LITERATURE REVIEW
2.1 State of art
This project allows the admin to register students of one class with the aid of the handheld device, this handheld device has a SM-630 fingerprint module (Which can store up to 700 fingerprints), an ATMega microcontroller, a 24C5l2electronic erasable programmable read-only memory(EEPROM), a 4 x 20 LCD display in order to accommodate the display of time, date and other information needed for proper usage of device, a keypad and a DSl307 real time clock (RTC).The data can be accessed and transferred to a computer through a serial connector in this case a MAX 232. The computer accesses this data from the Admin Application and stores it in a SQL database.
When the class attendance is being taken the lecturer enters the course code and the device is passed round the class (since it is mobile) then the handheld device authenticates the student and displays a status message showing that the student with registration number attended the class at the end of the process, the lecturer then presses the END key indicating the end of that attendance. The machine then resets and is ready to take a new set of class attendance. Since the device is mobile, a 9volt battery was used to power the handheld device.
2.2 Related works
A number of similar works exist on the implementation of different methods and principles to effectively monitor the attendance of students. In this section, here is an example of some of this other systems and their Working principles.
There have been quite a number of solutions written to enhance the attendance mechanism.
2.2.1 Related systems using Electronic cards
In [2] an embedded computer based lecture attendance management system was proposed. The system provides an improvised electronic card and card reader serially interfaced to the digital computer system. The card reader is kept stationary at the entrance of the classroom so that before the student gets into the class he swipes his card in the card reader then the reader sends information to the server and add a record for the student to the database. After each class it is expected that the student clock in again for the next class by going to the card reader again to swipe the card.
Authors in [3], made use of the barcode technology in their own smart cards, now these are better than magnetic strip swipe which cannot store large information as the other does and this system has less chances of failing according to research made by the authors. The interesting features and functionality of smart card that made it popular is the multi-purpose card it applies. To implement a smart card scheme certain design features is to ensure integrity across applications on multi-purpose cards. Smart cards have three broad functions which are authentication, storing value and storing personalized information. The smart card can also be used as a portable storage device and with the capability of holding a large amount of data of different forms and for different purposes. UiTM students' smart card includes barcode which is completely implemented in order to achieve the aim of this project. The feature of smart card, which it is a portable hardware unit makes it more convenient to use. A smart card is the most convenient and most portable cryptographic hardware unit; public key smart cards are able to perform the signing operation inside the card.
For this project, as the first-time class attendance signing system development, the researcher has decided to use UiTM student's smart card where the connection is made when the barcode reader contacts the barcode on the back of the students' smart card. The barcode reader provides a path for the application to send and receive commands from the barcode on the students' smart card. There are many types of readers on the market, the most prevalent being the serial, PC Card, and keyboard models .Once it can communicate with the reader, there is no protocol for communicating with smart card.
2.2.2 Related systems using R.F.I.D cards
In other to curb the problem of mobility which the systems in the first section have, the Radio frequency identification (R.F.I.D) cards were made such that they are contactless. According to [4]. The contactless card only needs to be passed within 10cm of the reader to perform a transaction by using the Radio Frequency identification (RFID) technology. An RFID technology is a non-touch recognition system that transmits and processes the information on events and environments using a Wireless frequency and small chips.
Typical RFID systems are made up of 2 major components, i.e. the readers and the tags. The reader, which is also called the interrogator, sends and receives radio frequency data to and fro the tags via antennas. A reader may have multiple antennas that are responsible for sending and receiving the radio Waves. The tag or transponder is made up of the microchip that stores the data, an antenna, and a carrier to which the chip and antenna are mounted. The tag antenna is the conductive element that enables the tag to send and receive data. For passive card, lower frequency is about 135 kHz and high-frequency 13.56 MHZ. The tags usually have a coiled antenna that couples with the coiled antenna of the reader to form a magnetic field. Then, the RF energy from the reader antenna is harvested by the antenna and used to power up the microchip, which then changes the electrical load on the antenna to reflect back its own signals.
Below are some solution proffered using the RFID cards.
Authors in [4] used the contactless cards to get information, now this information stored to the reader can be backed up on a system and they provide a medium for querying the database. This system has some functionalities of our proposed system but has two striking differences, the first is the student cannot know if it has registered him for the day due to any uncertainty, secondly it doesn’t still do anything about the “buddy-signing” problem so one student can carry 5 different KFID cards to sign for his friends.
Fi
Figure 2.1: The reader and transponder of RFID system [3]
Figure 2.2: The design flow of the RFID system [3]
In [5] the system uses these inputs to the database as the daily attendance of the student which will be printed out by the school administrator daily, so it has a daily reporting feature. The only difference between this system and that of the other RFID card system is the reporting feature. This reporting feature was achieved by sending this attendance to an SQL server and then it can generate the attendance from the database.
2.2.3 Related systems using facial recognition
Facial recognition is one of the biometric identification techniques. This system uses the face structure and features of the individual to authenticate and register users.
The mechanism was used in [6], the present authors used the Eigen face approach for face recognition which was introduced by Kirby and Sirovich in 1988 at Brown University. The method works by analyzing face images and computing Eigen face which are faces composed of eigenvectors. The comparison of Eigen face is used to identify the presence of a face and its identity. There is a five step process involved with the system developed by Turk and Pentland. First, the system needs to be initialized by feeding it a set of training images of faces. This is used to define the face space which is set of images that are face like. Next, when a face is countered it calculates an Eigen face for it. By comparing it with known faces and using some statistical analysis it can be determined whether the image presented is a face at all. Then, if an image is determined to be a face the system will determine whether it knows the identity of it or not. The optional final step is that if an unknown face is seen repeatedly, the system can learn to recognize it.
The two main components used in the implementation approach are open source computer vision library (OpenCV) and Face Light Tool Kit (FLTK). One of OpenCV’s goals is to provide a simple-to-use computer vision infrastructure that helps people build fairly sophisticated vision applications quickly. OpenCV library contains over 500 functions that span many areas in vision. The primary technology behind Face recognition is OpenCV; the interface is designed using FTLTK. The user stands in front of the camera keeping a minimum distance of 50cm and his image is taken as an input. The frontal face is extracted from the image then converted to gray scale and stored. The Principal component Analysis (PCA) algorithm is performed on the images and the Eigen values are stored in an xml file. When a user requests for recognition the frontal face is extracted from the captured video frame through the camera. The Eigen value is re-calculated for the test face and it is matched with the stored data for the closest neighbor. [6]
Figure 2.3: Architecture of the facial recognition system (6)
Figure 2.4: Operation of the system [6]
Authors in [7] also used the facial recognition system but implemented it in a different Way. The system designed is part of an in-house built learning management suite .It is constructed in many modules: Image capturing, Face Detector and Face recognizer. The required infrastructure in classroom is a rotating camera positioned centrally in the front of the classroom. Using this setup, the camera is capable to capture frontal images from students A different approach would be to use a camera at the entrance of the classroom, which would individually detect faces for everyone entering the classroom. This Way, the face detector would have much less Work to do, but there would be only one chance to capture a good frame. A frontal camera in the middle of the classroom can take as many pictures as necessary. Physically the system is integrated on the existing South East European Universities infrastructure. To function, the system requires each classroom to have at least one internet connected computer. This computer communicates with the Learning Management system (LMS) server, where captured images are transferred. Figure. 2.5 depicts the physical architecture of this system.
Figure 2.5: The Physical architecture of the system [7]
2.2.4 Related systems using Ear Recognition
In [8] a technique based on ear is also introduced that is a photo of the subject’s ear is taken and fed into the computer. Edge detection is carried out on this picture. From this detected edge, is separated a reference line with respect to which other features are identified. These extracted features are stored in a database in the form of a Vector, each vector corresponding to a particular image in the database. The feature vector of the test image obtained is compared with those in the vector database, For creating and maintaining database for records of individuals and feature vectors, Which are used for the purpose of comparison and decision making, linking of MATLAB and some data base using Open Database connectivity (ODBC) Drivers is carried out according to when a match is calculated. This match is compared with a decided threshold value, which decides the identity of the person.
Figure 2.6: Ear based attendance system framework [8]
2.2.5 Related systems using fingerprint recognition systems
In [9] the proposed student attendance system uses the fingerprint recognition techniques, the project can be divided in two parts, the hardware architecture and the software architecture. The hardware architecture can be divided into two categories which are fingerprint scanner which captures the image and a personal computer which: houses the database, runs the comparison algorithm and simulates the application function. The fingerprint scanner is connected to the computer via its USB interface. Basically this work does not involve the development of hardware. Using the Secugen Fingerprint Reader, the GrFinger Software Development Kit (SDK) toolbox provided by the Griaule (will explain the detail) can be used as an interface between the fingerprint reader and the attendance software.
Figure 2.7: USB module fingerprint scanner [9]
The software architecture consists of the database and the application program. The database consists of tables that stores records implemented in MySQL database. The application program is developed with Python3 programming language and it provides a user interface for the Attendance Management System.
Figure 2.8: the Attendance form of the software [9]
The fingerprint technology was also implemented in [10], A handheld device consisting of 8051 microcontroller is programmed in such a way that the USN (University Serial Number) or roll number is displayed on the LCD display, Buttons are kept to mark present and absent. Each student’s USN is unique and hence it is taken as the keyword and the present and absent is marked against it. The above process is repeated till present/absent field is marked for the last student. The User serial Number (USN) along with the present/absent field is stored in the memory. Figure 2.10 shows the development board used in this project; LCD unit is used to display the USN, The RS232 driver on board allows easy connection with PC or other embedded hardware. The board has User buttons to mark the student status as present or absent, and a special key is dedicated to send the data out to the computer via serial port, and status LEDs. RS232 (serial port) socket, is used for communication Quartz crystal with ll.0592 MHZ frequency, reset button, power plug-in jack, an LED for power GN and OFF, an LCD display slot and a slot to place 8051 IC[pv89v5lrd2]. The MAX232 is an integrated circuit that converts signals from an RS-232 serial port to signals suitable for use in TTL compatible digital logic circuits.
Figure 2.9: the working model of the automated attendance system [10]
Figure 2.10: the circuitry of the automated attendance system [10]
2.3 Summary of Reviewed literatures
System described in [2] and [3] only takes the attendance of the system when the student swipes in the card, this system is not mobile and still encourages buddy-signing as one student can still sign for his friend. In conclusion, the only difference between this and the normal paper method is that this is more accurate and just a bit faster. The systems described in [4] and [5] are efficient and can be set to take attendance for every class by setting it to take attendance at certain times of the day but the system still allows buddy-signing and a student can just leave his RFID cards in class While he is away. The systems in [6], [7] and [8] are very efficient, accurate and have high efficiency but they are capital intensive, complex and time consuming.
The system discussed in [9] has a very high efficient, development time is minimal, it offers reporting and ability to query its database but it is not mobile, the students have to queue up to take the attendance and do the same for the next class and also it needs to be connected directly to a system for each device so if it was to be implemented in a school, computers will have to be bought for each class. The system discussed in [10] is efficient but has various shortcomings; the lecturer has to take the attendance since for those absent the down button must be pressed. The system doesn’t have a Way to report the attendance in a user friendly manner.