Virtual Teacher
Automation, the replacement of people in the workplace by machines is not something new. Automation is the creation and application of technologies to produce and deliver goods and services with minimal human intervention. The implementation of automation technologies, techniques, and processes impr
2025-06-28 16:29:57 - Adil Khan
Virtual Teacher
Project Area of Specialization Artificial IntelligenceProject SummaryAutomation, the replacement of people in the workplace by machines is not something new. Automation is the creation and application of technologies to produce and deliver goods and services with minimal human intervention. The implementation of automation technologies, techniques, and processes improves the efficiency, reliability, and/or speed of many tasks that were previously performed by humans.
In recent years, colleges and universities continue to promote the process of education and teaching reform, various teaching modes are constantly introduced, such as "flip classroom" and other teaching modes continue to develop. The fundamental purpose of the development of various teaching modes is to solve the problem of classroom teaching efficiency and improve the quality of college student's education. The classroom, as an important place for college students to acquire knowledge, has an important impact on the development of college students.
The purpose of attendance in class is to count the number of students and urge them to attend classes on time to improve the quality of teaching. The traditional classroom attendance is mainly done by the teacher through the manual way of rollcall. Although this method can ensure the accuracy of naming, it usually wastes a lot of time, which not only occupies the classroom time, but also affects the enthusiasm of teachers and students, and reduces the quality of the classroom. This way of attendance can play a certain role in urging less-known classes, but for more classes, there may be a phenomenon of "substitution", which is difficult for teachers to find.
Virtual Teacher is a machine learning-based desktop application that can assist the teachers by conducting the lectures through its Text to Speech conversion feature, in the absence of a teacher. The system makes sure to help the teacher in any kind of emergency, need, or unavailability of the teacher to continue the class/lecture. The system will automatically take the attendance of the students with the help of attendance through the Face Recognition System and will provide a spreadsheet with the dully filled attendance and complete record of present and absent students.
The system has a portal where the teacher uploads the lecture (PPT or PDF form) and the system uses Text to Voice conversion and continues the lecture. The system makes sure to help the teacher in any kind of emergency or need, to continue the class.
Project Objectivesa). Assist the teacher
This system will be able to provide every time available assistance to the teacher with a single touch.
b). Easily conduct lectures
The system helps to conduct the classes easily through its text to voice conversion feature which helps students listen to and understand already uploaded lectures on the teaching portal.
c). Make Attendance easy
To replace old fashioned attendance system with an automated face recognition feature, this system makes the attendance easy, and you even don’t know when it is done without any disturbance.
d). Easy to use
This whole system is very simple and easy because of its interactive user interface.
Project Implementation MethodVirtual Teacher contains 2 main features which are an automatic attendance system through the face recognition module and automatic lecture delivery through text to voice conversion. It also contains a supporting feature for recording tasks and maintaining notes.
These features are first developed individually in the form of modules such as Face Recognition System and Text to Voice Conversion system. Then all these modules are integrated together with the help of PyQt4 which helps to create the user interfaces for python applications.
The automatic attendance system is mainly based on three technologies:
- Face detection technology
- Face recognition technology
- Deep machine learning
For face detection, the Haar feature proposed by Viola et al. combined with the AdaBoost cascade classifier can detect faces quickly. Since then, many researchers have devoted themselves to using more advanced features to improve the accuracy of face detection, such as Local Binary Pattern (LBP), Histogram of Oriented Gradient (HOG), Scale-invariant Feature Transform (SIFT).
According to the main functions and different locations, the system design can be divided into two parts:
- Camera acquisition terminal
- Server computing terminal.
The camera acquisition terminal is installed in the classroom. Its main function is to collect real-time student portrait videos in the classroom and transmit the collected portrait videos to the server through the line for storage and processing. The main function of the server is to segment the video information of the human image obtained by the camera, get the frame image, then segment the frame image, recognize the human image of the segmented image, and filter and improve the recognition results using multi-frame images. The server will feedback the recognition results to the terminal and control the movement and focusing of the terminal through the terminal platform, to obtain the second video of the area with poor recognition effect, and then improve the recognition accuracy.
Text to Speech Conversion:
Speech synthesis (or Text to Speech) is the computer-generated simulation of human speech. It converts human language text into human-like speech audio.
There are several APIs available to convert text to speech in Python. One of such APIs is the Google Text to Speech API commonly known as the gTTS API. gTTS is a very easy-to-use tool that converts the text entered, into audio which can be saved as an mp3 file.
The gTTS API supports several languages including English, Hindi, Tamil, French, German, and many more. The speech can be delivered at any one of the two available audio speeds, fast or slow. However, as of the latest update, it is not possible to change the voice of the generated audio.
System Flow Diagram:
1. Save time
The classroom attendance system designed in this paper is real-time in the classroom. It will not waste any classroom time and avoid the waste of time caused by manual rollcall.
2. It will not interfere with the classroom
When the system is used for classroom attendance, it will not produce factors such as voices that interfere with the classroom order, so it will not affect the classroom order.
3. It can improve students' learning efficiency
The system uses face recognition to check attendance. If students sleep in class or play with their mobile phones for a long time, they may not be recognized and then be judged absent. Therefore, the system will have a binding effect on students and then can improve the efficiency of classroom learning.
4. Flow of lectures and no lecture gap
The system's text to speech feature helps to continue lecture flow and no gap occurs. If any student has a query, they can ask the teacher in the next class.
5. Teachers don't need to rely on any other assistance
This system is the best and quick assistance for a teacher to engage the classes and the teacher has no need to wait or ask any other teacher for a favor.
Technical Details of Final DeliverableThe virtual teacher is a machine learning-based desktop application that will work as a hardware/software integrated system. The hardware of the system contains the 64MP Autofocus Camera which works under the instructions provided by the system through a Raspberry Pi. We are using the Raspberry Pi 4 Model B because of its versatility, features, and power.
The teacher has to login into the portal through the specific email provided by their institute like; teacher@muetkhp.edu.pk in our case. Then teacher will have access to the main dashboard where they can see the attendance records, and overall analytics of the attendance (1 month), teacher can upload lectures which will be used by the system to conduct and can add, edit or delete the notes/tasks.
For the automatic attendance system, the camera will be used to detect and recognize students' faces to mark the attendance and the raspberry pi will help the camera and system to communicate with each other and vice versa. The camera after recognizing the face and will send the data to the module, and the module in the system will mark the student as Present (P) or Absent (A) accordingly.
On the other hand, the text to speech conversion will use its gTTS API to simply convert text from any document or ppt to the speech and will conduct the lecture.
A plus feature of Notes and Tasks will help teachers to note down any tasks, reminders, or future plans for their lectures or class activities.
Final Deliverable of the Project HW/SW integrated systemCore Industry EducationOther Industries IT Core Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Quality EducationRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 69450 | |||
| 64MP Autofocus Camera for Raspberry Pi + Cable connection | Equipment | 1 | 16000 | 16000 |
| Raspberry Pi 4 Model B 2GB | Equipment | 1 | 32500 | 32500 |
| Dual Electronics LU43PW 3-Way High Performance Outdoor Indoor Speakers | Equipment | 1 | 10000 | 10000 |
| Raspberry Pi 4 case, with cooling fan and heatsink | Equipment | 1 | 1250 | 1250 |
| Research Travel Cost | Miscellaneous | 1 | 5000 | 5000 |
| Poster Printing | Miscellaneous | 2 | 600 | 1200 |
| Equipment Shipment | Miscellaneous | 1 | 3500 | 3500 |