Face Recognition based smart solution for student security

Project Title

Face Recognition based smart solution for student security

Project Area of Specialization Software EngineeringProject Summary

Every child's parents want to provide them with a suitable environment for learning, so they can lead the society and country in a positive direction in the future. In this regard, parents are also concerned about their security and safety when the children are out of home for education. Because of the high rate of kidnapping, parents are always worried about their children, moreover, these days child abuse is another big problem in our society.

To ensure the security and safety of students, we propose the development of a security system based on face_recognition. Although other biometric techniques are also available like fingerprints, voice recognition, etc. however these technologies can lead to proxies and unauthorized access, as we know that humans can primarily be identified by their faces. so face_recognition is a secure and unique technique to ensure student security. 

Our proposed system is based on the Open Source Computer Vision (OpenCV) library which is a machine learning library for computer vision. We will use this library to recognize students when they enter their classroom. This system will be able to mark a student's attendance when he/she is in the classroom at the time. If the student has not arrived at school or classroom because of any reason the system will send an alert message to the student's guardian, so they can take some actions accordingly.

Also due to the alert message to parents, the student will no longer take leave from school without their guardian’s permission.

Also, this system will help school management and supervisor to track their student attendance. This system will overcome ambiguities like fake attendance, resource consumption, and time consumption. Manual attendance techniques are also available but these techniques can lead to a lot of time consumption and wastage of resources.

By this system, the student’s education level can be improved because their parents will be able to trace their children.

Project Objectives

• To ensure student’s security

This system is based on face_recognition which is secure and has a high rate of accuracy after the recognition of the student his/her attendance will be marked. Other attendance technologies like fingerprints scanner, RFID, GPS, iris detection, and voice recognition may lead to fake attendance and someone else can check-in.

•   To provide rapid feedback to student’s parents

As this system is based on face_recognition so the camera will be used to recognize the student after recognition the system will send a pre-written message to the student's guardian. Otherwise, an alert message will be sent to the student's guardian in case of the student's absence.

• To provide an automated process for student’s attendance

Manual attendance is time-consuming and resources consuming, but this system will be able to mark the attendance of the students automatically after the recognition process.

• To save time that may spend on attendance

This system will be able to mark the student’s attendance after the recognition so a lot of time will be saved that may be spent on manual attendance.

• To eliminate unauthorized access

Other biometric techniques may lead to unauthorized access as a student can forget his RFID at home or someone else can use this RFID card to check-in. This system will recognize a student by his face to record his attendance.

Project Implementation Method

Our security system “Face Recognition Based Smart Solution for Student Security” is based on open-source computer vision which is also called OpenCV in short. This library was created by Intel in 1999 and written in C++ that is free for both commercial and academic use. It has Python, C++, and Java interfaces and can support various operating systems including Windows, macOS, Linux, Android, and iOS. This library has a large number of algorithms that can be used to detect objects and recognize faces.

Opencv is a simple library built using dlibs state-of-the-art face recognition built with deep learning. It has a face_recognizer library for face recognition. The dlib is a cross-platform software library that is implemented on computing platforms. It provides a simple face recognition command-line tool that has an accuracy of up to 99.38%.

In the first step, the system captures the image of the student and creates a database for the student which includes the student’s name, the student’s father’s name, guardian mobile phone number, and the address of the student. Afterimage capturing the student dataset is passed through the pre-trained model to recognize the student. 

If the student is recognized by the system a pre-written success message will be sent to the student’s guardian declaring that the student has arrived at the school safely and is going to attend the class on time. After sending SMS to the student's guardian, the student’s attendance will be recorded and an Excel sheet will be generated including attendance of the students. This will be an automated process and will not require manual resources.

In case if the student attendance is not recorded by the system then the system will be able to send an alert message to the student's guardian and supervisor declaring that the student is absent in today’s class. So they will be able to take action if the student is not reached at the school because of any problem.

Benefits of the Project

• This system can accurately track student’s faces and mark attendance without human error.

• Facial recognition technology can accurately report attendance and absence with an identification process that is fast as well as accurate.

• This system allows you to not only track students but also add visitors to the system so they can be tracked throughout the time. Access can be denied to any person, not in the system. if an incident should occur, facial recognition software can provide evidence for an investigation with a scanned image of a person or persons who have entered the area.

• This system is based on Machine Learning which is fully automated, managing the records of day to day activities will be much easier than the manual system.

• This system will reduce manual work.

• This system will save time and other resources.

• This system will help to minimize child abuse that is also an initiative of the current government.

• This system will help school management to ensure the security of a large number of students.

Technical Details of Final Deliverable

As we mentioned earlier this project is based on Computer Vision, which is an emerging sub-field of machine learning. In this project, we will be using an open-source computer vision library or OpenCV.

OpenCV is pretty smart to recognize faces in images which will be quite helpful. This system will solve a critical security issue that is always faced by every organization.

Primarily this system is proposed for schools but this system can be used in any organization where security is a big issue.

To use this system in any organization, the system will require a large number of images of the organization members to train the model. After training the model the system will use a camera that should be installed on the entrance to capture an image of any person while entering the area. The system will check this image and will compare the features of the image in the database to ensure security. If the person's face is not recognized by the system then the system will be able to send an alert message to the admin. 

An LED (light emitted Diode) screen will be used to display records of the student with the current status.

Final Deliverable of the Project HW/SW integrated systemCore Industry SecurityOther Industries Education , IT Core Technology Artificial Intelligence(AI)Other Technologies Internet of Things (IoT), OthersSustainable Development Goals Good Health and Well-Being for People, Quality Education, Peace and Justice Strong InstitutionsRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	51000
Resberry Pi 4 Board	Equipment	1	26000	26000
Samsung Security Camera	Equipment	1	9500	9500
LED Monitor Screen	Equipment	1	8000	8000
Connection Cables and Leds	Equipment	5	1000	5000
Stationary	Miscellaneous	5	500	2500