Smart Attedance using Real Time Face Recognition
Attendance of students has always been a challenging factor for teachers in terms of time, and accuracy. Computerized Manual attendance systems are time consuming and error prone. Automated attendance system has also introduced the technology of biometric identifications of students using fingerprin
2025-06-28 16:35:05 - Adil Khan
Smart Attedance using Real Time Face Recognition
Project Area of Specialization Artificial IntelligenceProject SummaryAttendance of students has always been a challenging factor for teachers in terms of time, and accuracy. Computerized Manual attendance systems are time consuming and error prone. Automated attendance system has also introduced the technology of biometric identifications of students using fingerprints and iris scan, which is again a time consuming process.
Proposed system will mark attendance automatically in classroom using real time face recognition technique without student/teacher’s intervention. The attendance of each student is marked based on the duration of his/her presence in class. System will also generate daily/monthly report of student presence along with his in/out behaviour in class.
As an additional feature, system can also track the student based on his/her check in time until his checkout. System will also generate alert for any unknown person detected in cameras.
Project Objectives- To fully automate attendance without any human involvement
- Periodic Attendance Reports
- Student Tracking within Campus
- Unauthorized person detection in classroom
Implementation is divided into following steps:
Survey of Existing Systems:
In this phase, detailed literature review will conducted by team on current research to find existing techniques and technologies that may help in the project. Literature with the latest publication (2010-2020) is planned to be concatenated but classes are also being explored.
Data Generation:
Data Generation is considered as the most challenging task in conducting a research. This research is based on the recognition of real time faces in a controlled environment. Images of students will capture using camera from different angles. Face detection algorithm will use to detect face and extract the region of interest in rectangular bounding box. All extracted images will convert to grayscale and resize equally e.g. (100x100, 150x150) and then stored in database for further processing. In this way, a dataset is produced for algorithms to run on it.
Model Design:
Proposed system will extract features of real time faces after preprocessing e.g. converting to grayscale, Re-size. Supervised learning technique will use to match the features of real time faces with the stored ones. After recognizing a student, Attendance of student will be marked with timestamp.
Implementation:
Process starts with a camera, which will use Viola Jones algorithm to detect faces as an input to model. PCA would be used for feature extraction and will produce eigen faces. Based on these eigen faces, algorithm will generate faces on real time by taking proportion of these eigen faces. Distance Classifier/ SVM would be use for classification or to match the features of real time faces with the stored ones. At the time of recognition, system will record in time of student. After that, if there is a delay in recognizing pre-matched face, system will record out time of student.
Testing:
After implementation, real time environment will be create for testing the model. System will recognize the faces of students and mark the attendance. To test the accuracy, Manual attendance will also be taken and then difference will be calculated between manual and automated attendance.
Benefits of the Project- Efficient and reliable system
- Effort less attendance
- Automatically prevent from fake attendance
- Mark attendance on the base of duration of presence in classroom
- Student Tracking
- Unauthorized person detection
- The final deliverable would be a hardware & software integrated system.
- The frames taken from camera would be used as an input to the system at backend.
- The system would perform face detection and face recognition in the video stream received from camera.
- The programming language would be Python.
- The library under use would be OpenCV.
- Ouput will be generated in the form of reports like attendance summary and student behaviour within campus (from check-in to check-out)
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 73200 | |||
| 4 channel DVR with 4 Cameras | Equipment | 1 | 50000 | 50000 |
| Tripod | Equipment | 4 | 2500 | 10000 |
| Cable & Connectors | Equipment | 1 | 5000 | 5000 |
| CV In Python! Face Detection & Image Processing (Udemy) Discounted | Miscellaneous | 1 | 2500 | 2500 |
| Python DIP From Ground Up (Udemy) Discounted | Miscellaneous | 1 | 2500 | 2500 |
| Complete Guide to TensorFlow for DL with Python (Udemy) Discounted | Miscellaneous | 1 | 3200 | 3200 |