non-face-to-face remote lectures, tests, evaluations, etc. to be utilized for identification and fraud verification.

Recently, due to the influence of COVID-19, offline activities of the public are being restricted.

For this reason, online and non-face-to-face technologies are essential in everyday life. However, there are many cases of abuse of these online and non-face-to-face technologies in negative aspects rather than positive ones.

In particular, in the private sector, lectures/meetings/conferences are conducted online, and in the case of negative abuse of the above in conducting many tests/evaluations, including civil service exams and CSATs, as well as meetings, the test or evaluation itself will be cancelled. There is a problem that cannot proceed.

In the case of Korean Patent Laid-Open Patent No. 10-2020-0012355 "Online lecture monitoring method with face authentication process using CLM and Gabor wavelet", operating the software on a computer and selecting and playing the lecture content through opening a file; detecting a viewing delusion by detecting a face from an input image of a student acquired through a camera, tracking the gaze, and examining the amount of change in eye movement between frames; determining whether the student stares at the screen; When it is determined that the student is gazing at the screen, a face authentication step of preventing a substitute lecture or attendance through the face authentication of the student; When the lecture content is being reproduced, if the student's face and pupil are detected, the number of staring screens increases by determining whether the student's face and pupil are detected. increasing the number of screens and displaying a warning light on the lecture content screen; Divide the internal product cumulative average by the number of gradient vectors to obtain the corrected internal product cumulative average value, and receive the corrected internal product cumulative average values of the previous frame and the current frame and perform Kalman filtering to obtain the corrected internal product cumulative average value of the current frame determining whether the eyes are opened or closed by updating the . And in real time, the total number of screens played so far, the number of stared screens confirmed by eye tracking, the screen stare rate that is the ratio of the number of stared screens to the total number of screens, and the number of viewing dazzle and stare screens that are the ratio of the number of deceptive screens to the total number of screens An online lecture monitoring method comprising the step of displaying the final learning rate, which is the ratio of the number of deceptive screens and the total number of screens." is disclosed.

In addition, in the case of Korean Patent Laid-Open Patent No. 10-2016-0053155 "Method of preventing cheating in e-learning using face recognition technology including photo face identification", a Learning Management System (LMS) that performs online distance education and It interlocks and secures the learner's face image in real time through the USB camera connected to the learner's PC. Disclosed is a method that can fundamentally block surrogate attendance by others, negligence in class attitude while taking an online test, and proxy test in the case of an online test by determining whether it is recognized in real time. To this end, it consists of a USB camera, a module for image preprocessing, a module for determining a photographic face, a module for detecting a normal face, a module for recognizing a face, and a statistical process server.

In addition, in the case of Republic of Korea Patent Registration No. 10-1879229 "Online lecture system and method to which eye tracking technology is applied", the software is operated on the computer, the lecture content is selected and played by opening the file, and from the input image of the learner acquired through the camera Detecting the face and tracking the gaze to detect viewing delusion, determining whether the student stares at the screen, and as a result of the determination, when the student's face and pupil are detected while the lecture content is being played, the number of staring screens increases, If the face and pupil of the student are not detected, it is determined that the screen is not stared, the number of non-gazing screens increases, and an online lecture method to which an eye tracking technology is applied to display a warning light on the lecture content screen is disclosed.

In addition, in the case of Korean Patent Registration No. 10-1619656 "Gaze tracking device and method for detecting pupil thereof," information about the pupil in the currently acquired eye image is predicted based on the pupil information detected in the previous eye image when the pupil is detected for eye tracking. And it relates to a gaze tracking device capable of improving accuracy by detecting a pupil based on the predicted pupil information, and a pupil detection method thereof, which receives an eye image through a camera, and the pupil state (position and size) in the eye image. ) is predicted, then a pupil candidate is selected from the eye image, and a pupil candidate most similar to the pupil state among the pupil candidates is detected as a pupil.

However, in conducting tests, learning and evaluation in various fields, many problems such as departure of test takers, proxy progress during evaluation, and unauthorized open book tests occur, but in reality, it is difficult to verify them, and accordingly There is a problem that the objectivity and fairness of testing, learning and evaluation cannot be guaranteed.

Republic of Korea Patent Publication 10-2020-0012355 Republic of Korea Patent Publication 10-2016-0053155 Republic of Korea Patent Registration 10-1879229 Republic of Korea Patent Registration 10-1619656

The purpose of the present invention to solve the above problems is to apply the object recognition function in CCTV and the analysis function of A.I to the online class/evaluation system, so that the face shape of the examinees and students, the arrangement of surrounding objects, and the flow of time The purpose of this system is to provide an online detection system for examining and student identification that can be used for identification and misconduct verification by automatically checking the system.

In order to achieve the above object, the present invention comprises: an image acquisition unit for acquiring an image of a user; a storage unit for storing the user's image first acquired from the image acquisition unit, images of surrounding objects, and time information at the time of image acquisition; a first sensing unit for recognizing the user's face and location from the user's image information acquired by the image acquisition unit; a first control unit comparing the user's face and location recognized by the first sensing unit with an initial image of the user stored in the storage unit; a second detection unit for extracting a main object as a reference from the image information of the surrounding objects obtained by the image acquisition unit; a second control unit for comparing the images of the main object recognized by the second sensing unit with the images of the surrounding objects stored in the storage unit; a third detection unit for recognizing a state in which a preset time has elapsed from the time information obtained at the time of image acquisition obtained by the image acquisition unit; After a preset time recognized by the third detection unit elapses, the acquisition of information from the first and second detection units and the acquisition of comparative information from the first and second control units are repeatedly performed again characterized in that

The effect of the present invention according to the above configuration is that it is possible in real time to confirm the identity of the learner and to confirm the departure of the trainee during the online video/live lecture, and accordingly, check the fraudulent behavior and the person to be evaluated during the online video/live evaluation It has the advantage of being able to confirm the replacement of

Therefore, the operator spends a lot of time and money to build the online education system, but in the end, for the test evaluation, it is conducted offline, the same as the existing test management/supervisor labor cost, offline test space rental costs, etc. can be reduced

From the point of view of the consumer, in the evaluation part after completing the online class, the part that had to be conducted offline in the same way as before is improved and the occurrence of time and physical costs can be reduced.

1 is a schematic diagram showing an online sensing system for identification of examinees and students of the present invention.

Hereinafter, the present invention will be described with reference to the accompanying drawings. However, the present invention may be embodied in several different forms, and thus is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be “connected (connected, contacted, coupled)” with another part, it is not only “directly connected” but also “indirectly connected” with another member interposed therebetween. "Including cases where

The terminology used herein is used only to describe specific embodiments, and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise.

In the present specification, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The present inventors include: an image acquisition unit for acquiring an image of a user; a storage unit for storing the user's image first acquired from the image acquisition unit, images of surrounding objects, and time information at the time of image acquisition; a first sensing unit for recognizing the user's face and location from the user's image information acquired by the image acquisition unit; a first control unit comparing the user's face and location recognized by the first sensing unit with an initial image of the user stored in the storage unit; a second detection unit for extracting a main object as a reference from the image information of the surrounding objects obtained by the image acquisition unit; a second control unit for comparing the images of the main object recognized by the second sensing unit with the images of the surrounding objects stored in the storage unit; a third detection unit for recognizing a state in which a preset time has elapsed from the time information obtained at the time of image acquisition obtained by the image acquisition unit; After a preset time recognized by the third detection unit elapses, the acquisition of information from the first and second detection units and the acquisition of comparative information from the first and second control units are repeatedly performed again characterized in that

More specifically, it is possible to provide and configure an online detection system for examining and student identification that can be used for online and non-face-to-face remote lectures, tests, and evaluations, which can be used for identification and fraud verification.

In the past, many problems have occurred in conducting tests, learning, and evaluation in various fields, such as departure of examinees, proxy progress during evaluation, and unauthorized open book tests, but in reality, it is difficult to verify them. There is a problem that the objectivity and fairness of testing, learning and evaluation cannot be guaranteed.

Therefore, if the present inventor uses the online detection system for examining and student identification, the object recognition function in CCTV and the analysis function of A.I are applied to the online class/evaluation system, and the face shape of the examinee and student, the arrangement of surrounding objects, As the system automatically checks the passage of time, it can be used for identification and fraud verification.

In other words, during online video/live lectures, it is possible to confirm the identity of the learner and to confirm the departure of the learner in real time. Accordingly, there is an advantage in that it is possible to check the fraudulent behavior and check the replacement of the person to be evaluated during the online video/live evaluation.

Therefore, the operator spends a lot of time and money to build the online education system, but in the end, for the test evaluation, it is conducted offline, the same as the existing test management/supervisor labor cost, offline test space rental costs, etc. can be reduced

From the point of view of the consumer, in the evaluation part after completing the online class, the part that had to be conducted offline in the same way as before is improved and the occurrence of time and physical costs can be reduced.

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the following claims, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention.

Claims (1)

an image acquisition unit for acquiring an image of a user;
a storage unit for storing an image of a user first acquired from the image acquisition unit, an image of surrounding objects, and time information at the time of image acquisition;
a first detection unit for recognizing the user's face and location from the user's image information acquired by the image acquisition unit;
a first control unit comparing the user's face and location recognized by the first sensing unit with an initial image of the user stored in the storage unit;
a second detection unit for extracting a main object as a reference from the image information of the surrounding objects obtained by the image acquisition unit;
a second control unit for comparing the images of the main object recognized by the second sensing unit with the images of the surrounding objects stored in the storage unit;
a third sensing unit for recognizing a state in which a preset time has elapsed from the time information obtained at the time of image acquisition obtained by the image acquisition unit;
After a preset time recognized by the third detection unit elapses, the acquisition of information from the first and second detection units and the acquisition of comparative information from the first and second control units are repeatedly performed again Online detection system for examining and student identification, characterized in that.

Images