CLASS ATTENDANCE RECORD BASED FACE RECOGNITION
GSJ: Volume 7, Issue 5, May 2019ISSN 2320-9186206GSJ: Volume 7, Issue 5, May 2019, Online: ISSN 2320-9186www.globalscientificjournal.comCLASS ATTENDANCE RECORD BASED FACERECOGNITION USING RASPBERRY PI[1]Rajaa Al-Badri [1], Sulaiman Al Hasani[1]Department of Electronics & Telecommunication Engineering,Global College of Engineering and TechnologyMuscat, OmanEmail: r.badri@gcet.edu.omAbstractEducational institutions are concerned about regularity ofstudent attendance. This is mainly due to students’ overallacademic performance is affected by attendance in theinstitute. Mainly there are two conventional methods ofmarking attendance which are calling out the roll call or bytaking student sign on paper. They both were more timeconsuming and difficult. Hence, there is a requirement ofcomputer-based student attendance management systemwhich will assist the faculty for maintaining attendancerecord automatically. In this project the automatedattendance system using Raspberry pi 3B withOpenCV/Python libraries have been implemented. Our ideashave been projected to implement “Class Attendance SystemBased on Facial Recognition”, in which it compasses largeapplications. The application includes face identification,which saves time and eliminates chances of proxy attendancebecause of face authentication. Hence, this system can beimplemented in a field where attendance plays an importantrole. In addition, as the project objectives and the designcriteria all met, it’s greatest to say this project is anengineering solution for all university and colleges to trackand manage the attendance.KeywordsAttendance, Detection, Recognition, Deep learning, Raspberrypi3B .I.INTRODUCTIONIn the recent years, Image processing which deals withextracting useful information from a digital image plays aunique role in the advent of technological advancements. Itfocusses on two tasks, improvement of pictorial informationfor human interpretation, also processing of image data forstorage, transmission and representation for autonomousmachine perception. Recently, it has been proven thatstudents engage better during lectures only when there iseffective classroom control (ResearchGate, 2018). The needfor high level student engagement is an important thing inany institution. Similarly, people have started to use imagecapturing devices never as before with the advent of smartphones and closed-circuit television. Since the application ofimage processing is vast, extensive work and research havebeen carrying out in utilizing its potential to and to make newinnovative applications. Facial recognition has been theearliest of the application derived from this technology,which is one of the most fool proof methods in humandetection. Face is a typical multidimensional structure andneeds good computational analysis for recognition. Biometricsmethods have been used for the same purpose since a long timenow. Although it is effective, and it is still not completelyreliable for purpose of detecting a person.II.LITERATURE SURVEYIn this section, we highlight some related works that weredeveloped to recognize faces and takedown attendancetogether with the advantages and disadvantages of eachsystem. First system, auto attendance using face recognition(By Mahvish), in this project the admin selects a camera tocapture, gather and save photos to database or a folder. Afterthe collection and saving the process accomplished thetraining set manager begin to extract faces from the pictureby face detection. The instructor chooses the course ID andthe class ID to begin the attending process (UKEssays,2013). Second system, attendance system on face detection(By Nevon projects) which is mainly created for using asimple and a secure way of recording attendance. Firstly, thesoftware program takes a photo of all the approvedindividuals and stores the information into the system’sdatabase. Then, the system stores images via mapping it intoa face match structure. The system will recognize theregistered person and mark his/her attendance along with thearrival time (Nevoproject, 2012). By analysing the twosystems we found that both has the advantage of storing thefaces and automatically marks attendance, multiple facedetection and maximize the number of extracted faces froman image. However, the accuracy of the system is not 100%,data processes a little bit slow (with Mahvish), detect facefrom a limited distance (with Nevoproject) and cannot repeatlive video to recognize missed faces (with Nevoproject).III.METHODOLOGYBased on the related works which have been reviewed toclarify the investigation methods a relevant task is followed,by identifying the advantages and disadvantages of previousworks and studies will enable us to predict our designrequirements and gives a chance for project improvements.The proposed face detection module for this project is Violajones algorithm. Also, for face recognition modules which isGSJ 2019www.globalscientificjournal.com
GSJ: Volume 7, Issue 5, May 2019ISSN 2320-9186207proposed for this project is a neural network architecture withLBPH.IV.PROPOSED SYSTEM STRUCTURECameraResultsRecordAtteDatasetStuFigure 1: The proposed system.structure.The block diagram in the figure 1 shows the proposedstructure for class attendance system-based facerecognition, designed using drawio software. The systemrequires a camera installed in the classroom at a positionwhere it could detect and recognize all the students in theclassroom and thus capture their images effectively. Thisimage is processed to get the desired results.V.PROPOSED SYSTEM CIRCUIT DIAGRAMFigure 3: The proposed overall system flow-chart.The following figure shows the project system circuitdesign in Fritzing circuit diagram maker:II.Figure 2: The proposed system circuit diagram.I.PROPOSED SYSTEM FLOWCHARTThe following figure shows the project system flowchart:HARDWARE CONSIDERATIONRaspberry pi 3 B :The Raspberry Pi is a low cost, credit-card sizedcomputer that plugs into a computer monitor or TV anduses a standard keyboard and mouse. It is a capable littledevice that enables people of all ages to explorecomputing, and to learn how to program in languages likeScratch and Python. The Raspberry Pi can interact withthe outside world and has been used in a wide array ofdigital maker projects, from music machines and parentdetectors to weather stations and tweeting birdhouseswith infra-red cameras. The Raspberry Pi set up needs:A. ScreenB. Mouse & KeyboardC. VGA to HDMI CableD. SD-Card.E. Power SupplyGSJ 2019www.globalscientificjournal.com
GSJ: Volume 7, Issue 5, May 2019ISSN 2320-9186III.208SOFTWARE CONSIDERATIONOpenCV-Python software:OpenCV supports a wide variety of programminglanguages such as C , Python, Java, etc., and is availableon different platforms including Windows, Linux, OS X,Android, and iOS. Interfaces for high-speed GPUoperations based on CUDA and OpenCL are also underactive development. OpenCV-Python is a library of Pythondesigned to solve computer vision problems (OpenCV,2018).IV.1.IMPLEMENTATIONFirstly, connecting Raspberry pi with requiredcomponents as shown in the following figure:Figure 6: Testing python connectivity with Gmail.5.6.Dataset creation from live video, using python script.All the files will be in one directory named withdataset and each file labelled with student name.Creating database for attendance using MySQL: Table for Students information. Table for attendance:Figure 4: The project system set-up.2.3.4.Testing face detection algorithm for a number of volunteersand the results are within approximately 98% accuracy to100%.Testing face recognition algorithm for a number ofvolunteers.Testing MySQL connectivity with python and Gmail, theoutput is as following below:Figure 7: The table of attendance MySQL.7.Figure 5: Testing MySQL connectivity with python.we will use Raspberry pi 3B features along with python tosend emails to the students who reach or exceed the absentee’spercentage. An email will be sent if A.P% 50% as shownbelow:GSJ 2019www.globalscientificjournal.com
GSJ: Volume 7, Issue 5, May 2019ISSN 2320-9186209sent directly to the student. GUI has been implemented tomake the system operation more intuitive and easier to learn.Figure 8: The output of email alert.8.The system is implemented in GUI using pyQt5 designer andthe result is as following:VI.CONCLUSIONIn this approach, a face recognition based automated studentattendance system is thoroughly described. The proposedapproach provides a method to identify the individuals bycomparing their input image obtained from recording videoframe with respect to train image. This proposed approachable to detect and localize face from an input facial image,which is obtained from the recording video frame. Besides,it provides a method in pre-processing stage to enhance theimage contrast and reduce the illumination effect. Extractionof features from the facial image is performed by applyingboth LBP and Haarcascaed. The algorithm designed tocombine LBP and deep learning neural network able tostabilize the system by giving consistent results. Theaccuracy of this proposed approach is 100 % for high-qualityimages, and good lighting condition.VII.ACKNOWLEDGMENTI wish to express my indebtedness to the god forcompleting this project and to those who helped me whichare the reason of the preparation of the manual script ofthis text. This would not have been made successfulwithout their help and precious suggestions. I would liketo extent my heartfelt gratitude towards my colleagues,who encouraged me to an extent, which made the projectsuccessful. Apart from that I would also like to thank theUniversity for providing all the facilities upon completionof this project. Finally, I would like to say thank you to myparent who are my constant source of inspiration,motivation and pillar of for me to complete this final yearproject.Figure 9: GUI design of the final system.V.RESULTS AND DISCUSSIONVIII.After ensuring the connectivity, the programming phases canbe implemented. As have been mentioned in the designspecifications the first thing to be done is dataset creation, andthis have been implemented with satisfied results. The datasetpython script is basically, capturing the trained images froma live video frames, then store them in one directory calleddataset. Next, is database creation which are important forattendance record process. There are three tables created inMySQL, user table, module table and attendance table. Thiscode is combined with the recognition code so that based onrecognized face IDs the attendance will be inserted. Thirdly,is the absentee’s announcement via email alert. If theabsentee’s percentage is 50% or more an email alert will beREFERENCES[1] Docs.opencv.org. (2018). OpenCV: Introduction toOpenCV-Python Tutorials. [online] Available at:https://docs.opencv.org/3.4/d0/de3/tutorial py intro.html [Accessed 10 Nov. 2018].[2] Engr.uconn.edu. (n.d.). RASPBERRY PI BASICS.[online]Availableat:http://engr.uconn.edu/ song/classes/nes/RPi.pdf[Accessed 15 Oct. 2018].[3] Foundation, R. (2018). Raspberry Pi — Teach,Learn, and Make with Raspberry Pi. rrypi.org/ [Accessed 7 Aug.2018].[4] Matrixaccesscontrol.com.(2018).FaceRecognition Attendance System – Biometric FacialGSJ 2019www.globalscientificjournal.com
GSJ: Volume 7, Issue 5, May 2019ISSN 2320-9186210Recognition System. [online] Available tion.html [Accessed 15 Oct. 2018].[5] NevonProjects.(2018).FaceRecognitionAttendance System Project. [online] Available ance-system/ [Accessed 17 Oct.2018].[6] Raspbian.org. (2018). FrontPage - Raspbian.[online] Available at: https://www.raspbian.org/[Accessed 10 Nov. 2018].[7] ResearchGate. (2003). Face Recognition: ALiterature Survey. [online] Available 092 Face Recognition A Literature Survey[Accessed 30 Nov. 2018].[8] Ukessays.com.(2018).FaceRecognitionAttendance System. [online] Available nition-attendance-system-6424.php?vref 1[Accessed 30 Nov. 2018].[9] W.-K. Chen, Linear Networks and Systems.Belmont, Calif.: Wadsworth, pp. 123-135, 1993.(Book style)[10] H. Poor, “A Hypertext History of eu.edu/home/pb/mudhistory.html. 1986. (URL link *include year)[11] K. Elissa, “An Overview of Decision Theory,"unpublished. (Unplublished manuscript)[12] R. Nicole, "The Last Word on Decision Theory," J.Computer Vision, submitted for publication.(Pending publication)[13] C. J. Kaufman, Rocky Mountain cation, 1992. (Personal communication)[14] D.S. Coming and O.G. Staadt, "Velocity-AlignedDiscrete Oriented Polytopes for Dynamic CollisionDetection," IEEE Trans. Visualization andComputer Graphics, vol. 14, no. 1, pp. 1-12,Jan/Feb 2008, doi:10.1109/TVCG.2007.70405.(IEEE Transactions )[15] S.P. Bingulac, “On the Compatibility of AdaptiveControllers,” Proc. Fourth Ann. Allerton Conf.Circuits and Systems Theory, pp. 8-16, 1994.(Conference proceedings)[16] H. Goto, Y. Hasegawa, and M. Tanaka, “EfficientScheduling Focusing on the Duality of MPLRepresentation,” Proc. IEEE Symp. ComputationalIntelligence in Scheduling (SCIS ’07), pp. rence proceedings)[17] J. Williams, “Narrow-Band Analyzer,” PhDdissertation, Dept. of Electrical Eng., HarvardUniv., Cambridge, Mass., 1993. (Thesis ordissertation)[18] E.E. Reber, R.L. Michell, and C.J. Carter, “OxygenAbsorption in the Earth’s Atmosphere,” TechnicalReport TR-0200 (420-46)-3, Aerospace Corp., LosAngeles, Calif., Nov. 1988. (Technical report withreport number)[19] L. Hubert and P. Arabie, “Comparing Partitions,” J.Classification, vol. 2, no. 4, pp. 193-218, Apr. 1985.(Journal or magazine citation)[20] R.J. Vidmar, “On the Use of Atmospheric Plasmasas Electromagnetic Reflectors,” IEEE Trans.Plasma Science, vol. 21, no. 3, pp. nals/21ps03vidmar, Aug. 1992. (URL for Transaction, journal,or magzine)[21] J.M.P. Martinez, R.B. Llavori, M.J.A. Cabo, andT.B. Pedersen, "Integrating Data Warehouses withWeb Data: A Survey," IEEE Trans. Knowledge 007.190746.(PrePrint)[22] Y. Yorozu, M. Hirano, K. Oka, and Y. Tagawa,“Electron spectroscopy studies on magneto-opticalmedia and plastic substrate interface,” IEEE Transl. J.Magn. Japan, vol. 2, pp. 740–741, August 1987[Digests 9th Annual Conf. Magnetics Japan, p. 301,1982].[23] M. Young, The Technical Writer’s Handbook. MillValley, CA: University Science, 1989.GSJ 2019www.globalscientificjournal.com
8. The system is implemented in GUI using pyQt5 designer and the result is as following: V. RESULTS. AND DISCUSSION. After ensuring the connectivity, the programming phases can be implemented. As have been mentioned in the design specifications the first thing to be done is dataset creatio
Mr. Pervez Ahmed 6 attendance Mr. Ali Pervez Ahmed 5 attendance Mr. Hassan Ibrahim Ahmed 5 attendance Mr. Suleman Ahmed 6 attendance Mr. Atta ur Rehman 6 attendance Mr. Muhammad Yousuf 6 attendance Mr. Muntazir Mehdi 5 attendance Operating and financial data with key ratios for the six years is annexed.
When the attendance is completed, the system will write the attendance information back to the system database, and the students can query the attendance result information after refreshing. Figure 2 below shows the student attendance process. The teacher logs on to the Web server side to see the attendance information for the course .
ATTENDANCE: 7 points attendance (weekly survey, meeting attendance, classroom attendance) – Attendance at all class events is mandatory – 3 free absence points (two or three days of absence based on attendance points) – Negative points can accumulate without limit – Having someone else sign you in is cheating; don’t do this!
2019 NATIONAL COLLEGE FOOTBALL ATTENDANCE ALL NCAA TEAMS Total Teams Games Attendance Average Change In Total Change In Avg. Home Attendance, Division I-FBS 130 831 34,177,838 41,129 348,051 -380 FBS Neutral-Site Attendance 19 1,061,206 55,853 -244,811 1,436 FBS Bowl Game Attendance # 40 1,637,417 40,935 34,799 -158
access levels. Teacher Access My Gradebook - access to all of your classes, grades and attendance My Students - access the Gradebook by student, view attendance, or choose report options by student My Classes - access your Gradebook, attendance reports, etc. by class Post Daily Attendance - enter or view daily attendance by class or period
Garment Sizing Chart 37 Face Masks 38 PFL Face Masks 39 PFL Face Masks with No Magic Arch 39 PFL Laser Face Masks 40 PFL N-95 Particulate Respirator 40 AlphaAir Face Masks 41 AlphaGuard Face Masks 41 MVT Highly Breathable Face Masks 42 Microbreathe Face Masks 42 Coo
the University, allowing students to check in and out of class using a mobile app or their student ID. Attendance is recorded in a Canvas tool called ODU Attendance Management Tool that integrates attendance data with your course and gradebook. Accessing the tool in Canvas To access the attendance management tool, go to your course menu, then se-
The current systems that are used for updating attendance automatically are usually RFID based, Bio -metric based and MATLAB based. Usually, the manual method of taking attendance is difficult and a time -consuming process. Hence it is import ant to construct an efficient method for managing attendance automatically.
