Browse Poster Wiki: 2022 Poster Award Winners, Awards Ceremony (Watch Recording from minute marker 1630), Posters by 2022 HPCC Systems Interns, Posters by Academic Partners, Poster Judges, About Virtual Judging, 2022 Poster Contest Home Page, Poster Contest Previous Years

Open

Akanksha A Pai is a 4th semester student studying Computer Science and Engineering at RVCE in India.  She is keen on exploring the fields of Artificial Intelligence, Computer Vision, Machine Learning and Cloud Computing. Akanksha is eager to learn more and she aims to combine her skills and knowledge into projects which may have an impact on the world.

Poster Abstract

It can be very tedious for a teacher to take attendance in every class, not to mention how time consuming it is. The solution I have designed for this is a smart face recognition based attendance system using the cameras fixed in the lecture hall, to recognize the faces of the students attending the class, with negligible input from the teacher , thus allowing them to spend more time on teaching.

I have used the pretrained Caffe model for face detection and gender detection. The face recognition was based on the DNN algorithm. HPCC Systems can be integrated into this application to cluster all the computers tracking attendance on the campus, thereby outputting efficient attendance tracking. The data obtained from each of the computers can be uploaded into the cloud for future use by students or the institutions. By doing so, the three primary components of HPC- computation, networking and storage can be efficiently put to use in this application.

The various features of the application are:

1. To prevent malpractice, only the admin or teacher has the right to take attendance.

2. The student is allowed to only login with their credentials and check their attendance.

3. New students/teachers can be added by the admin during the admission process. They can be removed too as and when needed.

4. Gender of the student/teacher is automatically detected by the application.

5. The timetable is stored in the database and has details about the subjects and teacher ID for each class in each branch. As an example, a timetable for 2 branches of the 3rd semester has been created.

6. The application is designed in such a way that it recognizes the face of the teacher, and looks into the timetable, querying by day, time, and teacher ID to determine the subject and class it is being taught in.

7. The application has been designed for ease of use, reducing the number of inputs the user has to provide.

Presentation

In this Video Recording, Akanksha provides a tour and explanation of her poster content.

Smart Face Recognition Based Attendance System

Click on the poster for a larger image. 

Open