Student Attendance By Image Analysis

A project Report

on

Biometric Approach Towards Student Attendance System

By

Anurag Srivastava BE/5568/10

Nikhil Sharma BE/5668/10

Niharika Gupta BE/5769/10

Under the guidance of

Prof. Smita Pallavi

Submitted in partial fulfillment of the requirement for the award of the

Degree of

Bachelor of Engineering in computer science

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

BIRLA INSTITUTE OF TECHNOLOGY

MESRA, PATNA CAMPUS

November 1,2013

ACKNOWLEDGEMENT

We would like to sincerely thank our mentor, Mrs. Smita Pallavi, Asst. Prof. ,

Computer Science and Engineering Department, BIT Mesra, Patna Campus for

her sagacious guidance and invaluable suggestions. We are grateful to her for

giving us an opportunity to work on “Biometric Approach Towards Student

Attendance System” with her. We would be ever indebted to her for planning of

the work, critical appraisal of the script and compilation of the project. With

sincere gratitude, we would also like to extend thanks to Dr. Kanhaiya Lal (In-

charge, Department of Computer Science and Engineering, BIT-Patna) for his

timely guidance.

We owe special thanks to Prof. Ashish Ranjan for his support in better

understanding of the concepts of Image Processing. This list is obviously

incomplete but allow us to submit that the omissions are inadvertent and we once

again record our deep-felt gratitude to all those associated with us in this endeavor.

Anurag Srivastava BE/5568/10

Nikhil Sharma BE/5668/10

Niharika Gupta BE/5769/10

Contents

1. Introduction

1.1 Problem Statement

1.2 Motivation and Challenges

1.3 Using Biometrics

1.4 Fingerprints

1.5 Why use Fingerprints?

1.6 Using Fingerprints for Student Attendance System.

2. Attendance Management Framework

2.1 Hardware-Software level design

2.2 Implementation Design

2.3 E-R Diagram

2.4 Network Design

2.5 Portable Device using wireless LAN

2.6 Data Flow Diagram

2.7 Database Management

2.8 Online Report Generation

3. Fingerprint Identification System

3.1 How Fingerprint Recognition Works?

3.2 Fingerprint Identification system flowchart

4. Fingerprint Enhancement

4.1 Segmentation

4.2 Normalization

4.3 Orientation Estimation

4.4 Ridge Frequency Estimation

4.5 Binarisation

4.6 Thinning

5. Fingerprint Recognition and Matching

5.1 Fingerprint Recognition

5.2 Matching

6. Software Design and Working Model

7. Future Work

8. Conclusion

9. References

10. Appendix

10.1 Matlab Functions used

Abstract

Biometric involves the identification and verification of individuals by analyzing

the human fingerprint characteristics. It has been widely used in various aspect of

life for different purposes. This project aims at effectively using this technology to

manage attendance of students at institutes like BIT Mesra automatically.

Manually taking the attendance and maintaining it for a long time makes it a

difficult task. Also it wastes a lot of time. This system takes attendance with the

help of a finger-print sensor module and all the records are saved on a computer. In

this project edge detection algorithm has been implemented for fingerprint

matching. This system is implemented in Matlab7 software. The hardware and

software can be integrated to make a portable attendance monitoring system. Our

matching technique runs in O (n) time.

Chapter 1

Introduction

1.1 Problem Statement

Designing a Student Attendance Management system based on fingerprint

recognition and faster one to many identification that manages records for

attendance in institutes.

1.2 Motivation and Challenges

Designing a better attendance management system for students so that records are

maintained with ease and accuracy was an important key behind motivating this

project. This would improve accuracy of attendance records because it will remove

all the hassles of roll calling and will save valuable time of the students as well as

teachers. Image processing and fingerprint recognition are very advanced today in

terms of technology.

1.3 Using Biometrics

Biometric Identification Systems are widely used for unique identification of

humans mainly for verification and identification. Biometrics is used as a form of

identity access management and access control. So use of biometrics in student

attendance management system is a secure approach. There are many types of

biometric systems like fingerprint recognition, face recognition , voice recognition,

iris recognition, palm recognition, , DNA recognition etc. In this project, we used

fingerprint recognition system.

1.4 Fingerprint

A fingerprint is an impression of the friction ridges on all parts of the finger. A

friction ridge is a raised portion of the epidermis on the palm or digits (fingers and

toes) or plantar (sole) skin, consisting of one or more connected ridge units of

friction ridge skin. These are sometimes known as "epidermal ridges" which

caused by the underlying interface between the dermal papillae of the dermis. [1].

It is believed that no two people have identical fingerprint in world, so the

fingerprint verification and identification is most popular way to verify the

authenticity or identity of a person wherever the security is a problematic question.

The reason for popularity of fingerprint technique is uniqueness of person arises

from his behavior; personal characteristics are like, for instance uniqueness, which

indicates that each and every fingerprint is unique, different from one other.

When human fingerprint experts determine if two fingerprints are from the same

finger, the matching degree between two minutiae pattern is one of the most

important factors. Thanks to the similarity to the way of human fingerprint experts

and compactness of templates, the minutiae-based matching method is the most

widely studied matching method.

1.5 Why use fingerprints? Fingerprints are considered to be the best and fastest method for biometric

identification. They are secure to use, unique for every person and does not change

in one's lifetime. Besides these, implementation of fingerprint recognition system

is cheap, easy and accurate up to satisfiability.

Fingerprint recognition has been widely used in both forensic and civilian

applications. Compared with other biometrics features , fingerprint-based

biometrics is the most proven technique and has the largest market shares . Not

only it is faster than other techniques but also the energy consumption by such

systems is too less.

1.6 Using fingerprint recognition system for attendance

management

Managing attendance records of students of an institute is a tedious task. It

consumes time and paper both. To make all the attendance related work automatic

and on-line, we have designed an attendance management system which could be

implemented in various institutes. It uses a fingerprint identification system

developed in this project. This fingerprint identification system uses existing as

well as new techniques in fingerprint recognition and matching.

Chapter 2

Attendance Management Framework

Manual attendance taking and report generation has its limitations. It is well

enough for 30-60 students but when it comes to taking attendance of students large

in number, it is difficult. For taking attendance for a lecture, a conference, etc. roll

calling and manual attendance system is a failure. Time waste over responses of

students, waste of paper etc. are the disadvantages of manual attendance system.

Moreover, the attendance report is also not generated on time.

To overcome these non-optimal situations, it is necessary that we should use an

automatic on-line attendance management system. So we present an

implementable attendance management framework. Student attendance system

framework is divided into three parts :

Hardware/Software Design,

Attendance Management Approach, and

On-line Report Generation.

Each of these is explained below.

2.1 Hardware - Software Level Design .

Proposed hardware consists following parts:

(1)Fingerprint Scanner,

(2)LCD/Display Module (optional),

(3)Computer

(4)LAN Connection

Fingerprint scanner will be used to input fingerprint of students into the computer

software.

LCD can be used to view the details of any individual student. However, the

display part can be implemented on the computer.

Fingerprint module

A computer can act as a server where the information of students can be stored and

their easy retrieval is possible. Computer Software present on this computer 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 database attendance records of the students.

Proposed software architecture consists of the database and the application

program.

Database: Record file stores all the information of the registered students as well

as their attendances in every subject.

Application Program: The application program is developed with Matlab7. It

provides a graphical user interface for the Attendance Management System. The

advantage of using of Matlab7 is its easy integration with the hardware.

Hardware present in classrooms

2.2 Implementation Process

Following points will make sure that attendance is marked correctly, without any

problem:

(1) All the hardware will be inside classroom. In this way outside interference will

be least. C-CTV cameras can be installed to prevent unauthorized access and

unprivileged activities.

(2) When teacher enters the classroom, the attendance marking will start.

Computer Software will start the process after taking login password from the

teacher.

(3) After some time, say 20 minutes of this process, no attendance will be given

because of late entrance. This time period can be increased or decreased as per

requirements.

(4) If attendance has already been marked, student is not able to mark another

attendance in the same lecture. This will show error on LCD screen.

Classroom Scenario

2.3 E-R Diagram

E-R Diagram

2.4 Network Diagram This attendance system will be spread over a wide network from classrooms via

intranet to internet. Network diagram is shown in fig. Using this network,

attendance reports will be made available over internet and e-mail. A monthly

report will be sent to each student via email and website will show the updated

attendance.

Network Diagram

We are using LAN for communication among servers and hardwares in the

classrooms. We can instead use wireless LAN with portable devices. Portable

device will have an embedded fingerprint scanner, wireless connection, a

microprocessor loaded with a software, memory and a display terminal.

Size of device could be small like a mobile phone depending upon how well the

device is manufactured.

2.5 Portable Device using Wireless LAN to implement

attendance system

Portable Device

This device should have a wireless connection. Using this wireless connection,

attendance taken would be updated automatically when device is in network of the

nodes which are storing the attendance records. Database of enrolled fingerprints

will be in this portable device. Size of enrolled database was 12.1 MB when 150

fingerprints were enrolled in this project. So for 10000 students, atleast 807 MB or

more space would be required for storing enrolled database. For this purpose, a

removable memory chip could be used. We cannot use wireless LAN here because

fetching data using wireless LAN will not be possible because of less range of

wireless devices.So enrolled data would be on chip itself. Attendance results will

be updated when portable device will be in the range of nodes which are storing

attendance reports.

We may update all the records online via the mobile network provided by different

companies. Today 3G network provides sufficient throughput which can be used

for updating attendance records automatically without going near nodes. In such

case, the need of database inside memory chip will not be mandatory. It will be

fetched by using 3G mobile network from central database repository. The design

of such a portable device is the task of embedded system engineers.

Using Portable Device

In this section, we suggest the working of portable device and the method of using

it for marking attendance. The device may either be having touchscreen

input/display or buttons with lcd display. A software specially designed for the

device will be running on it. Teachers will verify his/her fingerprint on the device

before giving it to students for marking attendance. After verifying the teacher's

identity, software will ask for course and and other required information about the

class which he or she is going to teach. Software will ask teacher the time after

which device will not mark any attendance. This time can vary depending on the

teacher's mood but our suggested value is 25 minutes. This is done to prevent late

entrance of students. This step will hardly take few seconds. Then students will be

given device for their fingerprint identification and attendance marking. In the

continuation, teacher will start his/her lecture. Students will hand over the device

to other students whose attendance is not marked. After 25 minutes or the time

decided by teacher, device will not input any attendance. After the class is over,

teacher will take device and will end the lecture. The main function of software

running on the device will be fingerprint identification of students followed by

report generation and sending reports to servers using 3G network. Other functions

will be downloading and updating the database available on the device from

central database repository.

2.6 Data Flow Diagram

Level 0 DFD

Level 1 DFD

2.7 Database Management

Database storage contains the fingerprint templates of students along with their

information (names, registration numbers, roll number and Subjects/lectures).

When student enrolls his/her finger on the fingerprint sensor module his/her

fingerprint is matched with database to mark the attendance.

2.8 On-Line Attendance Report Generation

Database for attendance can be stored in tabular form but here we are avoiding any

external storage means due to unavailability of MYSQL toolbox in matlab for

students .

Here database is stored in the form of structures .Primarily two structures are

maintained:

1. Student with attributes as

Name

Roll

Course

Day

2. Attendance with attributes as

Subject

Roll

Name

Attendance

Using this information, all the attendance can be managed for a student.

To implement multiple subjects teachers can have a separate structures with

attributes as subjects ,name, teacher_id.

For on-line report generation, a simple website can be hosted on college servers.

2.4 COMPARISON WITH OTHER STUDENT ATTENDANCE SYSTEMS

There are various other kinds of student attendance management systems available

like RFID based student attendance system and GSM-GPRS based student

attendance system.

Our system is better because first it saves time that could be used for teaching.

Second is its portability

[1]. Portability has its own advantage because the device could be taken to any

class wherever it is scheduled because it is dynamic. In GSM-GPRS based

systems, it use position of class for attendance marking which is not dynamic and

if schedule or location of the class changes, wrong attendance might be marked.

Problem with RFID based systems is that students have to carry RFID cards and

also the RFID detectors are needed to be installed. But, students may give proxies

easily using friend's RFID card. These problems are not in our system

[2]. We used fingerprints as recognition criteria so proxies cannot be given. If

portable devices are used, attendance marking will be done at any place and any

time. So our student attendance system is far better to be implemented.

Chapter 3

Fingerprint Identification System

An identification system is one which helps in identifying an individual among

many people when detailed information is not available. It may involve matching

available features of candidate like fingerprints with those already enrolled in

database.

3.1 How Fingerprint Recognition works?

Fingerprint images that are found or scanned are not of optimum quality. So we

remove noises and enhance their quality. We extract features like minutiae and

others for matching. If the sets of minutiae are matched with those in the database,

we call it an identified fingerprint. After matching, we perform post-matching steps

which may include showing details of identified candidate, marking attendance etc.

A brief flowchart is shown in next section.

3.2 Fingerprint Identification System Flowchart

A brief methodology of our Fingerprint Identification System is shown here in

following flowchart. Each of these are explained in the later chapters.

System Flowchart during fingerprint recognition

Chapter 4

Fingerprint Enhancement

The image acquired from scanner is sometimes not of perfect quality .It gets

corrupted due to irregularities and non-uniformity in the impression taken and due

to variations in the skin and the presence of the scars, humidity, dirt etc. To

overcome these problems , to reduce noise and enhance the definition of ridges

against valleys, various techniques are applied as following.

4.1 Segmentation

Image segmentation separates the foreground regions and the background regions

in the image. The foreground regions refer to the clear fingerprint area which

contains the ridges and valleys. This is the area of interest. The background regions

refer to the regions which are outside the borders of the main fingerprint area,

which does not contain any important or valid fingerprint information. The

extraction of noisy and false minutiae can be done by applying minutiae extraction

algorithm to the background regions of the image. Thus, segmentation is a process

by which we can discard these background regions, which results in more reliable

extraction of minutiae points. The background regions exhibit a very low grey -

scale variance value, whereas the foreground regions have a very high variance.

Firstly, the image is divided into blocks and the grey-scale variance is calculated

for each block in the image. If the variance is less than the global threshold, then

the block is assigned to be part of background region or else it is part of foreground

. The grey - level variance for a block of size S x S can be calculated as:

where Var(k) is the grey - level variance for the block k , G(i,j) is the grey – level

value at pixel (i,j) , and M(k) denotes the mean grey - level value for the

corresponding block k .

4.2 Normalization

Image normalization is the next step in fingerprint enhancement process.

Normalization is a process of standardizing the intensity values in an image so that

these intensity values lie within a certain desired range. It can be done by adjusting

the range of grey-level values in the image. Let G (i, j) denotes the grey-level value

at pixel (i, j), and N(i, j) represent the normalized grey-level value at pixel (i, j).

Then the normalized image can defined as:

Where Mo and Vo are the estimated mean and variance of I(i, j), respectively .

4.3 Orientation estimation The orientation field of a fingerprint image defines the local orientation of the

ridges contained in the fingerprint . The orientation estimation is a fundamental

step in the enhancement process as the subsequent Gabor filtering stage relies on

the local orientation in order to effectively enhance the fingerprint image. The least

mean square estimation method used by Raymond is used to compute the

orientation image. However, instead of estimating the orientation block-wise, we

have chosen to extend their method into a pixel-wise scheme, which produces a

finer and more accurate estimation of the orientation field. The steps for

calculating the orientation at pixel (i, j) are as follows:

1. Firstly , a block of size W x W is centered at pixel (i, j) in the normalized

fingerprint print image.

2. For each pixel in the block, compute the gradients dx (i, j) and dy (i, j),

which are the gradient magnitudes in the x and y directions, respectively.

The horizontal Sobel operator is used to compute dx(i, j) :[1 0 -1; 2 0 -2;1 0

1]

3. The local orientation at pixel (i, j) can then be estimated using the following

equations:

where θ(i, j) is the least square estimate of the local orientation at the block

centered at pixel θ(i, j).

Orientation Estimation

4. Smooth the orientation field in a local neighbourhood using a Gaussian

filter. The orientation image is firstly converted into a continuous vector

field, which is defined as:

where ᶲ x and ᶲ y are the x and y components of the vector field,

respectively.

4.4 Ridge Frequency Estimation

Another important parameter,in addition to the orientation image, that can be used

in the construction of the Gabor filter is the local ridge frequency. The local

frequency of the ridges in a fingerprint is represented by the frequency image.

The first step is to divide the image into blocks of size W x W.

In the next step we project the grey-level values of each pixels located inside each

block along a direction perpendicular to the local ridge orientation. This projection

results in an almost sinusoidal-shape wave with the local minimum points denoting

the ridges in the fingerprint.It involves smoothing the projected waveform using a

Gaussian lowpass filter of size W x W which helps in reducing the effect of noise

in the projection. The ridge spacing S(i, j) is then calculated by counting the

mediannumber of pixels between the consecutive minima points in the projected

waveform.The ridge frequency F(i, j) for a block centered at pixel (i, j) is given as

4.6 Binarisation

Most minutiae extraction algorithms operate on basically binary images where

there are only two levels of interest: the black pixels represent ridges, and the white

pixels represent valleys. Binarisation converts a greylevel image into a binary

image. This helps in improving the contrast between the ridges and valleys in a

fingerprint image,and consequently facilitates the extraction of minutiae. One very

useful property of the Gabor filter is that it contains a DC component of zero,

which indicates that the resulting filtered image has a zero mean pixel value.

Hence, binarisation of the image can be done by using a global threshold of zero.

Binarisation involves examining the grey-level value of every pixel in the

enhanced image, and, if the grey-level value is greater than the predefined global

threshold, then the pixel value is set to value one;else, it is set to zero.

The outcome of binarisation is a binary image which contains two levels of

information, the background valleys and the foreground ridges.

4.7 Thinning

Thinning is a morphological operation which is used to remove selected

foreground pixels from the binary images. A standard thinning algorithm from [1]

is used, which performs this operation using two sub iterations. The algorithm can

be accessed by a software MATLAB via the `thin' operation of the bimorph

function. Each sub iteration starts by examining the neighbourhood of every pixel

in the binary image, and on the basis of a particular set of pixel-deletion criteria, it

decides whether the pixel can be removed or not. These subiterations goes on until

no more pixels can be removed.

(a)Original Image, (b)Enhanced Image, (c)Binarised Image, (d)Thinned

Image

Chapter 5

Fingerprint Recognition and Matching

Fingerprint Recognition

The fingerprint recognition problem can be grouped into three sub-domains:

fingerprint enrollment,

verification and

fingerprint identification.

In addition, different from the manual approach for fingerprint recognition by

experts, the fingerprint recognition here is referred as AFRS (Automatic

Fingerprint Recognition System), which is program-based. Verification is typically

used for positive recognition, where the aim is to prevent multiple people from

using the same identity. Fingerprint verification is to verify the authenticity of one

person by his fingerprint. There is one-to one comparison in this case. In the

identification mode, the system recognizes an individual by searching the

templates of all the users in the database for a match. Therefore, the system

conducts a one to-many comparison to establish an individual’s identity.

The following are Fingerprint Recognition Techniques:

A. Minutiae Extraction Technique

Most of the finger-scan technologies are based on Minutiae. Minutia-based

techniques represent the fingerprint by its local features, like terminations and

bifurcations. This approach has

been intensively studied, also is the backbone of the current available fingerprint

recognition products . This is the most popular and widely used technique, being

the basis of the fingerprint comparison made by fingerprint examiners. Minutiae

are extracted from the two fingerprints and stored as sets of points in the two-

dimensional plane. Minutiae-based matching essentially consists of finding the

alignment between the template and the input minutiae sets those results in the

maximum number of minutiae pairings.

B. Pattern Matching or Ridge Feature Based Techniques Feature extraction and template generation are based on series of ridges as opposed

to discrete points which forms the basis of Pattern Matching Techniques. The

advantage of Pattern Matching techniques over Minutiae Extraction is that

minutiae points may be affected by wear and tear and the disadvantages are that

these are sensitive to proper placement of finger and need large storage for

templates. Pattern based algorithms compare the basic fingerprint patterns (arch,

whorl, and loop) between a previously stored template and a candidate fingerprint.

This requires that the images be aligned in the same orientation. To do this, the

algorithm finds a central point in the fingerprint image and centers on that. In a

pattern-based algorithm, the template contains the type, size, and orientation of

patterns within the aligned fingerprint image. The candidate fingerprint image is

graphically compared with the template to determine the degree to which they

match.

C. Correlation Based Technique

Two fingerprint images are superimposed and the correlation between

corresponding pixels is computed for different alignments (e.g. various

displacements and rotations). The cross-correlation is a well-known measure of

image similarity and the maximization in (1); it allows us to find the optimal

registration. The direct application of (1) rarely leads to acceptable results, mainly

due to the following problems:

i) Non-linear distortion makes impressions of the same finger significantly

different in terms of global structure; the use of local or block-wise

correlation techniques can help to deal with this problem.

ii) Skin condition and finger pressure cause image brightness, contrast, and

ridge thickness to vary significantly across different impressions. The use

of more sophisticated correlation measures may compensate for these

problems

iii) A direct application of (1) is computationally very expensive. Local

correlation and correlation in the Fourier domain can improve efficiency

Matching

Matching means finding most appropriate similar fingerprint to query fingerprint.

Fingerprints are matched by matching set of minutiae extracted. Minutiae sets

never match completely, so we compute match score of matching. If match score

satisfies accuracy needs, we call it successful matching. We used a new key based

one to many matching intended for large databases.

Existing Matching Techniques

1. One to many matching

Few algorithms are proposed by many researchers around the world which are

better than normal matching. But all of them are one to one verification or one to

one identification matching types. We developed a one to many matching

technique which uses key as the hashing tool. Initially, we do not match minutiae

sets instead we perform key matching with many keys of database. Those database

fingerprints, whose keys match with key of query fingerprint, are allowed for full

minutiae matching.

Algorithm : Key Based One to Many Matching Algorithm

M Input M from user;

j=1;

N Size of Database;

while j <= N do

if N - j >= 9 then

limit=M;

else

limit=N-j;

end

for i = j to j + limit - 1 do

Perform Matching(Gender, Class, i);

end

for i = 1 to M do

Gender Opposite of Estimated Gender;

Perform Matching(Gender, Class, i);

end

end

However we will be using edge detection technique which although involves one

to one matching but produces results with maximum efficiency.

2. Edge Detection

The purpose of edge detection in Automated Fingerprint Identification Systems

is to significantly reduce the amount of data found in a fingerprint image and leave

only the most important information. Edge detection works by finding points on an

image where the gray scale value changes greatly between pixels. The darker

pixels have low gray values while the lighter have high gray values. One method of

performing edge detection is based on convolution. Convolution is a mathematical

way of blending one function with another to produce a result expressing the

amount of overlap the functions have on one another. Two of the most common

edge detection filters are the Laplacian and the Canny operators. The Laplacian

operator is a method of edge detection based on taking the second derivatives of

the gray intensity (in the Cartesian coordinate system) while the Canny operator

uses the first derivative of the intensity. The Canny operator is the most commonly

used method for edge detection in AFIS since there are no significant advantages

in other systems[3]. The Laplacian function can be used to expresses the second

derivative of a function. There are some problems with using the Laplacian, since

it is especially prone to picking up features which are not actually edges in the

image. The Laplacian operator results in incorrect readings where the gray value

changes in small amounts consistently over part of the image. To reduce this noise

in an image, a Gaussian blur is often applied before the Laplacian operator. After

the second derivative is found, a threshold must be applied to determine actual

edges. More noise is produced with a lower threshold while a high threshold may

miss some edges. This is one of the most basic algorithms. Its implementation is as

follows:

ALGORITHM

Pic1 = Read image 1

Pic 2 = Read image 2

Edge_pic 1=edge(pic 1)

Edge_pic 2=edge(pic 2)

for a = 1 to 256

for b = 1 to 256

if(edge pic1(a,b)==1)

white_points = white_points+1;

else

black_points = black_points+1;

end

end

end

for i = 1 to 256

for j = 1 to 256

if(edge_pic1 (i,j)==1)&&(edge pic2(i,j)==1)

matched_data = matched_data+1;

end

end

end

total_data = white_points;

total_matched_percentage = (matched_data/total_data)*100;

if(total_matched_percentage >= 90)

Matched

else

Not Matched

End

Details

In the above algorithm a function edge is used for edge detection.This function

creates a binary image with black and white points. It looks for the sharp change in

intensity values to detect the edges. The algorithm used in project makes the use of

prewitt method or edge detection. After detection of edges,dots inside the edges are

made white in colour and the background gets black in colour.

This image is further enhanced and a binary image is produced as seen in

figure. After this we count the number of white points initial image to locate

fingerprint dots in sample image. Then both the image matrices are matched pixel

by pixel. If the number of dots matched exceeds 90% then the image is matched

else it is considered unmatched.

Original Scanned images

Binary Images after edge detection

Chapter 6

Software Design and Working model

LOGIN PAGE

This login Form is made For Security purpose. So only authenticated users can

access in to the Project.

There are two Type of persons who can enter in the project

1. Administrator

2. User

Login form allowing two user group

User can opt for either new registration or for attendance

New Registration Form

This form is filled by the students at the time of registration. It asks for details like

name, roll no, branch, semester, current attendance.

Student details being entered during new registration

Take Attendance

Attendance granted once finger print matches with student record

This Form is used to choose subjects and the month for which attendance is to be

filled up. When the student gives his/her attendance using the fingerprint scanner

module, the entry is matched with the fingerprints already present in the existing

database. If the fingerprint matches, their attendance is added.

View Attendance

Teachers can view the attendance of students in various subjects just by entering

their roll no thus various updation and attendance sheets can be framed

Software Testing

The proposed system has been tested for a class of 70 students. Four students were

20 minutes late than the lecture time. The attendance of these four students was not

updated (see rules for detail).

Out of other 66 students 63 students were properly identified and thus their

attendance record was updated.

1 unsuccessful identification occurred because student did not properly place his

finger on the sensor (see rules for detail).

1 student got identified as a different student due to presence of only 90%

matching criteria.

1 student failed identification due to unregistered or error-full details in the

database. The accuracy of the system is shown

No. of

students

No. of student

attendances

not counted

Successful

Identification

Unsuccessful

Identification

Accuracy

70 04 63 03 95.45%

Attendance Accuracy

Hence the software tested against various students was found to be functioning

properly.The only issue addressed while testing of software was:

Proper mechanism should be used to ensure that the thumb impression taken

everytime is exactly same.

Conclusion

This project mainly comprised of development of attendance management system

and fingerprint identification system. Attendance management is very helpful in

saving valuable time of students and teachers, paper and generating report at

required time. This project presented a framework using which attendance

management can be made automated and on-line.

Fingerprint Identification System used for student identification is faster in

implementation than any other fingerprint identification systems. For fingerprint

recognition, prevalent enhancement techniques clubbed with new techniques

helped in implementing this project in a better and efficient way.

As we have seen that further implementation of biometric technology like face

recognition grouped with various other image processing technologies like motion

sensing can make this software even better.

Future Work

Fingerprint identification system will be improved further using more indexing

techniques like ridge density tolerance etc.

Instead of using our database, we would be using database of students.

More functionalities like view attendance, subject-wise analysis can be added.

Student attendance system is designed using LAN in this project. A more thought

process can involve the implementation of this software over a wireless network.

The problem of using wireless LAN is that wireless devices are costly and

implementation is hard because the wireless devices work in small area. For large

campuses one can use mobile network which would be sufficiently suitable

because now-a-days 3G network provides much speed. It would meet necessary

throughput and data fetching speed requirements.

Biometric methodology can be implemented at higher levels where face

recognition and other biometric analysis can be done to provide more

authentication towards the presence of students. An integration of RFID system

with the Xbox Kinect technology and color camera sensors can come handy when

implemented with face recognition and motion sensing techniques. RFID systems

here can come handy in detecting the persons present in the class . Students can be

given a wrist band embedded with RFID tags which they should wear essentially

when they attend lectures. Here, RFID system can be an Active Reader Passive

Tag (ARPT) system whose reader will keep on interrogating whether the RFID

tags remain in the class during the lecturehours. RFID tags in this system can also

use a Battery Assisted Passive (BAP) tag which acts like a passive tag but has a

small battery to power the tag's return reporting signal. Thus with RFID system

multiple people entries present in the class can be recorded at the same time.What

if someone else is wearing two wrist bands at the same time?In that case, a student

will get the attendance although he will be absent during the class hours. To avoid

this scenario, Image analysis of thestudent can be implemented along with RFID

systems to ensure more Color camera sensors can capture the students’ image

whenever he/she enters the classroom and then image processing of the recorded

RGB content of image by color sensors can be done to produce a pattern to cross

check with patterns already present in the database(using pattern Recognition

techniques). Along with that, RFID systems will also sense the unique key

present in RFID tags, carried by the student and match that with students’

identity in the database. If the pattern matched with the RFID key is the same

matched during image analysis, then that person will get the attendance, else

the person will be marked absent.

RFID systems can also used be to track the students present in class at regular

intervals so as to ensure that they were present in the class all the time. In

case, Xbox Kinect detects any student motion , (like when they are going out

for some reason),it can again perform image analysis to match that student’s

record and with the help of RFID sensors it can check if the tag is present in the

class. If the tag gets detected in the class and kinect detected student’s motion

going out of the class, then student is marked absent until the kinect sensors

record his movement coming inside the class. Also in case the tag remains

undetected, the student is marked absent until his motion of entering inside

the class gets detected .Thus student motion detected with Xbox kinect can

also be helpful in maintaining a record if the student attended the whole

lecture or not. Machine learning techniques can be used to train the system to

detect the motion of people coming out and inside the classroom.

If in case, kinect sensors did not record any movement and RFID tags do not

respond to readers, then it that case student’s attendance in class is marked

absent. Thus RFID tags,color camera sensors and Xbox kinect make

interdependent system to provide factual data.

Thus future advancements in the field of biometrics and its implementation with

newer image processing technology in this project can produce highly

efficient,authentic and reliable results

REFERENCES

[1]. K.G.M.S.K. Jayawardana, T.N. Kadurugamuwa, R.G. Rage and S.

Radhakrishnan”, Timesheet: An Attendance Tracking System”, Pro-ceedings of

the Peradeniya University Research Sessions, Sri Lanka, Vol.13, Part II, 18th

December 2008.

[2]. Yohei KAWAGUCHI, Tetsuo SHOJI , Weijane LIN ,Koh KAKU-SHO,

Michihiko MINOH ,“Face Recognition-based Lecture Atten-dance System”,

Department of Intelligence Science and Technology, Graduate School of

Informatics, Kyoto University. Academic Center for Computing and Media

Studies, Kyoto University

[3]. American University of Beirut (2005, November 1). Fingerprint identification

– project 2.

Retrieved January 17, 2006, from http://webfea-

lb.fea.aub.edu.lb/dsaf/labs/projectv1.1.pdf

[4]. 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

http://webfea-lb.fea.aub.edu.lb/dsaf/labs/projectv1.1.pdf

http://webfea-lb.fea.aub.edu.lb/dsaf/labs/projectv1.1.pdf

Appendix Matlab Functions Used:

1. Start.m

function varargout = start(varargin)

% START M-file for start.fig

% START, by itself, creates a new START or raises the existing

% singleton*.

%

% H = START returns the handle to a new START or the handle to

% the existing singleton*.

%

% START('CALLBACK',hObject,eventData,handles,...) calls the local

% function named CALLBACK in START.M with the given input arguments.

%

% START('Property','Value',...) creates a new START or raises the

% existing singleton*. Starting from the left, property value pairs are

% applied to the GUI before start_OpeningFcn gets called. An

% unrecognized property name or invalid value makes property application

% stop. All inputs are passed to start_OpeningFcn via varargin.

%

% *See GUI Options on GUIDE's Tools menu. Choose "GUI allows only one

% instance to run (singleton)".

%

% See also: GUIDE, GUIDATA, GUIHANDLES

% Edit the above text to modify the response to help start

% Last Modified by GUIDE v2.5 31-Oct-2013 15:28:57

% Begin initialization code - DO NOT EDIT

gui_Singleton = 1;

gui_State = struct('gui_Name', mfilename, ...

'gui_Singleton', gui_Singleton, ...

'gui_OpeningFcn', @start_OpeningFcn, ...

'gui_OutputFcn', @start_OutputFcn, ...

'gui_LayoutFcn', [] , ...

'gui_Callback', []);

if nargin && ischar(varargin{1})

gui_State.gui_Callback = str2func(varargin{1});

end

if nargout

[varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});

else

gui_mainfcn(gui_State, varargin{:});

end

% End initialization code - DO NOT EDIT

% --- Executes just before start is made visible.

function start_OpeningFcn(hObject, eventdata, handles, varargin)

% This function has no output args, see OutputFcn.

% hObject handle to figure

% eventdata reserved - to be defined in a future version of MATLAB

% handles structure with handles and user data (see GUIDATA)

% varargin command line arguments to start (see VARARGIN)

% Choose default command line output for start

handles.output = hObject;

% Update handles structure

guidata(hObject, handles);

% UIWAIT makes start wait for user response (see UIRESUME)

% uiwait(handles.figure1);

% --- Outputs from this function are returned to the command line.

function varargout = start_OutputFcn(hObject, eventdata, handles)

% varargout cell array for returning output args (see VARARGOUT);




% Get default command line output from handles structure

varargout{1} = handles.output;

% --- Executes on button press in teacher.

function teacher_Callback(hObject, eventdata, handles)

% hObject handle to teacher (see GCBO)



login;

start('visible','off');

% --- Executes on button press in student.

function student_Callback(hObject, eventdata, handles)

% hObject handle to student (see GCBO)



clear all;

close all;

studlogin;

start('visible','off');

% --- Executes on button press in exit.

function exit_Callback(hObject, eventdata, handles)

% hObject handle to exit (see GCBO)



clear all;

close all;

2. login.m

function varargout = login(varargin)

% LOGIN M-file for login.fig

% LOGIN, by itself, creates a new LOGIN or raises the existing

% singleton*.

%

% H = LOGIN returns the handle to a new LOGIN or the handle to


%

% LOGIN('CALLBACK',hObject,eventData,handles,...) calls the local

% function named CALLBACK in LOGIN.M with the given input arguments.

%

% LOGIN('Property','Value',...) creates a new LOGIN or raises the


% applied to the GUI before login_OpeningFcn gets called. An


% stop. All inputs are passed to login_OpeningFcn via varargin.

%



%


% Edit the above text to modify the response to help login



gui_Singleton = 1;



'gui_OpeningFcn', @login_OpeningFcn, ...

'gui_OutputFcn', @login_OutputFcn, ...





end

if nargout


else


end


% --- Executes just before login is made visible.

function login_OpeningFcn(hObject, eventdata, handles, varargin)





% varargin command line arguments to login (see VARARGIN)

% Choose default command line output for login




% UIWAIT makes login wait for user response (see UIRESUME)



function varargout = login_OutputFcn(hObject, eventdata, handles)







% --- Executes on button press in pushbutton1.

function pushbutton1_Callback(hObject, eventdata, handles)

% hObject handle to pushbutton1 (see GCBO)



if(str2num(get(handles.edit1,'string'))==1234)

studreg;

login('visible','off');

else

msgbox('invalid password');

end

function edit1_Callback(hObject, eventdata, handles)

% hObject handle to edit1 (see GCBO)



% Hints: get(hObject,'String') returns contents of edit1 as text

% str2double(get(hObject,'String')) returns contents of edit1 as a double

% --- Executes during object creation, after setting all properties.

function edit1_CreateFcn(hObject, eventdata, handles)



% handles empty - handles not created until after all CreateFcns called

% Hint: edit controls usually have a white background on Windows.

% See ISPC and COMPUTER.

if ispc && isequal(get(hObject,'BackgroundColor'), get(0,'defaultUicontrolBackgroundColor'))

set(hObject,'BackgroundColor','white');

end






close all;

% --- Executes on button press in back.

function back_Callback(hObject, eventdata, handles)

% hObject handle to back (see GCBO)



clear all;

close all;

start;

login('visible','off');

3. studlogin.m

function varargout = studlogin(varargin)

% STUDLOGIN M-file for studlogin.fig

% STUDLOGIN, by itself, creates a new STUDLOGIN or raises the existing

% singleton*.

%

% H = STUDLOGIN returns the handle to a new STUDLOGIN or the handle to


%

% STUDLOGIN('CALLBACK',hObject,eventData,handles,...) calls the local

% function named CALLBACK in STUDLOGIN.M with the given input arguments.

%

% STUDLOGIN('Property','Value',...) creates a new STUDLOGIN or raises the


% applied to the GUI before studlogin_OpeningFcn gets called. An


% stop. All inputs are passed to studlogin_OpeningFcn via varargin.

%



%


% Edit the above text to modify the response to help studlogin



gui_Singleton = 1;



'gui_OpeningFcn', @studlogin_OpeningFcn, ...

'gui_OutputFcn', @studlogin_OutputFcn, ...





end

if nargout


else


end


% --- Executes just before studlogin is made visible.

function studlogin_OpeningFcn(hObject, eventdata, handles, varargin)





% varargin command line arguments to studlogin (see VARARGIN)

% Choose default command line output for studlogin




% UIWAIT makes studlogin wait for user response (see UIRESUME)



function varargout = studlogin_OutputFcn(hObject, eventdata, handles)






















end






set(handles.details,'string','');

set(handles.namemeta,'string','');

set(handles.name,'string','');

set(handles.rollmeta,'string','');

set(handles.roll,'string','');

set(handles.branchmeta,'string','');

set(handles.branch,'string','');

set(handles.currentmeta,'string','');

set(handles.current,'string','');

set(handles.record,'string','');

[filename, pathname] = uigetfile({'*.tif';'*.jpg';'*.gif';'*.*'}, 'Pick an Image File');

set(handles.edit1,'String',[pathname,filename]);

img=imread(get(handles.edit1,'string'));

axes(handles.axes1);

imshow(img,'Parent',handles.axes1);


load database.mat;

for i=1:length(array)

flag=matchfingerprint(array(i).image,get(handles.edit1,'string'));

if flag==1

set(handles.details,'string','Details');

set(handles.namemeta,'string','Name');

set(handles.rollmeta,'string','Roll No');

set(handles.branchmeta,'string','Branch');

set(handles.currentmeta,'string','Current Attendance');

set(handles.name,'string',array(i).name);

set(handles.roll,'string',num2str(array(i).roll));

set(handles.branch,'string',array(i).branch);

set(handles.current,'string',num2str(array(i).current_attendance));

break;

end

end

if flag~=1

set(handles.record,'string','Record Not Found');

end

clear;

function flag=matchfingerprint(path1,path2)

pic1 = imread(path1);


edge_det_pic1 = edge(pic1,'prewitt');%applying edge detection on first picture

%so that we obtain white and black points and edges of the objects present

%in the picture.

edge_det_pic2 = edge(pic2,'prewitt');%%applying edge detection on second picture

%initialization of different variables used

matched_data = 0;

white_points = 0;

black_points = 0;

x=0;

y=0;

l=0;

m=0;

%for loop used for detecting black and white points in the picture.

for a = 1:1:256

for b = 1:1:256

if(edge_det_pic1(a,b)==1)


else


end

end

end

%for loop comparing the white (edge points) in the two pictures

for i = 1:1:256

for j = 1:1:256

if(edge_det_pic1(i,j)==1)&&(edge_det_pic2(i,j)==1)


else

;

end

end

end

%calculating percentage matching.



%outputting the result of the system.

if(total_matched_percentage >= 90) %can add flexability at this point by reducing the

amount of matching.

flag=1;

else

flag=0;

end






clear all;

close all;

start;

studlogin('visible','off');

% --- Executes on button press in exit.

function exit_Callback(hObject, eventdata, handles)

% hObject handle to exit (see GCBO)



clear all;

close all;

4. studreg.m

function varargout = studreg(varargin)

% STUDREG M-file for studreg.fig

% STUDREG, by itself, creates a new STUDREG or raises the existing

% singleton*.

%

% H = STUDREG returns the handle to a new STUDREG or the handle to


%

% STUDREG('CALLBACK',hObject,eventData,handles,...) calls the local

% function named CALLBACK in STUDREG.M with the given input arguments.

%

% STUDREG('Property','Value',...) creates a new STUDREG or raises the


% applied to the GUI before studreg_OpeningFcn gets called. An


% stop. All inputs are passed to studreg_OpeningFcn via varargin.

%



%


% Edit the above text to modify the response to help studreg



gui_Singleton = 1;



'gui_OpeningFcn', @studreg_OpeningFcn, ...

'gui_OutputFcn', @studreg_OutputFcn, ...





end

if nargout


else


end


% --- Executes just before studreg is made visible.

function studreg_OpeningFcn(hObject, eventdata, handles, varargin)





% varargin command line arguments to studreg (see VARARGIN)

% Choose default command line output for studreg




% UIWAIT makes studreg wait for user response (see UIRESUME)



function varargout = studreg_OutputFcn(hObject, eventdata, handles)












clear all;

close all;

studdetails;

studreg('visible','off');






clear all;

close all;

studattendance;







close all;

% --- Executes on button press in viewdetails.

function viewdetails_Callback(hObject, eventdata, handles)

% hObject handle to viewdetails (see GCBO)



clear all;

close all;

viewdetails;







clear all;

close all;

start;


5. studdetails.m

function varargout = studdetails(varargin)

% STUDDETAILS M-file for studdetails.fig

% STUDDETAILS, by itself, creates a new STUDDETAILS or raises the existing

% singleton*.

%

% H = STUDDETAILS returns the handle to a new STUDDETAILS or the handle to


%

% STUDDETAILS('CALLBACK',hObject,eventData,handles,...) calls the local

% function named CALLBACK in STUDDETAILS.M with the given input arguments.

%

% STUDDETAILS('Property','Value',...) creates a new STUDDETAILS or raises the


% applied to the GUI before studdetails_OpeningFcn gets called. An


% stop. All inputs are passed to studdetails_OpeningFcn via varargin.

%



%


% Edit the above text to modify the response to help studdetails



gui_Singleton = 1;



'gui_OpeningFcn', @studdetails_OpeningFcn, ...

'gui_OutputFcn', @studdetails_OutputFcn, ...





end

if nargout


else


end


% --- Executes just before studdetails is made visible.

function studdetails_OpeningFcn(hObject, eventdata, handles, varargin)





% varargin command line arguments to studdetails (see VARARGIN)

% Choose default command line output for studdetails




% UIWAIT makes studdetails wait for user response (see UIRESUME)



function varargout = studdetails_OutputFcn(hObject, eventdata, handles)

































end
















end
















end
















end
















end






load database.mat%

details=struct ('serial',0,'name','','roll',0,'image','','branch','','current_attendance',0);

details.name=get(handles.edit6,'string');

details.roll=str2num(get(handles.edit3,'string'));

details.image=get(handles.edit1,'string');

details.branch=get(handles.edit7,'string');

details.serial=length(array)+1;%

%array=details;%

array=[array details];%

save database.mat array

clear all;

close all;

studreg;

studdetails('visible','off');

clear
















end
















end






close all;

6. studattendance.m

function varargout = studattendance(varargin)

% STUDATTENDANCE M-file for studattendance.fig

% STUDATTENDANCE, by itself, creates a new STUDATTENDANCE or raises the existing

% singleton*.

%

% H = STUDATTENDANCE returns the handle to a new STUDATTENDANCE or the handle to


%

% STUDATTENDANCE('CALLBACK',hObject,eventData,handles,...) calls the local

% function named CALLBACK in STUDATTENDANCE.M with the given input arguments.

%

% STUDATTENDANCE('Property','Value',...) creates a new STUDATTENDANCE or raises the


% applied to the GUI before studattendance_OpeningFcn gets called. An


% stop. All inputs are passed to studattendance_OpeningFcn via varargin.

%



%


% Edit the above text to modify the response to help studattendance



gui_Singleton = 1;



'gui_OpeningFcn', @studattendance_OpeningFcn, ...

'gui_OutputFcn', @studattendance_OutputFcn, ...





end

if nargout


else


end


% --- Executes just before studattendance is made visible.

function studattendance_OpeningFcn(hObject, eventdata, handles, varargin)





% varargin command line arguments to studattendance (see VARARGIN)

% Choose default command line output for studattendance




% UIWAIT makes studattendance wait for user response (see UIRESUME)



function varargout = studattendance_OutputFcn(hObject, eventdata, handles)












set(handles.serialmeta,'string','');

set(handles.serial,'string','');

set(handles.text3,'string','');













load database.mat;


flag=matchfingerprint(array(i).image,get(handles.edit1,'string'));

if flag==1

set(handles.serialmeta,'string','Serial No.');

set(handles.text3,'string','Name');

set(handles.text4,'string','Roll No');

set(handles.text5,'string','Branch');

set(handles.text10,'string','Current Attendance');

set(handles.serial,'string',array(i).serial);

set(handles.text6,'string',array(i).name);

set(handles.text7,'string',num2str(array(i).roll));

set(handles.text8,'string',array(i).branch);

set(handles.text11,'string',num2str(array(i).current_attendance));

break;

end

end

if flag~=1

set(handles.text9,'string','Record Not Found');

end

clear;

function flag=matchfingerprint(path1,path2)



edge_det_pic1 = edge(pic1,'prewitt');%applying edge detection on first picture

%so that we obtain white and black points and edges of the objects present

%in the picture.

edge_det_pic2 = edge(pic2,'prewitt');%%applying edge detection on second picture

%initialization of different variables used

matched_data = 0;

white_points = 0;

black_points = 0;

x=0;

y=0;

l=0;

m=0;

%for loop used for detecting black and white points in the picture.

for a = 1:1:256

for b = 1:1:256

if(edge_det_pic1(a,b)==1)


else


end

end

end

%for loop comparing the white (edge points) in the two pictures

for i = 1:1:256

for j = 1:1:256

if(edge_det_pic1(i,j)==1)&&(edge_det_pic2(i,j)==1)


else

;

end

end

end

%calculating percentage matching.



%outputting the result of the system.

if(total_matched_percentage >= 90) %can add flexability at this point by reducing the

amount of matching.

flag=1;

else

flag=0;

end
















end






studreg;

studattendance('visible','off');

% --- Executes on button press in grant.

function grant_Callback(hObject, eventdata, handles)

% hObject handle to grant (see GCBO)



load database.mat

serial=str2num(get(handles.serial,'string'));

array(serial).current_attendance=array(serial).current_attendance+1;

set(handles.text11,'string',num2str(array(serial).current_attendance));

save database.mat array






close all;

7. viewdetails.m

function varargout = viewdetails(varargin)

% VIEWDETAILS M-file for viewdetails.fig

% VIEWDETAILS, by itself, creates a new VIEWDETAILS or raises the existing

% singleton*.

%

% H = VIEWDETAILS returns the handle to a new VIEWDETAILS or the handle to


%

% VIEWDETAILS('CALLBACK',hObject,eventData,handles,...) calls the local

% function named CALLBACK in VIEWDETAILS.M with the given input arguments.

%

% VIEWDETAILS('Property','Value',...) creates a new VIEWDETAILS or raises the


% applied to the GUI before viewdetails_OpeningFcn gets called. An


% stop. All inputs are passed to viewdetails_OpeningFcn via varargin.

%



%


% Edit the above text to modify the response to help viewdetails



gui_Singleton = 1;



'gui_OpeningFcn', @viewdetails_OpeningFcn, ...

'gui_OutputFcn', @viewdetails_OutputFcn, ...





end

if nargout


else


end


% --- Executes just before viewdetails is made visible.

function viewdetails_OpeningFcn(hObject, eventdata, handles, varargin)





% varargin command line arguments to viewdetails (see VARARGIN)

% Choose default command line output for viewdetails




% UIWAIT makes viewdetails wait for user response (see UIRESUME)



function varargout = viewdetails_OutputFcn(hObject, eventdata, handles)







function editroll_Callback(hObject, eventdata, handles)

% hObject handle to editroll (see GCBO)



% Hints: get(hObject,'String') returns contents of editroll as text

% str2double(get(hObject,'String')) returns contents of editroll as a double


function editroll_CreateFcn(hObject, eventdata, handles)

% hObject handle to editroll (see GCBO)







end

% --- Executes on button press in enter.

function enter_Callback(hObject, eventdata, handles)

% hObject handle to enter (see GCBO)



load database.mat

set(handles.namemeta,'string','');

set(handles.rollmeta,'string','');

set(handles.branchmeta,'string','');

set(handles.currentmeta,'string','');

set(handles.name,'string','');

set(handles.roll,'string','');

set(handles.branch,'string','');

set(handles.current,'string','');

set(handles.record,'string','');

flag=0;


if array(i).roll==str2num(get(handles.editroll,'string'))

flag=1;

set(handles.namemeta,'string','Name');

set(handles.rollmeta,'string','Roll No');

set(handles.branchmeta,'string','Branch');

set(handles.currentmeta,'string','Attendance');

set(handles.name,'string',array(i).name);

set(handles.roll,'string',num2str(array(i).roll));

set(handles.branch,'string',array(i).branch);

set(handles.current,'string',array(i).current_attendance);

end

end

if flag==0

set(handles.record,'string','Record Not Found');

end






clear all;

close all;

studreg;

viewdetails('visible','off');

Student Attendance By Image Analysis

Documents

Transcript of Student Attendance By Image Analysis