MINISTRY OF EDUCATION AND TRAINING HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION ELECTRONICS AND COMMUNICATIONS ENGINEERING TECHNOLOGY DESIGN OF AUTOMATIC ATTENDANCE REGISTER AND STUDENT CONCENTRATION LEVEL MONITORING SYSTEM LECTURER: TRUONG NGOC SON STUDENT: LE XUAN TUAN DAT TRUONG KHAC HUY SKL 009328 Ho Chi Minh City, August 2020 HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION FACULTY FOR HIGH QUALITY TRAINING GRADUATION THESIS MAJOR: ELECTRONICS AND COMMUNICATIONS ENGINEERING TECHNOLOGY DESIGN OF AUTOMATIC ATTENDANCE REGISTER AND STUDENT CONCENTRATION LEVEL MONITORING SYSTEM ADVISOR: Assoc. TRUONG NGOC SON STUDENT: LE XUAN TUAN DAT – 18161056 TRUONG KHAC HUY – 18161016 HO CHI MINH CITY – 08/2022 HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY AND EDUCATION FACULTY FOR HIGH QUALITY TRAINING GRADUATION THESIS MAJOR: ELECTRONICS AND COMMUNICATIONS ENGINEERING TECHNOLOGY DESIGN OF AUTOMATIC ATTENDANCE REGISTER AND STUDENT CONCENTRATION LEVEL MONITORING SYSTEM ADVISOR: Assoc. TRUONG NGOC SON STUDENT: LE XUAN TUAN DAT – 18161056 TRUONG KHAC HUY – 18161016 HO CHI MINH CITY – 08/2022 THE SOCIALIST REPUBLIC OF VIETNAM Independence – Freedom– Happiness ----***---- Ho Chi Minh City, August 7th, 2022 GRADUATION THESIS ASSIGNMENT Student name: Le Xuan Tuan Dat Student ID: 18161056 Student name: Truong Khac Huy Student ID: 18161016 Major: Electronics and Communications Engineering Technology Class: 18161CLA Advisor: Assoc. Truong Ngoc Son Date of assignment: Date of submission: 1.
Thesis title: Design of automatic attendance register and student concentration level monitoring system. Initial materials provided by the advisor 3. Content of the thesis: - Refer to the document, read and summarize to find the development direction of the thesis. - Flow chart design and description them.
- Running and testing the system for completion. - Write a report and prepare slides. Final product: The GUI uses two different models to attend to students using face recognition and tracks or monitors pupils of students in the classroom. CHAIR OF THE PROGR ADVISOR (Sign with full name) (Sign with full name) THE SOCIALIST REPUBLIC OF VIETNAM Independence – Freedom– Happiness ----***---- Ho Chi Minh City, August 7th, 2022 ADVISOR’S EVALUATION SHEET Student name: Le Xuan Tuan Dat Student ID: 18161056 Student name: Truong Khac Huy Student ID: 18161016 Major: Electronics and Communications Engineering Technology Thesis title: Design of automatic attendance register and student concentration level monitoring system.
Truong Ngoc Son EVALUATION 1. Content of the thesis: - Thesis has 5 chapters with 54 pages. - Design of student attendance using face recognition and concentration tracking system. - The GUI model is successfully completed following the objectives in the proposal.
Approval for oral defense? (Approved or denied) .) Ho Chi Minh City, August 7th, 2022 ADVISOR (Sign with full name) THE SOCIALIST REPUBLIC OF VIETNAM Independence – Freedom– Happiness ----***---- Ho Chi Minh City, August 7th, 2022 PRE-DEFENSE EVALUATION SHEET Student name: Le Xuan Tuan Dat Student ID: 18161056 Student name: Truong Khac Huy Student ID: 18161016 Major: Electronics and Communications Engineering Technology Thesis title: Design of automatic attendance register and student concentration level monitoring system. Name of Reviewer: Ph.D Do Duy Tan 1. Content and workload of the thesis:. Approval for oral defense? (Approved or denied) .…) REVIEWER ACKNOWLEDGE The most crucial phase of every student's life is the process of finishing their graduation thesis.
The purpose of our graduation thesis is to provide us with essential information and research skills in preparation for our careers. First of all, we would like to thank Ho Chi Minh City University of Technology and Education. Particularly, during our time in the lecture hall, the professors of the Faculty of High-Quality Training passionately instructed and prepared us with vital information, providing the groundwork for our ability to finish the thesis. We want to express our gratitude to Assoc.
Truong Ngoc Son for his passionate assistance and guidance in terms of scientific thinking and effort. Those are some really helpful ideas, both for the creation of this thesis and as a stepping stone for our future studies and job development. Our team is hoping that Assoc. Truong Ngoc Son and the teachers would empathize and offer advice on how to improve if something is missing from the project.
HO CHI MINH CITY - 08/2022 APPROVAL Thesis title: Design of automatic attendance register and student concentration level monitoring system Advisor: TRUONG NGOC SON, Assoc. Student 1: LE XUAN TUAN DAT Student’s ID: 18161056 Class: 18161CLA1 Email: 18161056@student.vn Student 2: TRUONG KHAC HUY Student’s ID: 18161016 Class: 18161CLA2 Email: 18161016@student.vn “We commit not to copy or reuse the results of other people's work as part of the graduation project. A complete list of references has been provided.” Ho Chi Minh City, August 7th, 2022 GROUP MEMBER (Sign with full name) Le Xuan Tuan Dat Truong Khac Huy ABSTRACT In a scientific and technological world that continues to grow and improve, areas such as artificial intelligence (AI) deserve our attention. In recent years, artificial intelligence has been increasingly integrated into our everyday lives.
Traditional education has been impacted by the ongoing pandemic, causing a variety of challenges for students and instructors. Since then, online learning has grown in popularity, solving the problem of the epidemic but creating an entirely new set of challenges. Studying generally is not an active pursuit for students. Instead, they prefer to complete their tasks, such as using their phones and napping.
For the above reasons, we have designed an online student monitoring system that uses MediaPipe library and image processing technology to recognize and track students' eyes in real time. With many outstanding features such as face recognition, iris recognition and the ability to identify quickly and accurately. Our team decided to choose this library to support the group's product perfection in the most optimal. We have accurately recorded the student’s perspective in real-time and the use of artificial intelligence.
Finally, our group is working to design a model that can help teachers easily manage and monitor students in their classroom in the most convenient and optimal. TABLE OF CONTENT CHAPTER 1: INTRODUCTION. 13 CHAPTER 2: LITERATURE REVIEW. Introduction of MediaPipe.
Architecture of Mediapipe. Applications in Mediapipe. Human Pose Estimation. 21 CHAPTER 3: A SYSTEM OF STUDENT ATTENDANCE AND CONCENTRATION TRACKING DESIGN.
Data Collection Page. 26 CHAPTER 4: RESULT AND DISCUSSION. 37 CHAPTER 5: CONCLUSION AND FURTHER WORK. 40 LIST OF FIGURES Figure 2.
1: Cross-platform embedded by Mediapipe [35]. 2: Object detection using MediaPipe [36]. 3: Waypoints and their associated names [37]. 4: Face mesh prediction [38].
1: Block diagram of the proposed automatic attendance register and student concentration level monitoring system. 2: Flowchart of the login page. 3: Flowchart of the data collection page. 4: Flowchart of the classroom page.
1: The login page. 2: The main page. 3: The get data page (1). 4: The get data page (2).
5: The personal information page. 6: The checkin section of the classroom page. 7: Monitor and assess students' attention in the class page - Student looks to the left and right. 8: Monitor and assess students' attention in the class page - Notice board for distracted students.
9: Information about the student’s lessons is recorded in an Excel file. 37 LIST OF TABLES Table 4. Face detection and recognition accuracy testing. Introduction Because of the prolonged epidemic situation, students and parents have spent two years adjusting to online learning; however, there are still struggles with online learning.
Additionally, with the complicated development of the COVID- 19 outbreak, it is evident that digitizing the entire education industry as a revolution for Vietnamese education is a necessity to replace the traditional classroom. Distance education, online teaching, online training, courses, and virtual classrooms offer an alternative to traditional learning since learners do not need to be present or interact directly with the teacher. As an alternative, the lecturer will deliver materials, lectures, or instructions via Internet-based technology software. Due to the limitations of online learning, thousands of students do not attend school due to being unable to accompany their parents through online classes, or they go online and then leave, or they sleep or do private work like playing on the phone.
It's because students don't feel independent and aware of what they are learning. In the future, this will lead to a generation of students who will lose extensive knowledge, which will have negative effects on the education industry and the country's development. Considering the reasons cited above, the team built a model to monitor online students, use image processing and artificial intelligence, and determine concentration time. In the first function, the teacher can detect if students are studying or not, which reduces the number of students entering the classroom but leaving to do their work without the teacher realizing it.
Lastly, it is used to see if students are paying attention to their studies or are focusing on their phones. Check out the methods that engineers and university lecturers have developed to support online learning in the past. Wansen Wang and Yapa Peng published a paper [1] in 2013 about how to build a face detection system using the Adaboost algorithm. A paper [2] combining face-contour with Adaboost was published in 2013 to improve the detection performance.
First, a grayscale image 1 will be created from the detected image. Then, removing areas with no faces and noise using the connection filtering method. In the result, contour points are modified according to curves, area prioritization (eyes, mouth and face height proportionately estimated by vertical head and neck position and added with faceless contours around the boundary of the rectangle) and then the image is processed vertically and horizontally to determine exact face contour and surrounding contour, so background intervention can be removed. Adaboost helped the author remove background and noise to improve classification efficiency.
In E-learning, learners adopt many different postures to learn. As a result, E-Learning images have certain characteristics, such as those mentioned by the author in the article: learners are not required to meet any strict requirements, the lighting in the room is dim and uneven, and almost all learners wear glasses in real life. Moreover, the author's results in the article are also a 92% accuracy; besides, if the face is not detected, a pop-up message will appear that the face can't be detected, and of course, it can also detect faces when the learners are wearing glasses. In addition, perhaps because traditional learning was still a priority then, there were not that many articles mentioning E-learning in the following years.
Two years later, a paper evaluating the effectiveness of facial recognition methods and their role in supporting E-learning systems was published. The paper [3] also proposes a new feature extraction method that is based on the height and width of the face, for different regions such as the right eye, the left eye, the nose, and the mouth will be calculated separately to determine their respective locations of those areas and the distance is calculated using the Euclidean formula. According to the author, there are 12 steps in detecting and recognizing faces. In the first step, an RGB image will be read as input.
The next step is to use the face detection code on the input image and then detect the faces from there. Thirdly, cut out all the faces from each picture to create a single image. Reading each photo in the test set (separating faces from the previous step) is the next step. The fifth step is to read the codebook array (database of images).
As a next step, divide the codebook into n images. To calculate the variance for step 7, calculate the variance values for 2 each image in step 6 and place the variance values in a matrix using a formula. After that, calculate the variance based on the calculation formula for the test set (found in step 4).