Face Recognization System - Grasshopper Network ...grasshoppernetwork.com/Technical/Share/sites/default... · Web viewFace Recognization System is used for biometric security. But

FACE RECOGNIZATION SYSTEM

System EnvironmentThe system environment specifies the technical specification of requirements for the

developing software. The goal of this, it completely and consistently specifies the

requirements for the software products in a concise and unambiguous manner.

HARDWARE REQUIREMENT: Processor : Pentium IV

Memory : 32MB + RAM

Hard disk : 1 GB

Mouse : Scroll mouse

Monitor : Color monitor (preferable)

Key board : 102 keys

CD-ROM : Visual Studio is available only on CD-ROM

Webcam : Standard

2.2 SOFTWARE REQUIREMENT: Operating system : Ms-Windows98/2000/xp

Front end : VB 6.0 & VB.NET

Back end : Sql Server 2000

MINIMUM REQUIRMENT:Processor : Pentium IV

Memory : 512MB+RAM

Hard Disk : 80GB

Operating System : Ms-Windows xp

Copyright from Integrated Ideas Consultancy services 2003-2011 Page 1


System StudySystem study is a study about existing system. Here we will study in detail about the

existing system and its performance

Problem DefinitionFace Recognization System is used for biometric security. But for

recognized faces properly we required sophisticated face tracing cameras this camera are

quit expansive therefore in this project we developed a face recognized system which can

recognized the faces based on normal web camera by using igen values method

Existing System

Human guards.

Police.

Locks and keys.

Numeric keypads.

Magnetic cards / PINs.

Usernames / passwords.

Surveillance cameras.

Problems with the Traditional Security Approaches:

Human guards, police are expensive, prone to error and corruption.

Keys, PINs, passwords can be stolen, lost, or cracked.

PIN identifies a card and password identifies a username, not user.



Proposed SystemThe Facial recognition system mainly consists of two phases: Enrollment

phase and the Authentification / verification phase. The organization of the system is shown

below diagrammatically through the figures.

Enrollment: Capture and processing of user biometric data for use by system in subsequent

authentication operations.

During the first phase, user enrollment as shown in the Fig. 3.1, features are extracted from

the input face given by the user by a process called Feature extraction, and are modeled as a

template. The modeling is a process of enrolling user to the verification system by

constructing a model of his/her face, based on the features extracted from his/her facial

sample. After the features are extracted and all the signal processing is done the system

checks for the quality of the templates that are extracted from face, if sufficient quality of

features are extracted then the templates are stored in the database else the system needs to

acquire new facial image. The collection of all such enrolled models is called facial

database.



System AnalysisData flow diagram


Fig. a Level 0 Data flow diagram for the same system



Fig. b Level 1 Data flow diagram for the same system


4.3 UML Diagram:The UML does not include a specific notation for this database modeling as it

assumes an object oriented, development process and models data using objects and their

relationships. The UML diagram represent UML Diagrams to represent a semantic data

model.

Class Diagram:The UML methodology is being used extensively in software design and has many

types of diagram for various software design purposes. The class diagrams can be

considered as an alternative notation to ER diagrams, in UML class diagrams. A class is

displayed as a box

The top section gives the class name, middle section includes the attributes for individual

object of the class and the last section includes operations that can be applied to those object.

The designer of an optionally specify the domain of an attribute if desired by the domain

name or description.

A class represents an entity of a given system the provides an encapsulated implementation

of certain functionality of a given entity. The properties of a class are called attributes. A

class represents by a rectangle by a rectangle.




Fig. a Class Diagram for the same system


Sequential Diagram:UML Sequence diagrams are an easy and intuitive way of describing the behavior of

a system by viewing environment. A sequence diagram shows an interaction arranged in

time sequence.


Fig. b Sequence Diagram for the same system


4.4. E-R DiagramR Diagram:

The most widely used data modeling technique is entity relationship diagram, which

shows the data entities, their associated attributes and the relations between the entities. It is

widely used in database design.

An approach to data modeling proposed by, p.chen in 1976. An Entity relationship diagram

Is specialized graphic that illustrate the relationships between entities in a database. The

most widely used data modeling technique is entity relationship diagram, which shows the

data entities, their associated attributes and the relations between the entities. It is widely

used in database design.

Entity

Attribute

Relation

Figure: ER Notation



Methodology

The project will use the incremental and waterfall model. Incremental model will be

used to complete modules by module and testing the connected module. For example once

vendor and procurement is over, both will be tested. And will be released. Overall approach

will be waterfall where modules will be added to the system in top down order.


Fig. a E-R Diagram for the same system


System Design


Camera Face ImagesFace Detection

Data Base

Features Extraction

Eigen Faces

Nearest Neighbor classifier

Recognization

Test Images

Fig. Block diagram of the face Recognization system


Design of screens

Form1: Design of the screens






5.2. Sample Output

Fig. a Picture saves in the form



Fig. a Picture Training form



Fig. c Picture Test & Verified in the form



Fig. d Picture Test & Not Verified in the form



CodingPrivate Sub cmdStart_Click()

Call init

cmdStart.Caption = "Training Complete"

cmdStart.Enabled = False

cmdTest.Enabled = True

End Sub

Private Sub loadFace(Index As Integer, instance As Integer, picbox As PictureBox)

On Error GoTo loadImages_err

Dim filename As String

filename = App.Path & "\face\face" & Trim(CStr(Index)) & Chr(instance + 97) & ".jpg"

'MsgBox (filename)

If (Dir$(filename) <> "") Then

picbox.Picture = LoadPicture(filename)

End If

loadImages_exit:

Exit Sub

loadImages_err:

MsgBox "frmMain/loadFace/" & Error$(Err)

Resume loadImages_exit

End Sub



Private Sub init()

Dim i As Integer

Dim j As Integer

Call faces.init(image_Width, image_Height)

For j = 0 To 1

For i = 0 To 19

Call loadFace(i, j, pic(0))

Call faces.addFace(pic(0), Trim(Str(i)))

Next

Next

End Sub

Private Sub cmdTest_Click()

Static i As Integer

Dim closestImage As Integer

lblIdentity.Visible = True

pic(1).Visible = True

i = Text1

Call loadFace(i, 2, pic(0))

closestImage = Val(faces.Identify(pic(0)))

If closestImage = i Then

Call loadFace(closestImage, 0, pic(1))

MsgBox "Verified"



Else

'pic(1).Visible = False

MsgBox "not Verified"

End If

'i = i + 1

'If (i > 19) Then

' i = 0

'End If

End Sub

Private Sub Command1_Click()

Dim i As Integer

i = Shell("D:\\Imran ali\\Face Recognition Expression Ultimate\\Face Recognition final\\

FaceBiometricFinal\\CamPart", vbNormalFocus)

End Sub

Private Sub Command2_Click()

Out 888, 0

End Sub

namespace i_rely_solely_on_god

{

class Face_Detection

{

//Define variable for Convert RGB 2 YCBCR

//double Y = 0;

//double Cb = 0;

double Cr = 0;

int R = 0;



int G = 0;

int B = 0;

int r = 0;

int Testdetection, WPresentdetection = 0;

int BPresentdetection1 = 0;

AForge.Math.Histogram activeHistogram = null;

//Main function for face detection

int counter = 0;

public ArrayList al;

public int[] FaceDetection(Form1 Main, PictureBox PicFirst,

PictureBox Picresult,TextBox TWskin,PictureBox face,TextBox

TBskin,PictureBox picEye,TextBox txtEyeCount)

{

Testdetection = 0;

Graphics hh = PicFirst.CreateGraphics();

Bitmap PreResult = new Bitmap(PicFirst.Image);

Bitmap Result = new Bitmap(PicFirst.Width, Picresult.Height);

Bitmap HisResult = new Bitmap(PicFirst.Width,

Picresult.Height);

Bitmap Template50 = new Bitmap("sample50.bmp");

Bitmap Template25 = new Bitmap("sample25.bmp");

Bitmap facee = new Bitmap(face.Width, face.Height);

Bitmap eye = new Bitmap(40, 20);

for (int i = 0; i < PicFirst.Width; i++)

{

for (int j = 0; j < PicFirst.Height; j++)

{

//Getting red layer

R = PreResult.GetPixel(i, j).R;

//Getting green layer

G = PreResult.GetPixel(i, j).G;

//Getting blue layer

B = PreResult.GetPixel(i, j).B;

//Formula for convert RGB 2 YCBCR

//Y = 0.299 * R + 0.587 * G + 0.114 * B;

//Cb = -0.169*R - 0.332*G + 0.500*B;



Cr = 0.500 * R - 0.419 * G - 0.081 * B;

//Ckeck for "-" values(Because we can't use "-" values

for RGB color)

if (Cr < 0)

//Convert to Positive values

Cr =0;

HisResult.SetPixel(i, j, Color.FromArgb((int)Cr,

(int)Cr, (int)Cr));

if (Cr > 10)

//Convert to Positive values

Cr = 255;

//if (Cr>20)

// //Convert to Positive values

// Cr = Cr+128;

//Set the pixel by cr value

Result.SetPixel(i, j, Color.FromArgb((int)Cr,

(int)Cr, (int)Cr));

}

}

//Create filter form my image

FiltersSequence processingFilter = new FiltersSequence();

//Detection the adges

processingFilter.Add(new Edges());

WPresentdetection=0;

BPresentdetection1= 0;

//Apply filter for my pic

Picresult.Image =processingFilter.Apply( Result);

//Detect face with big template

for (int d = 0; d <150-50; d+=20)

{

Testdetection = 0;

WPresentdetection = 0;

BPresentdetection1 = 0;

for (int c = 0; c <150-50; c+=20)

{

Testdetection = 0;





for (int w = 0; w < Template50.Width; w++)

{

for (int h = 0; h < Template50.Height; h++)

{

if (Template50.GetPixel(w, h).B == 255)

{

if (Result.GetPixel(d + w, c + h).B ==

Template50.GetPixel(w, h).B)

{

WPresentdetection++;

}

}

//if (Template50.GetPixel(w, h).B == 255)

//{

// if (Result.GetPixel(d + w, c + h).B ==

Template50.GetPixel(w, h).B)

// {

// BPresentdetection1++;

// }

//}

}

}

TWskin.Text = WPresentdetection.ToString();

TBskin.Text = BPresentdetection1.ToString();

if (WPresentdetection >

377)//&&BPresentdetection1>1579)

{

hh.DrawRectangle(new Pen(Color.Green), d, c,60,

60);

hh.DrawRectangle(new Pen(Color.Red), d+20, c+20,

40, 20);

for (int i = 0; i < 60; i++)

{

for (int j = 0; j< 60; j++)

{

r = PreResult.GetPixel(i + d, j + c).R;



facee.SetPixel(i, j,

Color.FromArgb((int)r, (int)r, (int)r));

face.Image = facee;

// al.Add(facee);

}

}

int eyeCount = 0;

Bitmap im = (Bitmap)PicFirst.Image;

TWskin.Text = WPresentdetection.ToString();

TBskin.Text = BPresentdetection1.ToString();



Testdetection = 1;

break;

}

// Detect face with small template

//else

//{

// Testdetection = 0;

// WPresentdetection = 0;

// for (int w = 0; w < Template25.Width; w++)

// {

// for (int h = 0; h < Template25.Height; h++)

// {

// if (Result.GetPixel(d + w, c + h).B ==

255)

// {

// if (Result.GetPixel(d + w, c + h).B

== Template25.GetPixel(w, h).B)

// {

// WPresentdetection++;

// }

// }



// }

// }

// if (WPresentdetection > 50)

// {

// hh.DrawRectangle(new Pen(Color.Red), d, c,

30, 30);

// for (int i = 0; i < 30; i++)

// {

// for (int j = 0; j < 30; j++)

// {

// r = PreResult.GetPixel(i + d, j +

c).R;

// facee.SetPixel(i, j,

Color.FromArgb((int)r, (int)r, (int)r));

// face.Image = facee;

// }

// }

// TWskin.Text = WPresentdetection.ToString();

// WPresentdetection = 0;

111 // Testdetection = 2;

// break;

// }

//}

}

if (Testdetection == 1 || Testdetection == 2)

{


BPresentdetection1=0;

Testdetection = 0;

break;

}

}

//Draw histogram

AForge.Imaging.ImageStatistics stat =

new AForge.Imaging.ImageStatistics(HisResult);

if (stat != null)

{

//Do if the pic is gray



if (stat.IsGrayscale)

{

activeHistogram = stat.Red;

}

//Do if the pic is colourful

if (!stat.IsGrayscale)

{

activeHistogram = stat.Red;

}

}

return (activeHistogram.Values);

}

}

}


{

class Camera

{

//Variable of WebCamCapture class

private WebCamCapture Cam;

private Form1 Parent;

PictureBox PicFi;

//Initialize camera

public void Init_Cam(Form1 form, int W, int H, PictureBox

picFisrt)

{

Parent = form;

PicFi = picFisrt;

Cam = new WebCamCapture();

//Set camera height

Cam.CaptureHeight = H;

//Set camera width

Cam.CaptureWidth = W;

//Refresh picture after avery one milli seconds



Cam.TimeToCapture_milliseconds = 1;

//Get picture from camera

Cam.ImageCaptured += new

WebCamCapture.WebCamEventHandler(Cam_ImageCaptured);

}

public void Start()

{

//Starting Capture

Cam.Start(0);

}

//Get Picture of camera

//Set picCam equal camera image

public void Cam_ImageCaptured(object source, WebcamEventArgs e)

{

//Set image to picturebox

PicFi.Image = e.WebCamImage;

}

}

}


{

public partial class Form2 : Form

{

public Form2()

{

InitializeComponent();

}

private void button1_Click(object sender, EventArgs e)

{

pictureBox1.Image.Save

("d:\\"+txtName.Text ,System.Drawing.Imaging.ImageFormat.Jpeg);

this.Close();



}

}

}


{

partial class Form2

{

/// <summary>

/// Required designer variable.

/// </summary>

private System.ComponentModel.IContainer components = null;

/// <summary>

/// Clean up any resources being used.

/// </summary>

/// <param name="disposing">true if managed resources should be

disposed; otherwise, false.</param>

protected override void Dispose(bool disposing)

{

if (disposing && (components != null))

{

components.Dispose();

}

base.Dispose(disposing);

}

#region Windows Form Designer generated code

/// <summary>

/// Required method for Designer support - do not modify

/// the contents of this method with the code editor.

/// </summary>

private void InitializeComponent()

{



this.pictureBox1 = new System.Windows.Forms.PictureBox();

this.txtName = new System.Windows.Forms.TextBox();

this.label1 = new System.Windows.Forms.Label();

this.button1 = new System.Windows.Forms.Button();

((System.ComponentModel.ISupportInitialize)

(this.pictureBox1)).BeginInit();

this.SuspendLayout();

//

// pictureBox1

//

this.pictureBox1.Location = new System.Drawing.Point(55, 20);

this.pictureBox1.Name = "pictureBox1";

this.pictureBox1.Size = new System.Drawing.Size(278, 254);

this.pictureBox1.TabIndex = 0;

this.pictureBox1.TabStop = false;

//

// txtName

//

this.txtName.Location = new System.Drawing.Point(113, 289);

this.txtName.Name = "txtName";

this.txtName.Size = new System.Drawing.Size(220, 20);

this.txtName.TabIndex = 1;

//

// label1

//

this.label1.AutoSize = true;

this.label1.Location = new System.Drawing.Point(52, 292);

this.label1.Name = "label1";

this.label1.Size = new System.Drawing.Size(35, 13);

this.label1.TabIndex = 2;

this.label1.Text = "Name";

//

// button1

//

this.button1.Location = new System.Drawing.Point(55, 341);

this.button1.Name = "button1";

this.button1.Size = new System.Drawing.Size(278, 23);

this.button1.TabIndex = 3;



this.button1.Text = "SAVE";

this.button1.UseVisualStyleBackColor = true;

this.button1.Click += new

System.EventHandler(this.button1_Click);

//

// Form2

//

this.AutoScaleDimensions = new System.Drawing.SizeF(6F, 13F);

this.AutoScaleMode = System.Windows.Forms.AutoScaleMode.Font;

this.ClientSize = new System.Drawing.Size(381, 416);

this.Controls.Add(this.button1);

this.Controls.Add(this.label1);

this.Controls.Add(this.txtName);

this.Controls.Add(this.pictureBox1);

this.Name = "Form2";

this.Text = "Form2";

((System.ComponentModel.ISupportInitialize)(this.pictureBox1)).EndInit();

this.ResumeLayout(false);

this.PerformLayout();

}

#endregion

public System.Windows.Forms.PictureBox pictureBox1;

public System.Windows.Forms.TextBox txtName;

private System.Windows.Forms.Label label1;

private System.Windows.Forms.Button button1;

}

}



Main Form:

Test Case

a. Training: a.Face1

Test b.Face1

b. Training: a.face12

Test b.face12

c. Observation: a. Valid

b.Invalid

d.Output: a. If it’s valid then the Display the face & Verified it. .

b. If it’s invalid then display it is not verified.



List of abbreviations, Figures, Tables Table: user

FIELDS TYPE Size descriptionSlno Int To Enter the serial number

Name varchar 100 To enter the namePhone varchar 30 To enter the phone numberEmail varchar 100 To enter the email address

Address varchar 200 To enter the addressTable: images

Fields Type Size DescriptionSlno Varchar to enter the serial number

Imagea Varchar 20 To enter the a imagesImageb Varchar 20 To enter the b images

ASP -> Active server pages

SQL -> Structure query language

VWD-> Visual web developer

VB : Visual Basic

DFD : Data Flow Diagram.

CSS : Cascading Style Sheet.

RAM : Random Access Memory.

GB : Giga Byte.

XP : eXPerienced



Figures

Figure 4.1 zero level DFD

Figure 4.1 first levels DFD

Fig. a Class Diagram for the same system

Fig. b Sequence Diagram for the same system

Fig. a E-R Diagram for the same system



Fig. a Picture saves in the form

Fig. a Picture Training form

Picture Test & Verified in the form

Picture Test & Not Verified in the form



Conclusion

Even though face of a every persons is unique , the pose , the distance from the

cameras an light intensity where is which effect the performance of the system there fore in

the project of the pose in variant face recognized system is developed which can recognized

the faces even when such attributes changes. This system can be further inspect by

recognizing the faces directly in the video.



Future Enhancement

The face Recognization algorithm here can detect the face i.e. irrespective of the

distance of the user from camera light intensity, pose of the user etc. But the algorithm has

an upper limit & can recognize up to 20 Faces.

As the number of faces increases, rates of misdetection also increase. This can be improved

by combining phase or frequency features like revealed transform alongside the Eigen

features. Further, stronger classified like neural network can be implemented which

increases which the efficiency further.



Bibliography

Books

C# and .Net platform

By Andrew Troelsen.

Inside C#

By Tom Archer.

Fundamentals of database Systems

By Ramez Elmasri and S. B. Navathe

1] R. Brunelli and T. Poggio, “Face recognition: features versus templates,” IEEE PAMI,

vol.15. No 10, pp.1042-1052, Oct. 1993.




Documents

Face Recognization System - Grasshopper Network ...grasshoppernetwork.com/Technical/Share/sites/default... · Web viewFace Recognization System is used for biometric security. But