Automated Monitoring Attendance System Essay
Automated Monitoring Attendance System
1.1 The problem and its scope
In this paper we propose a system that automates the whole process of taking attendance and maintaining its records in an academic institute. Managing people is a difficult task for most of the organizations, and maintaining the attendance record is an important factor in people management. When considering academic institutes, taking the attendance of students on daily basis and maintain the records is a major task. Manually taking the attendance and maintaining it for a long time adds to the difficulty of this task as well as waste a lot of time.
For this reason an efficient system is designed. This system takes attendance electronically with the help of a fingerprint sensor and all the records are saved on a computer server. Fingerprint sensors and LCD screens are placed at the entrance of each room. In order to mark the attendance, student has to place his/her thumb on the fingerprint sensor. On identification student’s attendance record is updated in the database and he/she is notified through LCD screen. No need of all the stationary material and special personal for keeping the records. Furthermore an automated system replaces the manual system.
Nowadays, industry is experiencing many technological advancement and changes in methods of learning. With the rise of globalization, it is becoming essential to find an easier and more effective system to help an organization or company. In spite of this matter, there are still business establishments and schools that use the old-fashioned way. In a certain way, one thing that is still in manual process is the recording of attendance. After having these issues in mind we develop an Automated Monitoring Attendance System, which automates the whole process of taking attendance and maintaining it, plus it holds an accurate records.
Biometric systems have been widely used for the purpose of recognition. These recognition methods refer to automatic recognition of people based on the some specific physiological or behavioral features . There are many biometrics that can be utilized for some specific systems but the key structure of a biometric system is always same . Biometric systems are basically used for one of the two objectives identification  or verification . Identification means to find a match between the query biometric sample and the one that is already been stored in database . For example to pass through a restricted area you may have to scan your finger through a biometric device. A new template will be generated that will be then compared with the previously stored templates in database. If match found, then the person will be allowed to pass through that area.
On the other hand verification means the process of checking whether a query biometric sample belongs to the claimed identity or not . Some of the most commonly used biometric systems are (i) Iris recognition, (ii) Facial recognition,(iii)Fingerprint identification, (iv) Voice identification, (v) DNA identification, (vi) Hand geometry recognition and (viii)Signature Verification .Previously the biometrics techniques were used in many areas such as building security, ATM, credit cards, criminal investigations and passport control . The proposed system uses fingerprint recognition technique  for obtaining student’s attendance. Human beings have been using fingerprints for recognition purposes for a very long time , because of the simplicity and accuracy of fingerprints.
Finger print identification is based on two factors: (i) Persistence: the basic characteristics and features do not change with the time. (ii) Individuality: fingerprint of every person in this world is unique . Modern fingerprint matching techniques were initiated in the late 16th century  and have added most in 20th century. Fingerprints are considered one of the most mature biometric technologies and have been widely used in forensic laboratories and identification units . Our proposed system uses fingerprint verification technique to automate the attendance system. It has been proved over the years that fingerprints of each every person are unique . So it helps to uniquely identify the students.
1.3 Theoretical Background
For over 100 years, fingerprint has been used to identify people. As one of the biometric identification, fingerprint is the quite the most popular one. Besides getting the print for fingerprint is easy, it doesn’t need a special sophisticated hardware and software to do the identification. In the old times and even until now, fingerprints are usually taken using merely inks and papers (could be one print, ten prints, or latent print). Finger print is unique. There is no case where two fingerprints are found to be exactly identical.
During the fingerprint matching process, the ridges of the two fingerprints will be compared. Besides using ridges, some of the identification techniques also use minutiae. In brief, minutiae can be described as point of interest in fingerprints. Many types of minutiae have been defined, such as pore, delta, island, ridge ending, bifurcation, spurs, bridges, crossover, etc, but commonly only two minutiae are used for their stability and robustness (4), which are ridge ending and bifurcation.
To help in fingerprint identification, fingerprint classification method is implemented. There are some classification theories applicable in the real world such as The NCIC System (National Crime Information Center) Still used even until now, the NCIC system classifies fingers according to the combination of patterns, ridge counts, whorl tracing. NCIC determines
.Fingerprint Classification (FPC) field codes to represent the fingerprint characteristics. The following are the field codes tables:
Using NCIC system FPC Field Codes eliminates the need of the fingerprint image and, thus, is very helpful for the need of fingerprint identification for those who do not have access to an AFIS. Instead of relying to the image, NCIC relies more on the finger image information. The Henry and American Classification Systems Henry and American classification systems, although has a lot in common, are actually two different systems developed by two different people. The Henry Classification System (5) was developed by Sir Edward Henry in 1800s; used to record criminals’ fingerprints during Civil War. Henry System used all ten fingerprints with the right thumb denoted number 1, right little left finger denoted number 5, left thumb denoted number 6, and lastly the left little finger denoted number 10.
According to Henry System, there were two classifications; the primary and the secondary. In the primary classification, it was a whorl that gives the finger a value. While even numbered fingers were treated as the nominator, odd numbered fingers were treated as denominator. Each finger’s value was equal to the value of the whorl plus one. In the secondary classification, each hand’s index finger would be assigned a special capital letter taken from the pattern types (radial loop (R), tented loop (T), ulnar loop (U), and arch (A)). For other fingers except those two index fingers, they were all assigned with small letter which was also known as small letter group. Furthermore, a sub secondary classification existed; it was the grouping of loops and whorls, which coded the ridge of the loops and ridge tracings of whorls in the index, middle, and ring fingers. The following is the table of Henry System.
The American Classification System was developed by Captain James Parke. The difference lies in assigning the primary values, the paper used to file the fingerprint, and the primary values calculation.
In this system, all of the fingerprints are stored in cabinets. Each cabinet contains one different classification and, thus, the fingerprint cards are stored accordingly. The existence of AFIS system greatly helps the classification process. There is no need to even store the physical fingerprint cards. AFIS does not need to count the primary values of all those fingers and does not have to be as complicated as NCIC System. With the power of image recognition and classification algorithm, fingerprint identification can be done automatically by comparing the source digital image to the target database containing all saved digital images. Another important issue to know is the fingerprint classification patterns. These patterns are growing with each generation of AFIS and differ from one too to another, searching time and reduced computational complexity.
The first known study of fingerprint classification was proposed by in 1823 by Purkinje, which resulted in fingerprint classification down into 9 categories: transverse curve, central longitudinal strain, oblique stripe, oblique loop, almond whorl, spiral whorl, ellipse, circle, and double whorl. Later on, more in depth study was conducted by Francis Galton in 1892, resulted in fingerprint classification down into 3 major classes: arch, loop, and whorl. Ten years later, Edward Henry refined Galton’s experiment, which was later used by many law enforcement agencies worldwide. Many variations of Henry Galton’s classification schemes exists, however there are 5 most common patterns: arch, tented arch, left loop, right loop, and whorl. The following are types of fingerprint classification patterns:
Since IDAFIS is another extended form of AFIS, we do not need to implement all other classification systems. What we need to do is to see what kind of classification pattern the algorithm can distinguish.
In general, fingerprint matching can be categorized down into three categories: Correlation-based matching: the matching process begins by superimposing (lying over) two fingerprints, and calculating the correlation between both by taking displacement (e.g. translation, rotation) into account. Minutiae – based matching: Minutiae are first extracted from each fingerprint, aligned, and then calculated for their match. Ridge feature – based matching: Ridge patterns are extracted from each fingerprint and compared one with another. The difference with minutiae – based is that
instead of extracting minutiae (which is very difficult to do to low – quality fingerprint image); ridge pattern such as local orientation and frequency, ridge shape, and texture information is used.
Most of the attendance systems use paper based methods for taking and calculating attendance and this manual method requires paper sheets and a lot of stationery material. Previously a very few work has been done relating to the academic attendance monitoring problem. Some software’s have been designed previously to keep track of attendance .But they require manual entry of data by the staff workers. So the problem remains unsolved. Furthermore idea of attendance tracking systems using facial recognition techniques have also been proposed but it requires expensive apparatus still not getting the required accuracy . Automated Monitoring Attendance System is divided into three parts: Hardware/Software Design, Rules for marking attendance and Online Attendance Report. Each of these is explained below. 2 System Description
2 .1 Hardware
Required hardware used should be easy to maintain, implement and easily available. Proposed hardware consists following parts:
(1) Fingerprint Scanner
(2) LCD Screen
Fingerprint scanner will be used to input fingerprint of teachers/students into the computer software. LCD display will be displaying rolls of those whose attendance is marked. Computer Software will be interfacing fingerprint scanner and LCD and will be connected to the network. It will input fingerprint, will process it and extract features for matching. After matching, it will update the database attendance records of the students. A fingerprint sensor device along with an LCD screen is placed at the entrance of each classroom. The fingerprint sensor is used to capture the fingerprints of students while LCD screen notifies the student that his/her attendance has been marked.
2 .2 Rules for marking attendance
This part explains how students and teacher will use this attendance management system. Following points will make sure that attendance is marked correctly, without any problem: (1) All the hardware will be outside of the classroom.
(2) When teacher enters the classroom, the attendance marking will start. Computer software will start the process after inputting fingerprint of the teacher. It will find the Subject ID and current semester using the ID of the teacher or could be set manually on the software. If the teacher doesn’t enter the classroom, attendance marking will not start. (3) After some time, say 15 minutes of this process. The student who login after this time span will be marked as late on the attendance. This time period can be increased or decreased per requirements.
2 .3 Online Attendance Report
Database for attendance would be a table having following fields as a combination for primary field: (1) Day, (2) Roll, (3) Subject and following non-primary fields: (1) Attendance, (2) Semester. Using this table, all the attendance can be managed for a student. For online report, a simple website will be made for it. Which will access this table for showing attendance of students .The sq queries will be used for report generation? Following query will give total numbers of classes held in a certain subject. Now the attendance percent can easily be calculated:
2.4 Using wireless network instead of LAN
We are using LAN for communication among servers and hard wares in the classroom. We can instead use wireless LAN with portable devices. Portable device will have an embedded fingerprint scanner, wireless connection, a
microprocessor loaded with software, memory and a display terminal.
 D. Maltoni, D. Maio, A. K. Jain, S. Prabhaker, “Handbook of Fingerprint Recognition”, Springer, New York, 2003.
 A.C. Weaver, “Biometric authentication”, Computer, 39(2), pp 96 – 97 (2006).  J. Ortega – Garcia, J. Bigun, D. Reynolds and J.Gonzalez – Rodriguez, “Authentication gets personal with biometrics”, Signal Processing Magazine, IEEE, 21(2), pp 50 – 62 (2004).
 Anil K. Jain, Arun Ross and Salil Prabhakar,” An introduction to biometric recognition” , Circuits and Systems for Video Technology, IEEE Transactions on Volume 14, Issue 1, Jan. 2004 Page(s):4 – 20.  Fakhreddine Karray, Jamil Abou Saleh, Mo Nours Arab and Milad Alemzadeh, Multi Modal Biometric Systems: A State of the Art Survey ” , Pattern Analysis and Machine Intelligence Laboratory, University of Waterloo, Waterloo, Canada.  Abdulmotaleb El Saddik, Mauricio Orozco, Yednek Asfaw, Shervin Shirmohammadi and Andy Adler “A Novel Biometric System for Identification and Verification of Haptic Users ” , Multimedia Communications Research Laboratory (MCRLab) School of Information Technology and Engineering University of Ottawa, Ottawa, Canada .
 H. C. Lee and R. E. Gaensslen, “ Advances in Fingerprint Technology ” , Elsevier, New York .  Sharath Pankanti, Salil Prabhakar, Anil K. Jain, “ On the Individuality of Fingerprints ” , IEEE transaction on pattern analysis and machine intelligence, vol.24, no.8, August 2002.  Federal Bureau of Investigation, “ The Science of Fingerprints: Classification and Uses ” , U. S. Government Printing Office, Washington, D. C., 1984.  H. C. Lee and R. E. Gaensslen (eds.), “ Advances in Fingerprint Technology ” , Second Edition, CRC Press, New York, 2001.  K.G.M.S.K. Jayawardana, T.N. Kadurugamuwa, R .G. Rage and S. Radhakrishnan ” , Timesheet: An Attendance Tracking System ”, Proceedings of the Peradeniya University Research Sessions, Sri Lanka, Vol.13, Part II, 18th December 2008 .
 Yohei KAWAGUCHI, Tetsuo SHOJI , Weijane LIN ,Koh KAKUSHO , Michihiko MINOH ,“ Face Recognition – based Lecture Attendance System” , Department of Intelligence Science and Technology, Graduate School of Informatics,\ Kyoto
University. Academic Center for Computing and Media Studies, Kyoto University.  Digital Persona, Inc. t720 Bay road Redwood City, CA 94063 USA 5, http://www.digitalpersona.com
Table of Contents
1.1 The problem and its scope
1.3 Theoretical Background
2.1 Hardware and Software
2.2 Rule for marking attendance
2.3 Online Attendance Report
2.4 Using Wireless network instead of LAN
4.2 Conclusion and Recommendation