[INTERNATIONAL JOURNAL FOR RESEARCH &

DEVELOPMENT IN TECHNOLOGY]

Volume-4,Issue-2, Aug - 2015

ISSN (O) :- 2349-3585

Web Based Surveillance System Using A Snapshot

Model
YUVRAJ SAINI 1, N. C. BAJIA 2, ABHINANDAN JAIN 3, MEENU BHATI 4
1234

DEPARTMENT OF ELECTRONICS & COMMUNICATION,

123
PRATAP UNIVERSITY, JAIPUR
4
Global College of Technology
Analysis (PCA), facial recognition system, 2D faces
recognition, POP3.

Abstract: Todays world is computerized world. The

1. INTRODUCTION

cybercrime is also on an increase the web of www is

increased day by day. So protection of software is the

Electronic mail (e-mail) is one of the most popular network

important part. In existing system, email account can be

services nowadays. Most e- mail systems that send mail over

accessed by providing username and password. SMTP and

the Internet use simple mail transfer protocol (SMTP) to send

MIME protocol is used for sending notification to user. For

messages from one server to another. The messages can then

electronic mail (e-mail) transmission across Internet

be retrieved with an e-mail client using either post office

Protocol (IP) networks Simple Mail Transfer Protocol

protocol (POP) or Internet message access protocol (IMAP).

(SMTP) is used Email is submitted by a mail client (MUA) to

SMTP is used as the common mechanism for transporting

a mail server (MSA, mail submission agent) using SMTP.

electronic mail among different hosts within the transmission

The MSA delivers the mail to its mail transfer agent (MTA,

control protocol/Internet protocol (TCP/IP) suite. It is an

mail transfer agent). SMTP protocol is connection-oriented,

application layer protocol. Under SMTP, a client SMTP

text-based

can

process opens a TCP connection to a server SMTP process on

communicates with a mail receiver by sending command

a remote host and attempts to send mail across the connection.

and provide necessary data over a reliable ordered data

A face recognition system is a computer application for

stream channel. An SMTP session consists of commands

automatically identifying and verifying a person from a digital

send by an SMTP client (the initiating agent, sender, or

image/picture or a video frame from a video source. One of

transmitter) and responses from the SMTP server (the

the ways to do this is by comparing selected facial features

listening agent, or receiver) so that the session is opened,

from the image and a facial database. Face recognition is an

and session data are exchanged. A session may include zero

active field of research and has increased significantly since

or more SMTP transactions. MIME defines for sending

the early 1990s. Our aim is to study different face recognition

other kinds of information in email. These include text in

techniques and implement a 2D face recognition technique

other languages like English using character encodings and

using image processing and design a SMTP/POP3. E Mail

files containing images, sounds, movies. Mapping messages

client application will use the face recognition module for

into and out of MIME format is typically done automatically

validation and authentication of user. The application will

by an email client or by mail servers when sending or

allow the user to send/receive emails like ordinary email client

receiving Internet (SMTP/MIME) email

but instead of asking the user to specify the user name and

protocols

in

which

mail

sender

password the face recognition module must do the

Keywords Detection, Image processing, Spontaneous

authentication.

facial expression, Principal Component

There are many systems based on face recognition but there is

no previous system which is using face recognition for email

www.ijrdt.org | copyright 2014, All Rights Reserved.

Volume-4,Issue-2, Aug-2015
ISSN (O) :- 2349-3585

Paper Title:- Web Based Surveillance System Using A Snapshot

Model

access. When an e-mail is sent from the sender to receiver, in

person by using the webcam. Then image matching of that

most cases this involves, the sender machine sends the email

image is done with admin stored image from the database.

to local SMTP sever, which in then sends mail to recipients

Image matches admin image, admin can access the system and

local SMTP sever, and finally to recipients local machine.

if image does not match then the person will be unauthorized,

so for security we send a message on the admin mobile phone

2. JAVA MIME-COMPLIANT SMTP SERVICE

SMTP Client in Surveillance Monitor provides a Java MIME-

with help of any gateway and a mail on admin email-id with

hackers image and some notification.

compliant reusable package (as shown in Figure 1). SMTP

(Simple Mail Transfer Protocol) defined in RFC 821 is a

4. IMPLIMENTATION DETAILS
4.1 Method

standard e-mail sending protocol for a TCP/IP-based network.

A client can simply send a message to an SMTP server by
creating a socket connection to port 25 on the server. RFC 821
requires the SMTP data be 7-bit ASCII characters whereas
RFC 822 describes the format and some of the message
content

semantics

but

contains

no

content

structure

Fig.1 Block Diagram of Implementation

specification. RFC 1521 remedies the limitation of ASCIIbased messages by specifying an invertible encoding/decoding

Sample capture - When the system is attached to a video

scheme (e.g., BASE64, QUOTED-PRINTABLE, 7BIT and

surveillance system, the recognition software searches the

8BIT) for message data types. The Multipurpose Internet Mail

field of view of a video camera for faces. If there is a face in

Extension (MIME) standard, defined in RFCs 2045 - 2049,

the view, it is detected within a fraction of a second. A multi-

complements RFCs 821/822 defining of the message content

scale algorithm is used to search for faces in low resolution.

structure and support of the encoding of different types of

The system switches to a high resolution search only after a

media data (image, audio, and video) for transmission over

head-like shape is detected.

SMTP protocol. Currently, the SMTP Client can transmit two

MIME text message types text/plain and test/html, and two
image types image/jpeg and image/gif encoded in the
Base64 Content- Transfer-Encoding format as it is preferred
over quoted-printable for binary data [17].
3. PROPOSED SYSTEM

Alignment - Once a face is detected, the system determines

the heads position, size and pose. A face needs to be turned at
least 35 degrees toward the camera for the system to register
it.
Normalization -The image of the head is scaled and rotated
so that it can be registered and mapped into an appropriate size

We are supposed to develop an email application that will

and pose. Normalization is performed regardless of the heads

allow the user to access his/her account by face recognition

location and distance from the camera. Light does not impact

instead of providing username and password. The system

the normalization process.

provides face recognition technique to access an account.

After login, account will be opened if and only if face of the
user matched with the photograph of user stored in the
database.
In our project we are developing a System such that we
capture the image of the authorized as well as unauthorized

www.ijrdt.org | copyright 2014, All Rights Reserved.

Representation - The system translates the facial data into a

unique code also called as template. This coding process
allows for easier comparison of the newly acquired facial data
to stored facial data the template is much smaller than the
image from which it is drawn whereas quality facial images

(6)

Volume-4,Issue-2, Aug-2015
ISSN (O) :- 2349-3585

Paper Title:- Web Based Surveillance System Using A Snapshot

Model

generally require 150- 300 kb, the templates are approx. 1300
bytes or less than 1/100th of original.
Matching - The newly acquired facial data is compared to the
stored data and (ideally) linked to at least one stored facial
Fig.3

representation. The degree of similarity required for

verification also known as threshold can be adjusted for
different personals, pcs, time of the day and other factors. If

Window for the confirmation

the face of the user is matched with the photograph stored in

the database. His account will get opened

4.4 Sending and receiving of mails

4.2 Registration module

In this module after getting access to email account user will

In this module proposed system will gather all personal details

of user and just like registration done at other social websites
or email website for eg. Gmail, yahoo etc. In addition to

be able to send or compose mails, attach files to mails,

download files form mails, delete mails, read mails, move
mails, and receive mails normally.

common personal details such as Name, Address, Date Of

5. BASIC SMTP ARCHITECTURE

Birth, Age, Gender, nationality proposed system is supposed

to capture face of a user, this captured face will be stored in

SMTP stands for Simple Mail Transfer Protocol. MTP

the database.

preceded SMTP. The Commands of MTP are based directly on

4.3 Login module

those of FTP. It came into existence in 1981 (RFC 780).

SMTP is simpler than MTP it replaced. When an e-mail is sent

In this module login into proposed system will be done by

from the sender to receiver, in most cases this involves, the

capturing face of a user with web cam and comparing this

sender machine sends the email to local SMTP sever, which in

captured face with users face stored in database during

then sends mail to recipients local SMTP sever, and finally to

registration. If both faces match, access will be given to the

recipients local machine.

user.

5.1 Limitations
1.

Security matters for SMTP are worse.

2.

Its usefulness is limited by its simplicity.

3.

Transmission of executable files and binary files

using SMTP is not possible without converting into
text files. Use MIME to send mail in other format.

Fig..2 Window for the login

4.

It cannot transmit text data that contains national

language

characters.

These

national

language

characters use 8-bit codes with values of 128

decimal or more.
5.

www.ijrdt.org | copyright 2014, All Rights Reserved.

It is limited to 7-bit ASCII characters only.

(7)

Volume-4,Issue-2, Aug-2015
ISSN (O) :- 2349-3585
6.

Paper Title:- Web Based Surveillance System Using A Snapshot

Model

SMTP servers may reject mail messages beyond

some specific length.

5.2 Special Features

1.

Mail Forwarding: SMTP server may agree to accept

e-mail for non-local mailbox and forward it to the
appropriate destination.
Fig.4. Implementation of reading of mail module

2.

Mail

Gate

waying:

SMTP

servers

can

be

implemented as e-mail gateways which can translate

TCP/IP email in a suitable form for some another email system and vice-versa.
3.

7. CONCLUSION
This application will allow secure access to email account and
possibility if hacking by guessing password will be reduced at

Mail Relaying: SMTP includes the ability to relay

much extend. This will help industries where important

mail from one server to another, as explained earlier,

communications with partners, client and employees are done

provided certain conditions are met.

using emails. With this application security and confidentiality

is increased. We can extend this system in future to be used for

4.

5.

Address Debugging: VRFY command allows the

login into social networking sites such as facebook.com etc.

client to ask the sender to verify address of recipient

We can also use this system in ERP at colleges for taking

without sending mail to recipient.

attendance of staff members.

Mailing List Expansion: EXPN command allows

This work has presented a survey about Multimodal

expanding mailing list.

Spontaneous Face Detection Using Pcz Security. It isnt a

6. EXPERIMENTAL RESULTS
Receiving and reading of mails
This window opens up when user does successful login that is
when face are matched. This is the first window that opens up
after login. In this window user has to enter server address of
imap protocol, user name, password, check SLS connection
option and then click on Start button. As soon as start button is
clicked all the mails of a user will appear in right hand side
section of window. By clicking on any mail user can read,
delete, undelete, make it unread, pure i.e refresh and can move
that mail and can upload files.

trivial task, and today remains unresolved. These are the

current lines of research we are developing PCZ-SECURITY
system which can control unauthorized access from any
location. Quick action against illegal access can be taken New
or extended feature extraction methods. There is much
literature about extending or improving well

known

algorithms. For example, including weighting procedures to

PCA. Developing new kernel based methods or turning
methods like LDA into semi-supervised algorithms. Feature
extraction method combination. Many algorithms are being
built around this idea. As many strong feature extraction
techniques have been developed, the challenge is to combine
them. For example, LDA can be combined with SVD to
overcome problems derived from small sample sizes.
Classifier and feature extraction method combinations. Its a
common approach to face recognition. For instance, there are
recent works that combine different extraction methods with
adaptive local hyper plane (ALH) classification methods. Face

www.ijrdt.org | copyright 2014, All Rights Reserved.

(8)

Volume-4,Issue-2, Aug-2015
ISSN (O) :- 2349-3585

Paper Title:- Web Based Surveillance System Using A Snapshot

Model

recognition is also resulting in other dares, like expression

[1] Jafri, R.; Arabnia, H. (2009): A Survey of Face

recognition or body motion recognition. Overall, face

Recognition Techniques, Journal of Information Processing

recognition techniques and the emerging methods can see use

Systems, Vol.5, No.2.

in other areas. Therefore, it isnt just an unresolved problem

[2] Kawaguchi, Y.; Shoji, T.; Lin, W.; Kakusho, K.; Minoh, M.

but also the source of new applications and challenges.

(2005):

Administrator can get complete idea of who is trying to access

System.

the system with help of image capturing of unauthorized

[3] Senior, A. W.; Bolle, R. M. (2002): Face Recognition And

person and then sending image via SMS and E-Mail alert.

Its Applications, Chapter 4.

Enhance security should be provide with the help of face

[4] Verdi,J.(2014):Facial Recognition Technology Electronic

recognition technique.

Privacy Information Center.

Face

Recognition-based

Lecture

Attendance

[5] Zhang, Z.; Zhou, Z.; Sun, H.; Dong, F. (2012):

8. FUTURE SCOPE
Commercial applications have so far only scratched the
surface of the potential. Installations so far are limited in their
ability to handle pose, age and lighting variations, but as
technologies to handle these effects are developed, huge
opportunities for deployment exist in many domains. Face
verification, matching a face against a single enrolled
exemplar, is well within the capabilities of current Personal
Computer hardware. Since PC cameras have become
widespread, their use for face-based PC logon has become
feasible, though take-up seems to be very limited. Increased
ease-of-use over password protection is hard to argue with
todays somewhat unreliable and unpredictable systems, and
for few domains is their motivation to progress beyond the
combinations of password and physical security that protect
most enterprise computers. As biometric systems tend to be
third party, software add-ons the systems do not yet have full
access to the greater hardware security guarantees afforded by
boot-time and hard disk passwords. Visionics face-based
screen lock is one example, bundled with PC cameras.
Naturally such PC-based verification systems can be extended
to control authorization for single-sign-on to multiple
networked services, for access to encrypted documents and
transaction authorization, though again uptake of the
technology has been slow.

Comparison of Three Face Recognition Algorithms,

International Conference on Systems and Informatics.
[6] M. Osadchy, Y. LeCun, and M. Miller, Synergistic face
detection and pose estimation with energy-based models,
Journal of Machine Learning Research, vol. 8, pp. 1197
1215, May 2007.
[7] P. Viola and M. Jones, Rapid object detection using a
boosted cascade of simple features, in Proc. IEEE Conf. on
Computer Vision and Pattern Recognition, 2001, pp. 511518.
[8] C. Chen, R. Veldhuis, T. Kevenaar, and A. Akkermans,
Biometric binary string generation with detection rate
optimized bit allocation, in CVPR Workshop on Biometrics,
2008, pp. 17.
[9] P. J. Phillips, H. Moon, S. A. Rizvi, and P. J. Rauss, The
FERET evaluation methodology for face-recognition
algorithms, PAMI, vol. 22, no. 10, pp. 10901104, 2000.
[10] T. Sim, S. Baker, and M. Bsat, The CMU pose,
illumination, and expression database, PAMI, vol. 25, pp.
16151618, 2003.
[11] A. Juels and M. Sudan, A fuzzy vault scheme, in
Symposium on Information Theory, 2002.
[12] P. Tuyls and J. Goseling, Capacity and examples of
template protecting biometric authentication systems, in
ECCV Workshop BioAW, 2004.
[13] Y. Dodis, R. Ostrovsky, L. Reyzin, and A. Smith, Fuzzy
extractors: How to generate strong keys from biometrics and
other noisy data, SIAM J. Comput., vol. 38, no. 1, pp. 97
139, 2008.

REFERENCES

www.ijrdt.org | copyright 2014, All Rights Reserved.

(9)

Volume-4,Issue-2, Aug-2015
ISSN (O) :- 2349-3585

Paper Title:- Web Based Surveillance System Using A Snapshot

Model

[14] Y. Adini, Y. Moses, and S. Ullman, Face recognition: the

Conf. on Automatic Face and Gesture Recognition, 2006, pp.

problem of compensating for changes in illumination

560566.

direction, PAMI, vol. 19, no. 7, pp. 721732, 1997.

[18] S. Avidan and M. Butman, Blind vision, in ECCV (3).

[15] M. Turk and A. Pentland, Eigenfaces for recognition,

Springer, 2006, pp. 113.

Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 7186,

[19] A. Senior, S. Pankanti, A. Hampapur, L. Brown, Y.-L.

1991.

Tian, A. Ekin, J. Connell, C. F. Shu, and M. Lu, Enabling

[16] N. K. Ratha, S. Chikkerur, J. H. Connell, and R. M.

video privacy through computer vision, IEEE Security and

Bolle, Generating cancelable fingerprint templates, PAMI,

Privacy, vol. 3, no. 3, pp. 5057, 2005.

vol. 29, no. 4, pp. 561572, 2007.

[20] F. Dufaux and T. Ebrahimi, Scrambling for Video

[17] T. Boult, Robust distance measures for face-recognition

Surveillance with Privacy, in IEEE Workshop on Privacy

supporting revocable biometric tokens, in IEEE, 7th Intl.

Research in Vision. IEEE, 2006.

www.ijrdt.org | copyright 2014, All Rights Reserved.

(10)