project ii automated attendance management system using

Project II

"Automated Attendance ManagementSystem Using Face Recognition"

Submitted in partial fulfillment of the requirements for the degree of

Bachelor of Engineering

by

(Chowdhary Obaid Ahmed Niyaz Aasma) (13CO25)

(Punjani Ali Akbar Sajid Zaida ) (13CO49)

(Choudhary Yasir Ahmed Anis Nasreen ) (13CO24)

Supervisor

(Prof.Khan Mubashir)Co-Supervisor

(Prof.Gopale Apeksha)

Department of Computer Engineering,School of Engineering and Technology

Anjuman-I-Islam’s Kalsekar Technical CampusPlot No. 2 3, Sector -16, Near Thana Naka, Khanda Gaon,

New Panvel, Navi Mumbai. 410206

Academic Year : 2016-2017

CERTIFICATE

Department of Computer Engineering,School of Engineering and Technology,

Anjuman-I-Islam’s Kalsekar Technical CampusKhanda Gaon,New Panvel, Navi Mumbai. 410206

This is to certify that the project entitled Automated Attendance Management System Us-ing Face Recognition is a bonafide work of Chowdhary Obaid (13CO25), Ali Akbar Punjani(13CO49), Choudhary Yasir (13CO24) submitted to the University of Mumbai in partial fulfill-ment of the requirement for the award of the degree of Bachelor of Engineering in Departmentof Computer Engineering.

Prof.Mubashir Khan Prof. Javed Sheikh

Supervisor Project Co-dinator

Prof. Tabrez Khan Dr. Abdul Razak Honnutagi

Head of Department Director

Project Approval for Bachelor of Engineering

This project entitled " Automated Attendance Management Sytem Using Face Recognition "by Chowdhary Obaid Ahmed,Ali Akbar Punjani,Choudhary Yasir Ahmed is approved for thedegree of Bachelor of Engineering in Department of Computer Engineering.

Examiners

1. ..............................2. ..............................

Supervisors1. ..............................2. ..............................

Chairman.............................

Declaration

We declare that this written submission represents our ideas in our own words and where oth-ers ideas or words have been included, We have adequately cited and referenced the originalsources. We also declare that We have adhered to all principles of academic honesty and in-tegrity and have not misrepresented or fabricated or falsified any idea/data/fact/source in oursubmission. We understand that any violation of the above will be cause for disciplinary actionby the Institute and can also evoke penal action from the sources which have thus not beenproperly cited or from whom proper permission has not been taken when needed.

Chowdhary Obaid Ahmed13CO25

Ali Akbar Punjani13CO49

Choudhary Yasir Ahmed13CO24

Abstract

Tittle : Automated Attendance Management System Using Face RecognitionThe main goal and objective of this automated attendance system of face detection and recog-nition is to present face recognition in real time environment for educational institutes or anorganization to see and mark the attendance of their students and employees on a daily basis tokeep track of their presence. The system will mark and record the attendance in any environ-ment. This system is purely automated and user can capture video and accordingly attendancewill be marked, improving the accuracy to great extent and finally the attendance report will begenerated.

Chowdhary Obaid Ahmed13CO25B.E. (Computer Engineering)University of Mumbai.

Ali Akbar Punjani13CO49B.E. (Computer Engineering)University of Mumbai.

Choudhary Yasir Ahmed13CO24B.E. (Computer Engineering)University of Mumbai.

iv

Contents

Project Approval for Bachelor of Engineering . . . . . . . . . . . . . . . . . . . . . iiDeclaration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iiiTable of Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . viiList of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . viiiKeywords And Glossary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ix

1 Project Overview 11.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1

1.1.1 Background Introduction . . . . . . . . . . . . . . . . . . . . . . . . . 21.1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2

1.2 Problem Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31.3 Current Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31.4 The Problems with Current System . . . . . . . . . . . . . . . . . . . . . . . . 3

1.4.1 Advantages Over Current System . . . . . . . . . . . . . . . . . . . . 41.5 Goals and Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41.6 Scope and Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51.7 Report Organization: briefly explains all the chapters and their focus . . . . . . 5

2 Review Of Literature 62.1 OTP and Facial Recognition based Attendance System . . . . . . . . . . . . . 6

2.1.1 Description . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62.1.2 Pros . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62.1.3 Cons . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 72.1.4 How we overcome Those problem in Project . . . . . . . . . . . . . . 7

2.2 Student Attendance Tracker System in Android. . . . . . . . . . . . . . . . . . 72.2.1 Description . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 72.2.2 Pros . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 82.2.3 Cons . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 82.2.4 How we overcome Those problem in Project . . . . . . . . . . . . . . 8

2.3 Technological Review . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 92.3.1 HD Webcam C270 . . . . . . . . . . . . . . . . . . . . . . . . . . . 92.3.2 SQLserver . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

v

3 Requirement Analysis 113.1 Platform Requirement : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11

3.1.1 Supportive Operating Systems : . . . . . . . . . . . . . . . . . . . . . 113.2 Software Requirement : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 113.3 Hardware Requirement : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 123.4 Database Requirement : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

4 System Design and Architecture 144.1 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 144.2 Usecase Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 154.3 Class Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 164.4 Data Flow Diagrams . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 174.5 Component Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19

5 Methodology 205.1 Modular Description . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20

5.1.1 Webcam . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 205.1.2 Face Detection using Haar features . . . . . . . . . . . . . . . . . . . 215.1.3 Prinicipal component analysis(PCA): . . . . . . . . . . . . . . . . . . 225.1.4 Linear Discriminate Analysis (LDA): . . . . . . . . . . . . . . . . . . 235.1.5 Linear Binary Pattern Histogram (LBPH): . . . . . . . . . . . . . . . . 235.1.6 SQL server: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24

5.2 Sequence Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 255.3 Activity Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 265.4 Flow-Chart . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27

6 Implementation Details 286.1 Assumptions And Dependencies . . . . . . . . . . . . . . . . . . . . . . . . . 28

6.1.1 Assumptions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 286.1.2 Dependencies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28

6.2 Implementation Methodologies . . . . . . . . . . . . . . . . . . . . . . . . . . 296.2.1 Step I implementation: . . . . . . . . . . . . . . . . . . . . . . . . . . 296.2.2 Step II implementation: . . . . . . . . . . . . . . . . . . . . . . . . . 316.2.3 Step III implementation: . . . . . . . . . . . . . . . . . . . . . . . . . 326.2.4 Step IV implementation: . . . . . . . . . . . . . . . . . . . . . . . . . 33

6.3 Competitive Advantages of the project: . . . . . . . . . . . . . . . . . . . . . 34

7 Results and Analysis 357.1 Analysis and Result Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . 35

8 Conclusion and Future Scope 368.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 368.2 Limitations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36

vi

8.3 Future Enhancement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37

References 38

9 Appendix A 399.1 What is Local Binary Pattern? . . . . . . . . . . . . . . . . . . . . . . . . . . 399.2 The LBP feature vector: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 399.3 Correlation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 409.4 Average Paper Sheet waste generated in a year by a single employee . . . . . 40

Acknowledgment 41

vii

List of Figures

2.1 HD Webcam C270 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9

4.1 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 144.2 Usecase . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 154.3 Class Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 164.4 DFD Level 0 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 174.5 DFD Level 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 174.6 DFD Level 2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 184.7 Component Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19

5.1 webcam . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 205.2 Sequence Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 255.3 Activity Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 265.4 Flow Chart . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27

6.1 Starting of the GUI and WebCam . . . . . . . . . . . . . . . . . . . . . . . . 296.2 Training of the faces in database . . . . . . . . . . . . . . . . . . . . . . . . . 306.3 Trained data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 306.4 Face is detected . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 316.5 Face is recognized . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 326.6 Unknown face as the data is not trained . . . . . . . . . . . . . . . . . . . . . 336.7 Attendace Record of the present and absent students with date and time . . . . 33

viii

Keywords And Glossary

Keywords :Automated, Face Detection, Face Recognition, Haar features, Attendance,PCA,LDA,LBPH.

Glossary :

Face Detection:Face Detection: Face detection is a computer technology being used in a vari-ety of applications that identifies human faces in digital images.

Face Recognition: It is a type of biometric software application that can identify a specificindividual in a digital image by analysing and comparing patterns.

OpenCV(Open Source Computer Vision:) is a library of programming functions mainlyaimed at real-time computer vision.

ROI: Region of Interest.

Correlation: Correlation refers to any of a broad class of statistical relationships involvingdependence.

ix

Chapter 1

Project Overview

1.1 Introduction

In many Institution and Organization the attendance is a very important factor to maintain therecord of lectures, salary and work hours etc. Most of the institutes and organizations followthe manual method using old paper and file method and some of them have shifted to biometrictechnique. The current method that colleges use is that the professor passes a sheet or make rollcalls and mark the attendance of the students and this sheet further goes to the admin depart-ment with updates the final excel sheet. This process is quite hectic and time consuming. Also,for professors or employees at institutes or organizations the biometric system serves one at atime. So, why not shift to an automated attendance system which works on face recognitiontechnique? Be it a class room or entry gates it will mark the attendance of the students, profes-sors, employees, etc. This system uses Viola and Jones algorithm for detecting and recognizingthe faces. The main elements of this technology are as follows : a) Face Detection b) FaceRecognition.

(a) Face Detection: Face detection is a computer technology being used in a variety of ap-plications that identifies human faces in digital images. Face detection also refers to the psy-chological process by which humans locate and attend to faces in a visual scene. Face detectioncan be regarded as a specific case of object-class detection. In object-class detection, the task isto find the locations and sizes of all objects in an image that belong to a given class. Examplesinclude upper torsos, pedestrians, and cars. Face-detection algorithms focus on the detectionof frontal human faces. It is analogous to image detection in which the image of a person ismatched bit by bit. Image matches with the image stores in database. Any facial feature changesin the database will invalidate the matching process. A reliable face-detection approach basedon the genetic algorithm and the eigen-face technique: Firstly, the possible human eye regionsare detected by testing all the valley regions in the gray-level image. Then the genetic algorithmis used to generate all the possible face regions which include the eyebrows, the iris, the nostriland the mouth corners. Each possible face candidates is normalized to reduce lightning effectcaused due to uneven illumination and the shirring effect due to head movement. The fitnessvalue of each candidate is measured based on its projection on the eigen-faces. After a numberof iterations, all the face candidates with a high fitness value are selected for further verification.At this stage, the face symmetry is measured and the existence of the different facial features is

1

1.1. Introduction

verified for each face candidate

b) Face Recognition: A facial recognition system is a computer application capable of identify-ing or verifying a person from a digital image or a video frame from a video source. One of theways to do this is by comparing selected facial features from the image and a facial database. Itis typically used in security systems and can be compared to other biometrics such as fingerprintor eye iris recognition systems. Some facial recognition algorithms identify facial features byextracting landmarks, or features, from an image of the subjectâTMs face. For example, an al-gorithm may analyze the relative position, size, and/or shape of the eyes, nose, cheekbones, andjaw. These features are then used to search for other images with matching features. Other algo-rithms normalize a gallery of face images and then compress the face data, only saving the datain the image that is useful for face recognition. A probe image is then compared with the facedata. One of the earliest successful systems is based on template matching techniques applied toa set of salient facial features, providing a sort of compressed face representation. Recognitionalgorithms can be divided into two main approaches, geometric, which looks at distinguishingfeatures, or photometric, which is a statistical approach that distills an image into values andcompares the values with templates to eliminate variances. Popular recognition algorithms in-clude Principal Component Analysis using eigenfaces, Linear Discriminate Analysis, ElasticBunch Graph Matching using the Fisherface algorithm, the Hidden Markov model, the Multi-linear Subspace Learning using tensor representation, and the neuronal motivated dynamic linkmatching.

1.1.1 Background Introduction

The current method that colleges use is that the professor passes a sheet or make roll calls andmark the attendance of the students and this sheet further goes to the admin department with up-dates the final excel sheet. This process is quite hectic and time consuming. Also, for professorsor employees at institutes or organizations the biometric system serves one at a time. So, whynot shift to an automated attendance system which works on face recognition technique? Be ita class room or entry gates it will mark the attendance of the students, professors, employees,etc. This system uses Viola and Jones algorithm for detecting and recognizing the faces

1.1.2 Motivation

The main motivation for us to go for this project was the slow and inefficient traditional manualattendance system. This made us to think why not make it automated fast and mush efficient.Also such face detection techniques are in use by department like crime investigation where theyuse cctv footages and detect the faces from the crime scene and compare those with criminaldatabase to recognize them.

Also facebook, it uses an algorithm called deep face whose accuracy to recognize is 97.25%which is as close as what humans have that is 97.53%.

2

Chapter 1. Project Overview

1.2 Problem Definition

The goal of this project is to design an Automated attendance Management System which hasthe following functions:

1) Learning Phase- Detection identification of seat locations in an unknown environment.

2) Monitoring Phase- Detection of entering leaving events for each occupant into from respec-tive seat.

3) Real-time system- Implementation of real-time Attendance marking system and report gen-eration.

Now a days attendance marking involves manual attendance on paper sheet by professors andteachers. but it is very time consuming process and chances of proxy is also one problem thatarises in such type of attendance marking. So there is a need to develop an attendance systemwhich is automated and which reduce the paper work and also eliminate the chances of proxy.

1.3 Current Systems

At present attendance marking involves manual attendance on paper sheet by professors andteachers. but it is very time consuming process and chances of proxy is also one problem thatarises in such type of attendance marking. also there are attendance marking system such asRFID , Biometrics etc. but these systems are currently not so much popular in schools andclassrooms for students as they have thier own advantages and disadvantages.

1.4 The Problems with Current System

The problem with this approach in which manually taking and maintains the attendance recordsis that it is very inconvenient task. Traditionally, studentâTMs attendances are taken manually byusing attendance sheet given by the faculty members in class, which is a time consuming event.Moreover, it is very difficult to verify one by one student in a large classroom environment withdistributed branches whether the authenticated students are actually responding or not. Theability to compute the attendance percentage becomes a major task as manual computation pro-duces errors, and also wastes a lot of time. This method could easily allow for impersonationand the attendance sheet could be stolen or lost.

3

1.5. Goals and Objectives

1.4.1 Advantages Over Current System

The previous approach in which manually takes and maintains the attendance records was veryinconvenient task. Traditionally, studentâTMs attendances are taken manually by using atten-dance sheet given by the faculty members in class, which is a time consuming event. Moreover,it is very difficult to verify one by one student in a large classroom environment with distributedbranches whether the authenticated students are actually responding or not. The ability to com-pute the attendance percentage becomes a major task as manual computation produces errors,and also wastes a lot of time. This method could easily allow for impersonation and the atten-dance sheet could be stolen or lost.

An automatic attendance management system using biometrics would provide the needed solu-tion. The results showed improved performance over manual attendance management system.Biometric-based techniques have emerged as the most promising option for recognizing individ-uals in recent years since, instead of authenticating people and granting them access to physicaland virtual domains based on passwords, PINs, smart cards, plastic cards, tokens, keys and soforth, these methods examine an individualâTMs physiological and/or behavioral characteristicsin order to determine and/or ascertain his identity.

Biometric based technologies include identification based on physiological characteristics (suchas face, fingerprints, finger geometry, hand geometry, hand veins, palm, iris, retina, ear andvoice) and behavioral traits (such as gait, signature and keystroke dynamics). Face recognitionappears to offer several advantages over other biometric methods, a few of which are outlinedhere: Almost all these technologies require some voluntary action by the user, i.e., the userneeds to place his hand on a hand-rest for fingerprinting or hand geometry detection and has tostand in a fixed position in front of a camera for iris or retina identification.

However, face recognition can be done passively without any explicit action or participationon the part of the user since face images can be acquired from a distance by a camera. Thisis particularly beneficial for security and surveillance purposes. Furthermore, data acquisitionin general is fraught with problems for other biometrics: techniques that rely on hands andfingers can be rendered useless if the epidermis tissue is damaged in some way (i.e., bruised orcracked).

1.5 Goals and Objectives

The objective of this system is to present an automated system for human face recognition foran organization or institute to mark the attendance of their students or employees. This paperintroduces face detection method using the Voila and Jones algorithm and recognition usingLine Edge Map Technique(LEM).Scope of the system is that it can be easily implemented atany institute or organization. On the other hand, our system can be used in a completely newdimension of face recognition application, mobile based face recognition, which can be anaid for common people to know about any person being photographed by cell phone cameraincluding proper authorization for accessing a centralized database.

4

Chapter 1. Project Overview

1.6 Scope and Applications

This project performs well in the area of face detection and recognition but there is a room toimprove the algorithm performance in case of large number of students and also in case of facescaptured in a dark environment, so proposed system can be extended in the future to cover thisaspect. The efficiency of the algorithm also can be increased further so there is also a room forfuture work in this area. The proposed system can be enhanced further in terms of achievingmore efficiency by ease of analysis of patterns in the data.

1.7 Report Organization: briefly explains all the chaptersand their focus

The remaining part of the project is organized as follows. Chapter 1 presents Project overviewrelated work.

Chapter 2 presents a Literature review related work.

Chapter 3 introduces the Software and Hardware Requirement of the project.

Chapter 4 proposes the Project Design of the Project . It represent the architectural design, frontend design and database design of the project.

Chapter 5 presents Methodology and modulat Description of our project.

Chapter 6 presents Implementaion details which consists of Assumption and Dependies of ourproject.

Chapter 7 presents the result and test cases.

Chapter 8 provides some concluding remarks and directions of our future work.

5

Chapter 2

Review Of Literature

2.1 OTP and Facial Recognition based Attendance System

2.1.1 Description

ABSTRACT: Today in most colleges and universities attendance is done manually or by bio-metric means which takes a considerable amount of time or require a large number of resources.The pen and paper based attendance system requires a large amount of human effort and henceresulting in manual errors. Whereas the biometric system requires a large amount of capitalcost and the considerable amount of operational cost. We propose a fully software based ap-proach using android application which uses OTP and facial recognition base authenticationmethods to reduce the nuisance of pen and paper based attendance system, proxies, and thehigh maintenance cost of the biometrics.

2.1.2 Pros

• The system is portable and can be easily installed and used on any mobile phone runningAndroid OS.

• The authentication model proposed in the system eliminates the nuisance of proxies com-pletely by following a pure software approach, which reduces the cost involved withsystem considerably.

• The complete process of attendance registration takes place in just a few seconds, whichsaves precious lecture time.

6

Chapter 2. Review Of Literature

2.1.3 Cons

• Too much authentication and verification steps are involved, herby only technical peoplecan easily use the software

• Complications such as password authentication address verification, One Time Password

• (OTP) verification is involved thereby increasing the complexity in the software

2.1.4 How we overcome Those problem in Project

• Using just the appropriate face detection and recognition algorithms, all the authenticationsteps can be eliminated.

2.2 Student Attendance Tracker System in Android.

2.2.1 Description

Student Information Tracking System is an Android application to manage student at-tendance on mobile. In many colleges teachers use to take attendance manually. Mainobjective of this project is to add mobility and automation in the existing attendance pro-cess. This system helps teachers to take attendance through mobile and also keep in touchwith student in some aspect.

This System allow teachers to take attendance, edit attendance, view student’s bunks, sendimportant documents in pdf format such as exam time table, question bank etc. and alsohelps teachers to inform students about the events that college is going to organize.Thissystem also helps students in specifying bunks, deleting bunks, viewing their bunks. Thissystem gives a prior intimation to student as soon as his attendance goes below the spec-ified attendance deadline in the form of an alert. This system helps students to keep intouch with the events that college is going to organize.

7

2.2. Student Attendance Tracker System in Android.

2.2.2 Pros

Installing this software into the android smart phone Calculating the attendance, it willtoo time consuming for the staff.

• Improve the accuracy.

• Less paper work

• No chance of the mistake while calculating the attendance manually.

• Staff work will be less.

2.2.3 Cons

• Android Phone is the major requirement for this software to work

• All students may or may not be able to afford an Android phone

• The system consists of how effectively the student can bunk the lectures,which is demor-alising the student to attend all the lectures

2.2.4 How we overcome Those problem in Project

• The platform (OS) on which the system is working should be changed so as to maintainthe costing of using the system, on user end.

• The system should motivate students to attend all the lectures rather than including mod-ules such as bunk manager, which indirectly demotivates them to attend all the lectures.

8

Chapter 2. Review Of Literature

2.3 Technological Review

2.3.1 HD Webcam C270

Figure 2.1: HD Webcam C270

What you need:Windows VistaWindows 7 (32-bit or 64-bit)Windows 8Basic requirements: 1 GHz512 MB RAM or more200 MB hard drive spaceInternet connectionUSB 1.1 port (2.0 recommended)

For HD 720p video recording:2.4 GHz Intel Core2 Duo2 GB RAM200 MB hard drive spaceUSB 2.0 port1 Mbps upload speed or higher1280 x 720 screen resolution

9

2.3. Technological Review

2.3.2 SQLserver

Microsoft SQL Server is a relational database management system developed by Mi-crosoft. As a database server, it is a software product with the primary function of storingand retrieving data as requested by other software applicationsâ”which may run either onthe same computer or on another computer across a network (including the Internet).

Microsoft markets at least a dozen different editions of Microsoft SQL Server, aimed atdifferent audiences and for workloads ranging from small single-machine applications tolarge Internet-facing applications with many concurrent users.The history of Microsoft SQL Server begins with the first Microsoft SQL Server productâ“ SQL Server 1.0, a 16-bit server for the OS/2 operating system in 1989 - and extends tothe current day.

As of December 2016 the following versions are supported by Microsoft:

• SQL Server 2008

• SQL Server 2008 R2

• SQL Server 2012

• SQL Server 2014

• SQL Server 2016

The current version is Microsoft SQL Server 2016, released June 1, 2016. The RTMversion is 13.0.1601.5. SQL Server 2016 is supported on x64 processors only.

.

.

.

10

Chapter 3

Requirement Analysis

To be used efficiently, all computer software needs certain hardware components or other soft-ware resources to be present on a computer. These prerequisites are known as (computer)system requirements and are often used as a guideline as opposed to an absolute rule. Mostsoftware defines two sets of system requirements: minimum and recommended.

3.1 Platform Requirement :

3.1.1 Supportive Operating Systems :

The supported Operating Systems for client include: Windows 2010, windows 2008, windows2007.We as developer of our project will follow the given responsibilities:1. Completing the tasks within the deadlines.2. Informing our internal and external guides regularly about our performance.3. Maintaining the logbook.4. Implementing of project on well planned manner.5. Dividing the tasks among project equally

3.2 Software Requirement :

The Software Requirements in this project include:a. Microsoft visual studiob. Opencv frameworkc. Dot NET framework

11

3.3. Hardware Requirement :

Software requirements deal with defining software resource requirements and prerequisites thatneed to be installed on a computer to provide optimal functioning of an application. These re-quirements or prerequisites are generally not included in the software installation package andneed to be installed separately before the software is installed.

OpenCV (Open Source Computer Vision Library) is an open source computer vision and ma-chine learning software library. OpenCV was built to provide a common infrastructure forcomputer vision applications and to accelerate the use of machine perception in the commer-cial products. Being a BSD-licensed product, OpenCV makes it easy for businesses to utilizeand modify the code. The library has more than 2500 optimized algorithms, which includesa comprehensive set of both classic and state-of-the-art computer vision and machine learningalgorithms.

These algorithms can be used to detect and recognize faces, identify objects, classify humanactions in videos, track camera movements, track moving objects, extract 3D models of objects,produce 3D point clouds from stereo cameras, stitch images together to produce a high reso-lution image of an entire scene, find similar images from an image database, removered eyesfrom images taken using flash, follow eye movements, recognize scenery and establish markersto overlay it with augmented reality, etc.

OpenCV has more than 47 thousand people of user community and estimated number of down-loads exceeding 7 million. The library is used extensively in companies, research groups andby governmental bodies. As an asynchronous event driven framework.

3.3 Hardware Requirement :

The most common set of requirements defined by any operating system or software applica-tion is the physical computer resources, also known as hardware, A hardware requirements listis often accompanied by a hardware compatibility list (HCL), especially in case of operatingsystems. An HCL lists tested, compatible, and sometimes incompatible hardware devices for aparticular operating system or application.

Components Minimum Recommended

ProcessorIntel Core i3-2100 2ndgeneration

Intel Core i7 5th gener-ation

RAM 4GB 8GB

Camera HD 720p WebcamFull HD 1080p Web-cam

Disk 128Gb 512Gb

12

Chapter 3. Requirement Analysis

3.4 Database Requirement :

SQLserverMicrosoft SQL Server is a relational database management system developed by Microsoft. Asa database server, it is a software product with the primary function of storing and retrievingdata as requested by other software applicationsâ”which may run either on the same computeror on another computer across a network (including the Internet).

Microsoft markets at least a dozen different editions of Microsoft SQL Server, aimed at differentaudiences and for workloads ranging from small single-machine applications to large Internet-facing applications with many concurrent users.The history of Microsoft SQL Server begins with the first Microsoft SQL Server product â“SQL Server 1.0, a 16-bit server for the OS/2 operating system in 1989 - and extends to thecurrent day.

13

Chapter 4

System Design and Architecture

4.1 System Architecture

Figure 4.1: System Architecture

14

Chapter 4. System Design and Architecture

4.2 Usecase Diagram

Figure 4.2: Usecase

15

4.3. Class Diagram

4.3 Class Diagram

Figure 4.3: Class Diagram

16


4.4 Data Flow Diagrams

Figure 4.4: DFD Level 0


17

4.4. Data Flow Diagrams


18


4.5 Component Diagram

Figure 4.7: Component Diagram

19

Chapter 5

Methodology

5.1 Modular Description

5.1.1 Webcam

A webcam short for a web camera is a digital camera that is connected to a computer. It ca sendlive pictures from whereevr it is sited to another location by means of the internet. May desktopcomputer screens and laptops come with a built in camera and microphone, but if yours doesnot , you can add a seperate webcam at any time.

There are various types. Some are plugged into computers through USB ports, but others arewireless (wifi). Other features might include:an integral microphone, the ability to pan and tilt, in-built sensors that can detect movement andstart recording, a light that, when on, will let you know that the camera is in use.

Figure 5.1: webcam

20

Chapter 5. Methodology

setting up a simple webcam if your computer doesn’t already have one built in is not difficult aslong as you stick to the easy steps that follow an apply a little patience.

it’s important to realise that there are hundreds of different types and brands of web cams andthey all have slightly different installation instructions. So you must follow the ones that camewith your webcam very carefully and do exactly as they say.

Follow these step-by-step instructions to install a webcam:

Step 1: Buy your webcam from a reputable supplier, either online or a local computer shop.Webcams come in all shapes and sizes, and vary from basic models to more complicated onesthat come with extra gadgets such as motion detectors. Prices vary a lot, too. Make sure thatthe one you choose has a built-in microphone if you want to use your webcam for chatting tofriends and relatives.

Step 2: Carefully read the installation instructions before attempting to install the webcam.

Step 3: Make sure you have everything to hand that you will need to complete your installation.The webcam should come with a USB cable that will connect it to your computer (except if youhave a wireless version).

Step 4: The webcam package includes a CD containing important software. Insert this intoyour computer CD drive. The set-up program should run automatically, but if it does not, clickStart and then My Computer. Double-click on the disk drive as this will prompt the files to runon the CD.

Step 5: Make sure that you follow meticulously the steps of the software program you will beinstalling the drivers that allow your computer to communicate with the webcam. It may beimportant to plug in the webcam in a certain order with other cables and equipment, so onlyplug it in when prompted to do so. Step 6: Now position your webcam. If it has a monitorclip, attach it securely to the top of your screen pointing at your face (see left for an example).Adjust it so that that people at the other end can see your whole face and not just your forehead.

Step 7: Now you have completed the set-up, it is the time to see the results! Click Start againand find your webcam program. Double-click on it and the program will open up.

5.1.2 Face Detection using Haar features

Object Detection using Haar feature-based cascade classifiers is an effective object detectionmethod proposed by Paul Viola and Michael Jones in their paper, "Rapid Object Detection us-ing a Boosted Cascade of Simple Features" in 2001. It is a machine learning based approachwhere a cascade function is trained from a lot of positive and negative images. It is then used todetect objects in other images.

21

5.1. Modular Description

Here we will work with face detection. Initially, the algorithm needs a lot of positive images(images of faces) and negative images (images without faces) to train the classifier. Then weneed to extract features from it. For this, haar features shown in below image are used. They arejust like our convolutional kernel. Each feature is a single value obtained by subtracting sum ofpixels under white rectangle from sum of pixels under black rectangle.

For this, we apply each and every feature on all the training images. For each feature, it finds thebest threshold which will classify the faces to positive and negative. But obviously, there will beerrors or misclassifications. We select the features with minimum error rate, which means theyare the features that best classifies the face and non-face images. (The process is not as simpleas this. Each image is given an equal weight in the beginning. After each classification, weightsof misclassified images are increased. Then again same process is done. New error rates arecalculated. Also new weights. The process is continued until required accuracy or error rate isachieved or required number of features are found).

5.1.3 Prinicipal component analysis(PCA):

One of the simplest and most effective PCA approaches used in face recognition systems isthe so-called eigenface approach. This approach transforms faces into a small set of essentialcharacteristics, eigenfaces, which are the main components of the initial set of learning images(training set). Recognition is done by projecting a new image in the eigenface subspace, afterwhich the person is classified by comparing its position in eigenface space with the position ofknown individuals.The advantage of this approach over other face recognition systems is in its simplicity, speedand insensitivity to small or gradual changes on the face. The problem is limited to files that canbe used to recognize the face. Namely, the images must be vertical frontal views of human faces.

The whole recognition process involves two steps:A. Initialization processB. Recognition process

The Initialization process involves the following operations:i. Acquire the initial set of face images called as training set.ii. Calculate the Eigenfaces from the training set, keeping only the highest eigenvalues. TheseM images define the face space. As new faces are experienced, the eigenfaces can be updatedor recalculated.iii. Calculate distribution in this M-dimensional space for each known person by projecting hisor her face images onto this face-space.These operations can be performed from time to time whenever there is a free excess opera-tional capacity. This data can be cached which can be used in the further steps eliminating theoverhead of re-initializing, decreasing execution time thereby increasing the performance of theentire system.

Having initialized the system, the next process involves the steps:i. Calculate a set of weights based on the input image and the M eigenfaces by projecting theinput image onto each of the Eigenfaces.

22


ii. Determine if the image is a face at all (known or unknown) by checking to see if the imageis sufficiently close to a free space.iii. If it is a face, then classify the weight pattern as either a known person or as unknown.iv. Update the eigenfaces or weights as either a known or unknown, if the same unknown personface is seen several times then calculate the characteristic weight pattern and incorporate intoknown faces. The last step is not usually a requirement of every system and hence the steps areleft optional and can be implemented as when the there is a requirement.

5.1.4 Linear Discriminate Analysis (LDA):

Linear Discriminant analysis explicitly attempts to model the difference between the classes ofdata. LDA is a powerful face recognition technique that overcomes the limitation of Principlecomponent analysis technique by applying the linear discriminant criterion. This criterion triesto maximize the ratio of the determinant of the between-class scatter matrix of the projectedsamples to the determinant of the within class scatter matrix of the projected samples. Lineardiscriminant group images of the same class and separates images of different classes of theimages.

Discriminant analysis can be used only for classification not for regression. The target vari-able may have two or more categories. Images are projected from two dimensional spaces toc dimensional space, where c is the number of classes of the images. To identify an input testimage, the projected test image is compared to each projected training image, and the test imageis identified as the closest training image.

The LDA method tries to find the subspace that discriminates different face classes. The within-class scatter matrix is also called intrapersonal means variation in appearance of the same in-dividual due to different lighting and face expression. The between-class scatter matrix alsocalled the extra personal represents variation in appearance due to difference in identity. Lineardiscriminant methods group images of the same classes and separates images of the differentclasses. To identify an input test image, the projected test image is compared to each projectedtraining image, and the test image is identified as the closest training image.

5.1.5 Linear Binary Pattern Histogram (LBPH):

LBP is really a very powerful method to explain the texture and model of a digital image.Therefore it was ideal for feature extraction in face recognition systems. A face image is firstsplit into small regions that LBP histograms are extracted and then concatenated in to a singlefeature vector. This vector forms an efficient representation of the face area and can be usedto measure similarities between images. Automatic facial expression analysis is a fascinatingand challenging problem, and impacts important applications in several areas such as humanâ“computer interaction and data-driven animation.

Deriving a facial representation from original face images is an essential step for successful fa-cial expression recognition method. In this paper, we evaluate facial representation predicatedon statistical local features, Local Binary Patterns, for facial expression recognition. Various

23

5.1. Modular Description

machine learning methods are systematically examined on several databases. Broad experi-ments illustrate that LBP features are effective and efficient for facial expression recognition.

The area binary pattern (LBP) was originally designed for texture description. It’s invariantto monotonic grey- scale transformations which are essential for texture description and anal-ysis for the reason of computational simplicity processing of image in real-time is possible.With LBP it’s possible to explain the texture and model of an electronic digital image. This iscompleted by dividing a picture into several small regions from which the features are extracted.

These features contain binary patterns that describe the environmental surroundings of pixels inthe regions. The features that are formed from the regions are concatenated into a single featurehistogram, which describes to forms a representation of the image. Images will then be com-pared by measuring the similarity (distance) between their histograms. According a number ofstudies face recognition utilising the LBP method provides positive results, both with regardsto speed and discrimination performance. Due to the way the texture and model of images isdescribed, the technique is apparently quite robust against face images with different facial ex-pressions, different lightening conditions, aging of persons and image rotation. hence it is goodfor face recogition purposes.

5.1.6 SQL server:

Microsoft SQL Server is a relational database management system developed by Microsoft. Asa database server, it is a software product with the primary function of storing and retrievingdata as requested by other software applications which may run either on the same computer oron another computer across a network (including the Internet).

Like other RDBMS software, Microsoft SQL Server is built on top of SQL, a standardizedprogramming language that database administrators (DBAs) and other IT professionals use tomanage databases and query the data they contain. SQL Server is tied to Transact-SQL (T-SQL), an implementation of SQL from Microsoft that adds a set of proprietary programmingextensions to the standard language.

24


5.2 Sequence Diagram

Figure 5.2: Sequence Diagram

25

5.3. Activity Diagram

5.3 Activity Diagram

Figure 5.3: Activity Diagram

26


5.4 Flow-Chart

Figure 5.4: Flow Chart

27

Chapter 6

Implementation Details

6.1 Assumptions And Dependencies

6.1.1 Assumptions

• The detector module should crop every human face from the input image and not to cropother areas. So it was assumed that the detector will be very accurate in cropping just andall the human faces from the uploaded image and save it for further recognition.

• The recognition module has to be very accurate in recognizing that is comparing thedetected image with the the images fetched from the database. So it was assumed that therecognition module will correctly recognize all the faces from the uploaded image so thata correct attendance sheet is produced.

6.1.2 Dependencies

• Our System use openCV. Opencv provides libraries which has funtions like LBP whichare the core part of detection and recognition module.

• Our System is also uses webcam preferably with high specification for clearly detectingand recognizing the faces.

• It also considers various factors such as varying light conditions, accessories on face andchanging environments.

28

Chapter 6. Implementation Details

6.2 Implementation Methodologies

The proposed system introduces an automated attendance system which integrates a web camand face recognition algorithms. Any laptop with a web camera can capture a live video fordetection and recognition. The live video will undergo face detection and face recognition sothe detected faces are extracted from the image. The extracted faces are then compared with thesaved faces of the database and on the successful recognition the database is updated with theattendance and a sheet is generated and displayed to the user.

This work is being carried out in five stages:

6.2.1 Step I implementation:

In this stage starting the GUI and the webcam for Generating Data for Training is performed.At first the wecam is started and then the system is trained that is the cropped images are savedto the database and they undergo detection and recognition. Further this data will be used tocompare the detected images in all the uploaded files and mark the attendance.

Figure 6.1: Starting of the GUI and WebCam

29

6.2. Implementation Methodologies

Figure 6.2: Training of the faces in database

Training of the person YASIR is performed by taking the training image from various angle andvarious expressions.

Figure 6.3: Trained data

As you can see in fig 6.3 the data of various students is trained in the specified folder. one cantrain any number of images of a particular person as required.Basically in this stage the capturing of the live video will be done using webcam and furtherface detection and recognition will be performed.

30


6.2.2 Step II implementation:

Face detection is done from live webcam using Haar classifier. The faces are detected by usingthe trainig data stored in the database.

Figure 6.4: Face is detected

In fig 6.4 the face of the person is detected and the message shown is "OUT OF PERIOD" asthe person is present before the specified time of lecture.

31

6.2. Implementation Methodologies

6.2.3 Step III implementation:

Face Recognition is performed using either PCA or LDA or LBPH algorithms,by comparingthe generated data with the data trained in the database.

Figure 6.5: Face is recognized

In fig 6.5 , The professor can define lecture timings directly in the GUI according to his/herneed. Once the lecture timing has started then the process is started and if the student is presentin the specified lecture timing and lecture threshold the face of the person is recognized fromthe trained images from the database and shown in the GUI with his/her name.

In fig 6.6 the person was not trained and hence it is showing "UNKNOWN".

32


Figure 6.6: Unknown face as the data is not trained

6.2.4 Step IV implementation:

As soon as the name of the student is shown the Attendance is marked with current date andtime.

Figure 6.7: Attendace Record of the present and absent students with date and time

if the face is matched with the trained data and if the face is not matched then the person willbe shown as unknown.Eventually,the attendance sheet is generated.

33

6.3. Competitive Advantages of the project:

6.3 Competitive Advantages of the project:

• The work of administration department to enter the attendance is reduced and also sta-tionary cost so every institute or organization will opt for both, time and money savingpurpose.

• Many companies like the fact that these video based systems are automated. They neednot worry about having extra task force, to monitor the attendance system.

• This system is cost efficient, no extra hardware required just a webcam itself.Hence it iseasily deployable.

• Easy maintainability as the system only requires a webcam (for detection) a permanentdatabase (for storage).

• It is a secure system as database can be protected record modification is prevented.

• There is no scope for forgery/proxy of another individual.

• It saves a lot of time as no manual work is involved in attendance management system

34

Chapter 7

Results and Analysis

7.1 Analysis and Result Discussion

Throughout the testing period, we observed the following problems in our system:

Algorithm used for Face Detection:

Haar like Feature was used throughout our system for face detection irrespective of the al-gorithms used for face Recognition. This algorithm worked with 100% accuracy under idealconditions for face detection.

Algorithms used for Face Recognition

1. Principal Component Analysis (PCA):Face Detection Accuracy : 100% throughout the testing period (Under ideal conditions)Face Recognition Accuracy : 90% per 10 faces in the database i.e. the first error was observedwhen the number of faces crossed 9.

2. Linear Discriminant Analysis (LDA):Face Detection Accuracy : 100% throughout the testing period (Under ideal conditions)Face Recognition Accuracy : 70% per 10 faces in the database i.e. the first error was observedwhen the number of faces crossed 7.

3. Linear Binary Pattern Histogram (LBPH):Face Detection Accuracy : 100% throughout the testing period (Under ideal conditions) FaceRecognition Accuracy : 50% per 10 faces in the database i.e. the first error was observed whenthe number of faces crossed 5.

35

Chapter 8

Conclusion and Future Scope

8.1 Conclusion

This system is developed for maintaining the attendance record. The main motive behind de-veloping this system is to eliminate all the drawbacks which were associated with manual at-tendance system. The drawbacks ranging from wastage of time and paper,till the proxy issuesarising in a class, are eliminated. Hence, desired results with user friendly interface is expectedin the future, from the system. The efficiency of the system could also be increased by integrat-ing various steps and techniques in the future developing stages of the system

8.2 Limitations

• System start misbehaving when the head count crosses certain limit.

• System faces recognition issues if the light conditions are poor.

• Webcam and processor with high specification is required as system consumes a lot ofresources.

36

Chapter 8. Conclusion and Future Scope

8.3 Future Enhancement

The research work has implemented a face recognition system by using PCA which is eigenvec-tor based multivariate analyses. Often, its operation can be thought of as revealing the internalstructure of the data in a way which best explains the variance in the data. By implementingPCA the proposed Face Recognition System supplies the user with a lower-dimensional picture,a "shadow" of this object when viewed from its most informative viewpoint.

The algorithm has been tested with multiple students in the scene and also captured faces atdifferent angles in the scene. The algorithm delivers quite good results but there is a room toimprove the algorithm performance in case of large number of students and also in case of facescaptured in a dark environment, so proposed system can be extended in the future to cover thisaspect. The efficiency of the algorithm also can be increased further so there is also a roomfor future work in this area. This system can be enhanced further in terms of achieving moreefficiency by ease of analysis of patterns in the data.

37

References

[1] Technical Paper on â• Image Based Intelligent Attendance Logging System, IEEE TechnicalPaper by Hary Oktavianto, Hsu Gee-Sern Chung Sheng-Luen, June 30-July 2, 2012, Dalian,China.

[2] Z. Zhou, X. Chen, Y. â“C. Chung, Z. He, T. X. Han, and J. M. Keller, "Activity analysis,summarization, and visualization for indoor human activity monitoring,â IEEE Transactions onCircuits and Systems for Video Technology, Volume 18, Issue 11, pp. 1489-1498, 2008.

[3] OpenCV. Available: http://sourceforge.net/projects/ opencvlibrary/.

[4] Activity zones for context-aware computing, Lecture Notes in Computer Science, Volume2864/2003, pp. 90-106, 2003.

[5]International Journal of Innovative Research in Computer and communication Engineer-ing(Vol.3,Issue 8,Aug 2015)(Automated Attendance System Using Face Recognition.)

[6]International Journal of Computer Applications (0975-8887) Volume 98-No.20,July 2014(Ad-jacency Matrix based Face Recognition Approach.)

[7]International Journal of Information Technology and Knowledge Management July-December2012, Volume 5, No. 2, pp. 361-3639(Face Recognition Techniques: Classification and Com-parisons.)

[8]Face Recognition using Line Edge Map Vipin Kumar and Mohit Mehta Department of Elec-tronics and communication, Punjab College of engineering and technology, India Accepted 01January 2014, Available online 10 January 2014, Vol.2 (Jan/Feb 2014 issue)

[9]International Journal of Advanced Computer Research (ISSN (Print): 2249-7277 ISSN (On-line): 2277-7970) Volume-4 Number-4 Issue-17 December-2014 939 Study of Face Recogni-tion Techniques Sangeeta Kaushik1*, R. B. Dubey2 and Abhimanyu Madan3

[10]Face Recognition Using Line Edge Map Yongsheng Gao, Member, IEEE, and Maylor K.H.Leung, Member, IEEE (IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINEINTELLIGENCE, VOL. 24, NO. 6, JUNE 2002)

38

Chapter 9

Appendix A

9.1 What is Local Binary Pattern?

Local binary patterns (LBP) is a type of visual descriptor used for classification in computer vi-sion. LBP is the particular case of the Texture Spectrum model proposed in 1990. LBP was firstdescribed in 1994. It has since been found to be a powerful feature for texture classification; ithas further been determined that when LBP is combined with the Histogram of oriented gradi-ents (HOG) descriptor, it improves the detection performance considerably on some datasets.

9.2 The LBP feature vector:

Divide the examined window into cells (e.g. 16x16 pixels for each cell).For each pixel in a cell,compare the pixel to each of its 8 neighbors (on its left-top, left-middle, left-bottom, right-top,etc.). Follow the pixels along a circle, i.e. clockwise or counter-clockwise. Where the centerpixelâTMs value is greater than the neighbour value, write"0". Otherwise, write "1". This givesan 8-digit binary number (which is usually converted to decimal for convenience).Compute thehistogram, over the cell, of the frequency of each "number" occurring (i.e., each combination ofwhich pixels are smaller and which are greater than the center). This histogram can be seen as a256-dimensional feature vector. Optionally normalize the histogram. Concatenate (normalized)histograms of all cells. This gives a feature vector for the entire window.

39

9.3. Correlation

9.3 Correlation

Correlation technique is used for face recognition. Where after face detection image under-goesface recognition process, where test image will be compared with training images in ordertoperform face recognition.

9.4 Average Paper Sheet waste generated in a year by a sin-gle employee

Lowering paper usage at the office can result in higher efficiency measures and increased pro-ductivity levels throughout an organization. Changes in paper consumption can include in-creasing recycling efforts, printing less or even going paperless with document managementsoftware. Doing so could provide inspiration to employees as well as large monetary savingsfor your organization.The average office worker continues to use a staggering 10,000 sheets ofcopy paper every year.

40

ACKNOWLEDGMENT

We would like to take the opportunity to express our sincere thanks to our guide Prof. Mubashir Khan,

Assistant Professor, Department of Computer Engineering, AIKTC, School of Engineering, Panvel for

his invaluable support and guidance throughout our project research work. Without his kind guidance &

support this was not possible.

We are grateful to him for his timely feedback which helped us track and schedule the process effec-

tively. His time, ideas and encouragement that he gave is helped us to complete our project efficiently.

We would also like to thank Dr. Abdul Razak Honnutagi, AIKTC, Panvel, for his encouragement

and for providing an outstanding academic environment, also for providing the adequate facWelities.

We are thankful to Prof. Tabrez Khan, HOD, Department of Computer Engineering, AIKTC, School

of Engineering, Panvel and all our B.E. teachers for providing advice and valuable guidance.

We also extend our sincere thanks to all the faculty members and the non-teaching staff and friends

for their cooperation.

Last but not the least, We are thankful to all our family members whose constant support and encourage-

ment in every aspect helped us to complete our project.

Chowdhary Obaid Ali Akbar Punjani Choudhary Yasir

Roll No:13CO25 Roll No:13CO49 Roll No:13CO24

41

project ii automated attendance management system using

Documents