Face Recognition Based Attendance System: A Case Study, Schemes and Mind Maps of Software Engineering

Download Face Recognition Based Attendance System: A Case Study and more Schemes and Mind Maps Software Engineering in PDF only on Docsity!

CHAITANYA JINDAL

CASE STUDY

Face Recognition based Attendance System

INTRODUCTION

The traditional method of taking attendance in classrooms involves the teacher manually checking attendance at the beginning and end of class. However, this method has limitations because some students may be missed or answer multiple times. To address this issue, a face recognition-based attendance system has been proposed. This system uses face recognition technology to identify students and take attendance based on their presence in the classroom accurately and quickly. While facial recognition technology has been around for a while, recent advances in deep learning have allowed it to improve in accuracy and efficiency. The use of a facial recognition-based attendance system will be examined in this case study along with how it may help both teachers and students in the classroom. The different steps in the procedure, such as face detection and face recognition, will also be covered. Ultimately, the case study intends to show how facial recognition technology may be used to increase the precision and effectiveness of tracking student attendance in classes.

BACKGROUND

To maintain consistent attendance and track students' academic progress, attendance systems are frequently used in educational institutions. Yet conventional attendance methods, such as paper sign-in sheets or RFID-based systems, have a number of drawbacks, including laborious human record-keeping, the potential for unauthorised access, and the potential for student distraction during lectures. To address these limitations, a face recognition-based attendance system using deep learning algorithms has been proposed. The system aims to provide a faster, more accurate, and reliable way of taking attendance in classrooms. The system utilizes high-definition monitor video and information technology to recognize and record students' faces during lectures. The proposed system is based on two stages, face detection, and face recognition. In the face detection stage, the input image is searched to find any face, and image processing cleans up the facial image for easier recognition. In the face recognition stage, the detected and processed face is compared to the database of known faces to decide who that person is. The system also includes an automatic attendance analysis module, which uses fixed seating arrangements to contrast faces' coordinates and determine the identity of each student to achieve automatic attendance. The proposed system's methodology involves recording a video of every student, separating frames per minute for class attendance, applying deep learning algorithms for face detection and face recognition, and automatic attendance analysis. The system's experimental design involves using the ORL Database of Faces, which contains ten different images of each of 40 distinct subjects ( different images). Evaluation measures such as accuracy and Mean Average Precision (MAP) will be computed for the face recognition system.

PROPOSED SOLUTION/CHANGES

The face recognition-based attendance system is susceptible to a variety of recommended fixes and adjustments that might improve the system's effectiveness and efficiency.

1. Boost system accuracy: Machine learning algorithms that can identify and learn from the patterns of employees' face features may be utilised to train the system. By doing this, the accuracy of the system will be improved, and the veracity of the employee attendance records will be ensured.
2. Guarantee a high-quality camera: To combat the issue of subpar cameras, businesses should spend money on high-end cameras that can precisely record an employee's likeness. This will ensure that the system operates efficiently even in dimly light areas.
3. Have a backup plan: If the face recognition-based attendance system breaks down, it's critical to have a plan B in place. A manual register or an additional attendance system, like a fingerprint or iris recognition system, could serve as this backup system.
4. Employee education: Companies should give workers appropriate instruction on how to operate the system. Employee errors brought on by improper camera positioning or face scanning will be less common as a result of this.
5. Test the system frequently: To make sure the system is operating properly, frequent testing is necessary. This will make it easier to spot any systemic problems and fix them before they worsen.
6. A face recognition-based attendance system should comply with privacy and data protection laws, therefore organisations must make sure of this. This can be accomplished by informing employees in a straightforward manner about how their data is being gathered, stored, and utilised and by receiving their consent. The issues faced by the facial recognition-based attendance system can be overcome and its efficacy and efficiency in accurately recording employee attendance can be improved by implementing the suggested remedies and improvements.

CONCLUSION

Using a facial recognition-based attendance system has several benefits over using a standard attendance system, including higher efficiency, a decrease in errors, and improved security. Yet, there are some possible disadvantages as well, such as the requirement for very accurate and superior cameras. It is advised to thoroughly test and calibrate the face recognition software before use to allay these worries. Also, routine system upkeep and updates can guarantee the system's continuous efficacy and accuracy. Overall, the facial recognition-based attendance system is a promising option that can significantly increase efficiency and security for companies. It can be a useful tool for controlling employee attendance and enhancing overall operations with correct deployment and upkeep.