TWO LEVEL SECURITY SYSTEM USING MATLAB (KEYPAD+ FACE RECOGNTION)

PROJECT IDEA: The future of computing is not limited to controlling the computers by our conventional input door control like keyboards, mouse, joystick etc. The technologies are changing very rapidly and very soon it will be our conventional method to automate the system Different software companies as working on face recognition software including Math-Works. We will use M T! " here for face detection. Humans often use faces to recognize individuals and over the past few decades advancement in computing has led to the recognitions automatically using the image acquiring hardware and computing algorithms. The algorithms had been developed through sophisticated mathematical computing and matching process to recognize the face of the individual. The development has propelled various face recognition technologies which add on to the security of the system. This technology can be used for the verification as well as identification (open set & close set operations). Automatic face recognition system is new concept emerged. This system requires the various features matching of the face by the administrator with a pre defined data. acial recognition technology ( !T) has emerged as an attractive solution to address many contemporary needs for identification and the verification of identity claims. "t brings together the promise attempt to tie identity to individually distinctive features of the body# and the more familiar functionality of visual surveillance systems

"$A%& 'A(T)!& *&+"'&

',$()T&!

*,,! ',0T!,1

-&T)( .,/

KEYPAD

INTRODUCTION: The whole project can be divided into two parts. Part one includes hardware and second includes software. In Hardware we are using the !" port of the co#puter$ usb to uart interface$ %e&pad unit and controller and of interface the door control. In software section we shall use 'AT(A" )**+,)*-- to interact with the co#puter and !" port for co##unication for a recognition and notification sending and receiving fro# the real ti#e hardware. In this project there are two levels

of securit& that is first user has to enter the correct password .e#bedded/ and then face is #atched.'AT(A"/ then the door will open else in all cases alar# will activate. . DESCRIPTION HARDWARE: In hardware the co#ponents are !" port$ !" to A0T voltage level converter controller to ta%e input and generate output. To drive the #otor we have used L293D IC capable of provide larger amount of current to drive the motor. We also have a ke pad unit for user to enter the password. Circ i!": !" to A0T converters circuit for A0T co##unication.

()12D,#otor driver circuit 3ircuit for 'icrocontroller !" webca#

(3D Interface Ke&pad interface.242/

BLOCK DIAGRAM
FACE DETECTION FOR DOOR CONTROL

WINDOW 'P

OS

INTERFACE DESIGNED IN MATLAB

USB TO UART+C#$!r#%%&r

ALARM

DOOR CONTROL

KEYPAD

( SOFTWARE: The software section is co#pletel& based on !"#L"$. In our interface we have used !"#L"$ for face recognition. We have used it in such a wa that it matches the face from the predefined database and generates an event. #his event is used to control the device b giving the controller input to control the output and thus control door control KEY COMPONENTS: HARDWARE: 3o#puter s&ste# !" webca# !" T5 A0T #odule AT61!6)72 controller ()12D #otor driver 0esistors$ (ED. $ P3"$#otors etc. KEYPAD using switches

SOFTWARE: 8indow 5! 'AT(A" )**+. IA9IP toobo4es/ 'IK05 3 for controller progra##ing. ADVANTAGES: Auto#atic s&ste# 'ore secure LIMITATIONS: The ca# could be able to capture good i#ages. Data anal&sis should be accurate for secure usage THE DEVELOPMENT OF FRS: "n order to appreciate the comple2ity (and susceptibilities) of !T# we need to get a sense of all the comple2 tas3s that ma3e up a system and how small variations in the system or environment can impact on these tas3s. 4e will endeavor to 3eep the discussion on a conceptual level. However# from time to time# we will need to dig into some of the technical detail to highlight a relevant point. Facial recognition algorith ! -teps in the facial recognition process .1et us for the moment assume that we have a probe image with which to wor3. The facial recognition process normally has four interrelated phases or steps. The first step is face detection# the second is normalization# the third is feature e2traction# and the final cumulative step is face recognition. These steps depend on each other and often use similar techniques. They may also be described as separate components of a typical !-. 0evertheless# it is useful to 3eep them conceptually separate for the purposes of clarity. &ach of these steps poses very significant challenges to the successful operation of a !-. Detecting a "ace: *etecting a face in a probe image may be a

relatively simple tas3 for humans# but it is not or a computer. The computer has to decide which pi2els n the image is part of the face and which are not. Nor ali#ation: ,nce the face has been detected (separated from its bac3ground)# the face needs to be normalized. This means that the image must be standardized in terms of size# pose# illumination# etc.# relative to the images in the gallery or reference database. To normalize a probe image# the 3ey facial landmar3s must be located accurately. Feat$re e%traction an& recognition: ,nce the face image has been normalized# the feature e2traction and recognition of the face can ta3e place. "n feature e2traction# a mathematical representation called a biometric template or biometric reference is generated# which is stored in the database and will form the basis of any recognition tas3. acial recognition algorithms differ in the way they translate or transfer m a face image (represented at this point as grayscale pi2els) into a simplified mathematical representation (the 5features6) in order to perform the recognition tas3 (algorithms will be discussed below). "t is important for successful recognition that ma2imal information is retained in this transformation process so that the biometric template is sufficiently distinctive. Face recognition algorith ! The early wor3 in face recognition was based on the geometrical relationships between facial landmar3s as a means to capture and e2tract facial features. This method is obviously highly dependent on the detection of these landmar3s (which may be very difficult is variations in illumination# especially shadows) as well as the stability of these relationships across pose variation. These problems were and still remain significant stumbling bloc3s for face detection and recognition. This wor3 was followed by a different approach in which the face was treated as a general pattern with the application of more general patter n recognition approaches# which are based on photometric characteristics of the image. These two starting

points7 geometry and the photometric approach are still the basic starting points for developers of facial recognition algorithms. To implement these approaches a huge variety of algorithms have been developed7 '( Princi)al Co )onent! Anal*!i! +PCA, The ('A technique converts each two dimensional image into a one dimensional vector. This vector is then decomposed into orthogonal (uncorrelated) principle components (3nown as eigen8faces)9in other words# the technique selects the features of the image (or face) which vary the most from the rest of the image. "n the process of decomposition# a large amount of data is discarded as not containing significant information since :;< of the total variance in the face is contained in =8>;< of the components. This means that the data needed to identify an individual is a fraction of the data presented in the image. &ach face image is represented as a weighted sum (feature vector) of the principle components (or eigen faces)# which are stored in a one dimensional array. &ach component (eigen face) represents only a certain feature of the face# which may or may not be present in the original image. A probe image is compared against a gallery image by measuring the distance between their respective feature vectors. or ('A to wor3 well the probe image must be similar to the gallery image in terms of size (or scale)# pose# and illumination. "t is generally true that ('A is reasonably sensitive to scale variation. -( LDA: Linear Di!cri inate Anal*!i! 1*A is a statistical approach based on the same statistical principles as ('A. 1*A classifies faces of un3nown individuals based on a set of training images of 3nown individuals. The technique finds the underlying vectors in the facial feature space (vectors) that would ma2imize the variance between individuals (or classes) and minimize the variance within a number of samples of the

same person (i.e.# within a class). ?. Ela!tic B$nch Gra)h Matching +EBGM) &.%$ relies on the concept that real face images have many nonlinear characteristics that are not addressed by the linear analysis methods such as ('A and 1*A9such as variations in illumination# pose# and e2pression. The &.%$ method places small bloc3s of numbers (called 5%abor filters6) over small areas of the image# multiplying and adding the bloc3s with the pi2el values to produce numbers (referred to as 5@ets6) at various locations on the image. These locations can then be ad@usted to accommodate minor variations. The success of %abor filters is in the fact NOTE: The !*!te ha! t.o le/el o" !ec$rit*: Fir!t the $!er enter! the )a!!.or& $!ing 0e*)a&( I" the )a!!.or& i! correct the "ace recognition inter"ace i! o)ene&( The $!er then chec0e& "or it! "ace recognition an& i" it al!o atche! then the !*!te 1&oor i! o)ene&( The alar .ill 2e acti/ate& i" the $!er i! .rong at an* !tage( A))lication !cenario! "or "acial recognition !*!te ! +FRS, Armed with this description of the core technical components of facial recognition and how they function together to form a system# these are few typical applications scenarios envisioned in the academic literature and promoted by systems developers and vendors. The e2amples we have selected are intended to reflect the wide8ranging needs !- might serve# as well as diverse scenarios in which it might function. "n the scenario that we have called 5the grand prize#6 an !- would pic3 out targeted individuals in a crowd. -uch are the hopes for !- serving purposes of law enforcement# national security# and counter terrorism. (otentially connected to

video surveillance systems (''T+) already monitoring outdoor public spaces li3e town centers# the systems would alert authorities to the presence of 3nown or suspected terrorists or criminals whose images are already enrolled in a systemAs gallery or could also be used for trac3ing down lost children or other missing persons. This is among the most ambitious application scenarios given the current state of technology -cenarios in which !- may be used for authentication or verification purposes include entry and egress to secured high8ris3 spaces# for e2ample military bases# border crossings# and nuclear power plants# as well as access to restricted resources# such as personal devices# computers# networ3s# ban3ing transactions# trading terminals# and medical records. "n these environments# not only is movement controlled# cooperation is structured by the way incentives are organized. AT)*")+,-: This is the #icrocontroller b& AT'E($ having the architecture si#ilar to 6*7- #icrocontroller. It has flash #e#or& and EEP05' #e#or& of the si:e -)% and )% respectivel&. It has inbuilt A0T chip inside$ hence we can develop the serial co##unication easil&. ;or progra##ing the #icrocontroller we have used the co#piler 'i%ro<c developed b& 'i%ro=electroni%a co#pan&. It is based on c based language and #an& inbuilt hardware libraries$ which provides ver& eas& wa& for the user to develop the progra#s. "urner used is also fro# sa#e co#pan&. 3SB to 3ART Con/erter There are several types of )-. to )A!T converters are available. Anyone can be used without any problem. The tas3 of these

modules is to convert the data stream of )-. to )A!T compatible. The driver must be installed in the computer in order to use it so that a virtual ',$ port gets created inside the computer. MOTOR DRIVER Here we used ()12D to drive the #otors$ whatever signals it receives fro# the #icrocontroller on the basis of that it will drive the #otors. An H./ri01& is an electronic circuit which enables a voltage to be applied across a load in either direction. These circuits are often used in robotics and other applications to allow D3 #otors to run forwards and bac%wards. H=bridges are available as integrated circuits$ or can be built fro# discrete co#ponents

MATLAB: $AT1A. -tands for $atri2 1aboratory ."t is the most commonly and widely used -oftware platform by math 4or3s for comple2 mathematical computations. "t ma3es computation very simple and easy for users and allows the user to concentrate on solving the problem rather than wasting most of the time focusing on the mathematical comple2ities. MI4RO5 C

The software includes the compiler for programming the controller that is $"B!, 8' 'ompiler.

MI4RO C COMPILER
Menu Bar Fast Icons

The $"B!, ' for C;=> Project Explorer 'ompiler is a powerful Controller Settings feature8rich development library tool for AtmelDs C;=> microcontrollers. "t is Code Editor Message designed to provide the area user with the easiest 6 La2!G$r$ Technologie! P/t( Lt&( ...(la2!g$r$(co possible solution for developing applications for embedded systems without compromising on performance. "tAs highly advanced integrated development environment ("*&)# broad set of library routines# ready8to8run and comprehensive documentation should be more than enough to get anyone off to a great start when developing C;=> applications.