Monitor Student’s Presence in Classroom _________________________________________________________________________________________

Abstract— This project is developed for two purposes: first is avoid the manual roll number call by lecturers which is time consuming task and also to avoid proxy, second is parents monitor their children. This project aims at providing software to automatically record the students’ attendance during lecture in a classroom using facial recognition technology instead of the traditional manual roll call methods. Facial recognition method is very important and is used in various applications for identification and detection.

Keywords —Face Recognition, Attendance System, Camera, Image Processing technology, OpenCV Library Software

___________________________________________________________________________________________________

Introduction

This project deals with the development and implementation of a smart and real time attendance application that monitor and traces the exact position of a student. Parents whose numbers are registered in the school/college database can use this application in their mobile phones. It provides some authentication and thus enhances security of student by using CAMERA which is used in the classroom. Using this application, parents can be carefree about the safety of their children despite being busy in their hectic job schedule. It helps you to get the actual position of your children on your smart mobile phone or even your computer. It is enabled with 3D earth map that provides you most accurate position of your child at a regular interval of time. The software provides you real time positioning system with finest accuracy. The student recognition application is for Classroom Attendance system. The attendance is automatically updated onto a personal computer of classroom and then takes printout of attendance sheet. Also the incoming and outgoing timings of the Students can be recorded in camera for later records. Facial recognition technology uses in different areas in large organizations. This is mainly because these applications improve the performance and effectiveness of the organization (colleges).For an organization to be effective, it needs accurate and fast means of recording the performance of the lecturer inside college. Biometric recognition has the potential used for evaluating the performance of those people working within the college. Although biometric technologies are being applied in many fields but it has not yet delivered its promise of guaranteeing automatic face recognition. This research is providing an automated attendance system that recognizes students using face recognition technology which record their attendance in lectures and evaluating their performance accordingly.

LITERATURE SURVEY

The Existing systems that use RFID, barcode scanner, biometrics like fingerprint recognition, iris recognition etc. to identify students are time management systems used in many colleges [2] and existing techniques involve fingerprint tracking which does not provide the exact position of the student as it is having some limitation due to distance. Face recognition system has been utilized in much application over past year: Video Gaming, Smart Cards and Face ID, drivers’ license-national ID- passports- voters’ registration, internet and intranet security, terrorist alert, advanced video surveillance, Crime stopping, time attendance and monitoring. Our system will try to provide a solution to this problem as we are using camera, it provides the exact position by taking multiple face detection, face matching algorithm and update attendance of student in teacher catalog and providing the children’s updated information to their parents. Every day a lecture, laboratory starts the lecturer or teaching Assistant delays the lecture to record students’ attendance. When lecture with large number of student at that time this manual attendance is a lengthy process and takes a lot of time and effort. During an exam, traditional attendance system causes a lot of disturbance and interruption. • Registration: This will provide the users their respective Id and Password. • Login: This function will check that only the valid users are allowed to access their web application. • Edit Profile: Parents can view their information and edit it as and when required. • Post notifications: Teachers can add all important notifications whenever required.

Proposed system

1 Architectures of proposed system

[pic]

System Architecture

The application provides some security to the child by continuously informing their parents about their academic report. Also this application can be used only by the parents whose numbers are stored in school database. The registration and login information should be encrypted and decrypted properly to provide safety and protect illegal use of application.
Enrollment

First step in every biometric system is the enrollment of persons using general data and their unique biometric features as templates. This work uses the enrollment algorithm as shown in the Figure 1.

| | Enhanc- | Feature |
|Capture | | |
| Image | ement |Extraction |

Data base

Fig 1. Enrollment Process

Image is captured from the camera which is used in the classroom and then it is enhanced using histogram equalization and noise filtering. In the second step face is detected in the image and features are extracted from it. These unique features are then stored in the face database with certain id of that person.

System Description

The system consists of a camera that captures the images of the students in the classroom and sends it to the image enhancement module. After enhancement the image comes in the Face Detection and Recognition modules and then the attendance is marked on the database server. This is shown in the experimental setup in Figure2. At the time of enrollment templates of face images of individual students are stored in the Face database. Here all the faces are detected from the input image and the algorithm compares them one by one with the face database. If any face is recognized the attendance is marked on the server from where anyone can access and use it for different purposes. This system uses a protocol for attendance. A time table module is also attached with the system which automatically gets the subject, class, date and time. Teachers come in the class and just press a button to start the attendance process and the system automatically gets the attendance without even the intensions of students and teacher. In this way a lot of time is saved and this is highly secure process no one can mark the attendance of other. Attendance is maintained on the server so anyone can access it for it purposes like administration, parents and students themselves.
Camera takes the images continuously to detect and recognize all the students in the classroom. In order to avoid the false detection we are using the skin classification technique [19]. Using this technique enhance the efficiency and accuracy of the detection process. In this process first the skin is classified and then only skin pixels remains and all other pixels in the image are set to black, this greatly enhance the accuracy of face detection process.

Two databases are displayed in the experimental setup Figure 2. Face Database is the collection of face images and extracted features at the time of enrollment process and the second attendance databases contains the information about the teachers and students and also use to mark attendance

System Algorithm

This section describes the software algorithm for the system. The algorithm consists of the following steps

• Image acquisition • Histogram normalization • Noise removal • Skin classification • Face detection • Face recognition • Attendance

In the first step image is captured from the camera. There are illumination effects in the captured image because of different lighting conditions and some noise which is to be removed before going to the next steps. Histogram normalization is used for contrast enhancement in the spatial domain. Median filter is used for removal of noise in the image. There are other techniques like FFT and low pass filter for noise removal and smoothing of the images but median filter gives good results. This Algorithm is shown in the Figure 3. Next is the description of each step in the above algorithm with effects on the images after each process

4.1 Image Acquisition

Image is acquired from a high definition camera that is connected above the white board. This camera is connected to the computer. It captures images after every 2 minutes and sends these images to the computer for processing. Figure 4 shows the input image of classroom captured by the camera

4.2 Histogram Normalization

Captured image sometimes have brightness or darkness in it which should be removed for good results. First the RGB image is converted to the gray scale image for enhancement Histogram normalization is good technique for contrast enhancement in the spatial domain. Figure 7 shows the histogram normalized image of the input image. This can be easily seen that the students sitting on the back rows are now clearly seen and in this way they can be easily recognized. There are other techniques for making an image illumination invariant (1). Figure 8 shows the histogram after the equalization of input image.

Noise Filtering:

Many sources of noise may exist in the input image when captured from the camera. There are many techniques for noise removal. Low pass filtering in the frequency domain may be a good choice but this also removes some important information in the image. In our system median filtering in is used for the purpose of noise removal in the histogram normalized image.
Skin classification

This is used to increase the efficiency of the face detection algorithm. Voila and Jones (8) is used for detection and its accuracy can be increased if the skin is classified (18) before the scanning procedure of faces

Face Detection

In this section faces are detected and shown in the figure 10 by marking circles on the faces of student Algorithm is trained for the images of faces and then applied on the class room image for detection of multiple faces in the image. The algorithm can also detect the veil faces as shown in the Figure 11. After the detection of faces from the images next step is cropping of each detected face. The algorithm uses the technique of threading to enhance the speed of algorithm. Each cropped image is assigned to a separate thread for the recognition purposes. Figure 12 shows the cropped faces from image

Face Recognition and Attendance

After the face detection step the next is face recognition. This can be achieved by cropping the first detected face from the image and compare it with the database. This is called the selection of region of interest. In this way faces of students are verified one by one with the face database using the EigenFace method [17] and attendance is marked on the server. Face Recognition techniques (14) (17) are used in our system

MATEMATICAL MODEL

The model of Monitor Student’s Presence in Classroom System as a Finite State Machine MSPCS is defined as a Five tuples relationship

MSPCS ││ (S, Σ, s, F, δ)
Where

1 S is a set of valid states that forms the domain of the MSPCS, S = {s0, s1, …, s8} where the states are: s0 – Teacher Registration System, s1 – Student Images capture by camera, s2 – Database student Image, s3 –Result of Image Compare, s4 – Parents Registration , s5 –Login and child Status checked s6 - Attendance is taken s7 - Entry is granted, s8 – Entry denied s9 – Exit

2 Σ is a set of events that the Software may accept and process, Σ = {e0, e1, …, e12} where:

e0 - Start, e1- Face Detection, e2 – Face Recognition Data, e3 – Check for Student Image Match, e4 – Match Found, e5 – Match not found, e6 –Status confirmed, e7 – status not confirmed, e8-Attendance Marked.

CONCLUSION

This application will be used for many purposes. Main purpose is for an automatic attendance Pilot phase of this project would be to monitor the movement/behavior of children in the classroom. Parents can monitor presence/absence of their children from remote location without physically visiting to the college or school. However, after successful implantation of pilot, same concept might be implemented in various areas like institute, police department, constitution, organization etc.

Acknowledgment

A project of this magnitude has been a journey with various ups and downs. It was the support from Guide, Colleagues and Family, which has helped me in the successful accomplishment of this project. I am glad to express my sentiments of gratitude to all who rendered their valuable help for the successful completion of the project. I am thankful to my guide Prof.L.J.Sankpal, for the guidance and encouragement in this work. His expert suggestions and scholarly feedback had greatly enhanced the effectiveness of this work. I would also like to express my appreciation and thanks to all my colleagues and family members who knowingly or unknowingly have assisted and encouraged me throughout my journey.

References

1] Ravi Shankar Sivalingam Anoop Cherian Joshua Fasching Nicholas Walczak Nathaniel Bird “A Multi-Sensor Visual Tracking System for Behavior Monitoring of At-Risk Children.”2012 IEEE International Conference on Robotics and Automation RiverCentre, Saint Paul, Minnesota, USA May 14-18, 2012
2] APARNA BEHARA, M.V. RAGHUNADH “REAL TIME FACE RECOGNITION SYSTEM FOR TIME AND ATTENDANCE APPLICATIONS”.
3] Balwant Singh, Sunil Kumar, Paurush Bhulania “LECTURE ATTENDANCE SYSTEM WITH FACE RECOGNITION AND IMAGE PROCESSING” International Journal Of Advance Research In Science And Engineering IJARSE, Vol. No.2, Issue No.3, March, 2013
4] Naveed Khan Balcoh, M. Haroon Yousaf, Waqar Ahmad and M. Iram Baig “Algorithm for Efficient Attendance Management: Face Recognition based approach”. IJCSI International Journal of Computer Science Issues, Vol. 9, Issue 4, No1,July2012ISSN(Online):1694-08.

-----------------------
2

1

1