International Journal of Emerging Research in Management &Technology Research Article May 2016 Special Issue on International Conference on Advances in Engineering (ICAE) -2016 Conference Held at Hotel Magaji Orchid, Sheshadripuram, Bengaluru, India. Face Recognition Based Attendance Monitoring System Vadiraj. M Vinay Raghavendra. R Prem Sagar. S Vinod Kumar. B UG Scholar UG Scholar UG Scholar UG Scholar Dept. of ECE Dept. of ECE Dept. of ECE Dept. of ECE KSIT, Bengaluru, India KSIT, Bengaluru, India KSIT, Bengaluru, India KSIT, Bengaluru, India Rajeshwari Devi. D. V Asst. Professor Dept. of ECE KSIT, Bengaluru, India Vikram. R. Lakkavalli Asst. Professor Dept. of ECE KSIT, Bengaluru, India Abstract Attendance marking is one of the important tasks in each and every organization. There are many traditional methods proposed for the same. This paper aims at providing one of the efficient methods for marking the attendance. The attendance will be marked based on facial recognition of the person.agroup image of the class will be captured and detected faces are segmented from the captured image. The segmented faces are then compared with a predefined database of all the students of the class. A message will be sent to absenteesthroughsms using a GSM module. Index Terms- Face detection, Face segmentation, Face recognition, PCA, GSM. I. INTRODUCTION Maintaining the attendance is very important in all the institutes for checking the presence of students. Every institute has its own method in this regard. Some are taking attendance manually using the traditional pen and paper or file based approach and some have adopted methods of automatic attendance techniques. There are many methods existing for this purpose they are: Fingerprint Based System Iris Recognition RFID Based System Face Recognition [1][3] The first three methods proved inefficient because students have to make a queue to touch their thumb on the scanning device which consumes the time. This system uses the face recognition approach for the automatic attendance of students in the classroom environment without student s intervention [5]. This attendance is recorded by using a camera attached in the classroom that is continuously capturing images of students, detect the faces in images and compare the detected faces with the student database and mark the attendance [4]. The system consists of a camera that captures the images of the students sitting in the classroom and sends it to the image enhancement module. In the image enhancement module, images are enhanced so that matching can be performed easily. After enhancement, the image comes in the face detection and recognition modules. At the time of enrollment, templates of face images of individual students are stored in the face database. The faces are detected from the captured by camera. In the recognition module the detected faces are constantly compared against stored database. If any face is recognized the attendance is updated and can be accessed by anyone, the information will be sent to the absentees parents using GSM technology. The block diagram of face recognition system is shown in Fig1. CAMERA 16X2 LCD DISPLAY PC ARM 7 CONTROLLER GSM POWER SUPPLY Fig. 1 Block Diagram of the System 2016, IJERMT All Rights Reserved Page 254
II. METHODOLOGY The proposed system uses Viola-Jones algorithm for face detection [2]. The Viola Jones face object detection frame work proposed in 2001 by Paul Viola and MichaelJones.is the first object detection framework to provide competitive object detection rates in real-timeface feature based approaches can be subdivided into low level and high level analysis, feature analysis and active shape model analysis [2].Face detection techniques can be categorized into two major groups that are feature based approaches and image based approaches. Image and video based approaches use linear subspace method, neural networks and statistical approaches for face object detection.face detection is controlled by special trained scanning window classifiers Viola-Jones Face Detection Algorithm is the first real-time face detection system. The system uses PCA (Principal Component Analysis) which is an efficient method for face recognition [4]. The system functions by projecting face image onto a feature space that spans the significant variations among known face images. The significant features are known as Eigen faces, because they are the eigenvectors (Principal Component) of the set of faces that do not necessarily correspond to the features such as eyes, ears, and noses [1][4][7]. The projection operation characterize an individual face by a weighted sum of the Eigen faces features and so to recognize a particular face it is necessary only to compare The methodology flows in the following manner: START IMAGE DETECTION SEGMENTATION RECOGNIZED IMAGE = STUDENT ID RECOGNITION DATA SET NO YES RECORD ATTENDANCE DATABASE GENERATE REPORT DISPLAY RESULT SEND SMS NOTIFICATION STOP Fig. 2 Methodology A. Creation of database The database is created, in prior to recognition process, which constitutes of images of all students of the class under different criterions like different facial elevations or positions and different lighting conditions. B.Capturing the image The next step is to continuously capture the image of the students in the classroom in order to get adjusted to proper lighting conditions and elevations. C. Face Detection The next part is face detection which determines the location and sizes of human faces in the captured image. The faces are detected from the captured image using Viola-Jones algorithm. D. Face Segmentation The main objective here is to eliminate the foreign objects other than faces, which are detected [3]. The detected faces are segmented from the image and are pre-processed and stored for recognition [3][4]. The segmented image will be converted to gray scale for efficient recognition. E. Face Recognition The face recognition is the most important part of this system. It is an automatic method of identifying or verifying a person from a digital image or a video frame. It is done by comparing the extracted features from the captured image with the images that are previously stored in the predefined database. The recognition process is implemented using PCA algorithm [5]. 2016, IJERMT All Rights Reserved Page 255
PCA is used here because it is one of the simplest method or algorithm for multivariate analysis [5]. It involves in transformation of data into a new coordinate system. The main aim in PCA is to reduce the dimensions of data and to decompose face structure into orthogonal and uncorrelated components which are called Eigen faces [4][6]. The face image is a weighted sum of Eigen faces which can be 1-dimensional array [6]. F. Identification of absentees and sending a SMS The absentees are those who are present in the data base but not in the captured image. An automatic SMS notification will be sent to the mobile numbers of the absentees. III. SOFTWARE SETUP The name MATLAB is expanded as Matrix Laboratory. MATLAB is a high performance language for technical computing. It integrates computation, visualization, and programming environment. It has sophisticated data structures, contains built-in editing and debugging tools, and supports object oriented programming. These factors make MATLAB an excellent tool for teaching and research.there are tool boxes in MATLAB for signal processing, image processing, symbolic computation, control theory, simulation, optimization, and several other applied sciences. The software part of this system is implemented using MATLAB version R2013a. IV. HARDWARE SETUP The hardware components used for the system includes: A. Camera B. ARM7 Controller C. Display Unit D. GSM Module A. Camera The camera used here is a PC web camera that captures the images of students for both database creation and test images. B. ARM7 Controller The ARM 7 controller is a 32-bit ARM7 TDMI-S microcontroller in a tiny LQFP64 package. It has 8 kb to 40 kb of onchip static RAM and 32 kb to 512 kb of on-chip flash memory and 128-bit wide interface/accelerator enables high-speed 60 MHz operation. It has In-SystemProgramming/In-Application Programming (ISP/IAP) via on-chip boot loader software. Single flash sector or full chip erase in 400 ms and programming of256 B in 1 ms.in addition, the LPC2148 provides 8 kb of on-chip RAM accessible to USB by DMA.One or two (LPC2141/42 vs. LPC2144/46/48) 10-bit ADCs provide a total of 6/14analog inputs, with conversion times as low as 2.44s per channel.single 10-bit DAC provides variable analog output (LPC2142/44/46/48 only). There are two 32-bit timers/external event counters (with four capture and four comparechannels each), PWM unit (six outputs) and watchdog timer. Additionally, it has low power Real-Time Clock (RTC) with independent power and 32 khz clock input. C. Display Unit The LCD is used as a display unit in the system to display the results. A 16x2 display and 4 data pins are being used. The operating voltage of LCD is 5V. D.GSM Module A GSM 900 module is a self-contained dual-band modem.this modem supports transmissions like data, fax, Short Messages (Point to point and cell broadcast) and voice calls. The main features of the modem are as follows: 2 watts E-GSM 900 radio section 1 Watt GSM1800 radio section. Echo Cancellation and noise reduction. Full GSM or GSM / GPRS software stack. It also comprises several interfaces like LED function indicating the operating status. External antenna (via SMA connector). RS232 Serial (via 9-pin SUB HD connector). Power supply (via 2.5mm DC power jack). SIM card holder. V. RESULTS The results obtained in MATLAB are given below. From the group image, faces are detected and the recognised faces are found to be correctly matching with the actual face image. 2016, IJERMT All Rights Reserved Page 256
Fig. 3 Input image and detected faces Fig. 4 Test image 1 and its recognized image Fig. 7 Test image 2 and its recognized image Fig. 8 Test image 3 and its recognized image 2016, IJERMT All Rights Reserved Page 257
The recognized persons ID s are sent to the ARM controller and the same is displayed in the LCD Fig. 9 LCD output VI. CONCLUSION This system provides an efficient method for monitoring the attendance using face recognition. This approach has overcome major time constraints that are encountered with other attendance monitoringsystems like biometrics and RFID systems. A SMS notification will be sent to absentees. VII. FUTURE WORKS In future, the system can be enhanced to recognize a large group of students or used in campus surveillance. The personal computer can be replaced with a Raspberry-Pi processor which makes the system compact and efficient. REFERENCES [1] Kandla Arora. Real Time Application of Face Recognition Concept. International Journal of Soft Computing and Engineering, November 2012. [2] Yi-Qing Wang. An Analysis of the Viola-Jones Face Detection Algorithm. Image Processing On Line, June 2014. [3] Pankaj Agarwal, Dr. S. K. Shriwastava. Dr. S. S. Limaye. MATLAB Implementation of Image Segmentation Algorithms. IEEE, 2010. [4] Mrunmayee Shirodkar, Varun Sinha, Urvi Jain, bhushan Nemade. Automated Attendance Management System Using Face Recognition. International Journal of Computer Applications. [5] Ajinkya Patil, Mrundang Shukla. Implementation of Classroom Attendance Based on Face recognition in Class. International Journal of Advances in Engineering and Technology, July 2014. [6] Abhishek Jha. Class Room Attendance System Using Facial Recognition System. The International Journal of Mathematics, Science, Technology and Management. [7] Rafael C. Gonzalez. Digital Image Processing Using MATLAB, TMH, 2 nd Edition 2010 [8] http://www.mathworks.in 2016, IJERMT All Rights Reserved Page 258