Paper-2 an Intelligent Gate Controller Using a Personal Computer and Pattern Recognition Protocols

7/29/2019 Paper-2 an Intelligent Gate Controller Using a Personal Computer and Pattern Recognition Protocols

1/8

International Journal of Computational Intelligence and Information Security, J an-Feb 2013 Vol. 4, No. 1-2ISSN: 1837-7823

13

An Intelligent Gate Controller Using a Personal Computer and PatternRecognition Protocols

Philip A. ADEWUYI1, Muniru O. OKELOLA2, Adewale O. J EMILEHIN2

1 Mechatronics Engineering Department, Bells University of Technology, Ota, Nigeria

2Electronic and Electrical Engineering Department, Ladoke Akintola University of Technology, Ogbomoso,Nigeria

Abstract

The issue of security of lives and properties has become the number one concern of everybody aroundthe world. Governments as well as individuals invest heavily in security concerns. In the past years, it isobserved that many suicide attacks were carried out using vehicular tools. So, an intelligent gate controller

using a personal computer and pattern recognition is developed to prevent unwanted person(s) or elements(s)from gaining vehicular access into protected areas. Combination of software and hardware engineering is thebedrock of this work. Four Surveillance cameras are used to capture and recapture face of the driver as well asthe character recognition of the plate numbers of vehicles which serve as the input to the data bank system foronward comparison and processing by the computer system. The output of the computer system triggers theelectronic switch which controls the operations of the DC motor responsible for the opening and closing of thegate. At the centre of this work is the PIC16F84A which is programmed using mikroC Pro for PIC softwareto serve as the interface between the software elements and the hardware elements. This choice is made to makethe electronic switching operations very fast to prevent odd manipulations.

Keywords: Intelligent, Controller, Pattern recognition, Surveillance, DC motor, PIC

1. Introduction

Security consciousness at the entry points of any establishment is important. More so, employing theright security system at sensitive places is highly desirable [1]. In order to have the desired secured area, the useof a computer system and pattern recognition protocols are employed to set up a novel controller which operatesthe gate depending on the signals received from the processed input parameters such as the face recognition andthe plate numbers identification to give or deny entry access to a particular vehicle. The interrelationshipbetween the software and the hardware components are greatly utilized in this work. Looking critically at thiswork, it could be seen that the work combined two separate systems. That is, automatic gate control system anda surveillance system. It is rare to find a system in which the two systems are combined to form a single unit.Previous works were aimed at the control of a gate using either a remote control or a sensor at the entrance ofthe gate to detect the presence of any object that is trying to make a passage [2].

The hardware components involved in the physical control of the gate are; relays as electronicswitches, dc motor, microcontroller, power supply unit and a sensor. The feature that makes this work differfrom the conventional automatic gate control system is the software which utilizes the technology of patternrecognition in order to grant entry access. The face of the driver and the plate numbers of the vehicle beingdriven are captured using surveillance cameras. These parameters serve as the input data to the designedcontroller. There are various other projects that utilize surveillance cameras system. These existing systems areusually applied in traffic safety & monitoring, school & workplace security, crime fighting & prevention [3].

The rest of this work is divided into sections such as; automatic face recognition, principal componentanalysis, PCA algorithms, methodology, design and construction, results and discussion, and conclusion.


2/8


14

2. Automatic Face RecognitionAccording to the free dictionary, automatic face recognition is a biometric identification by scanning a

person's face and matching it against a library of known faces [4]. Developed in the 1960s, the first semi-automated system for face recognition required the administrator to locate features (such as eyes, ears, nose, andmouth) on the photographs before it calculated distances and ratios to a common reference point, which werethen compared to reference data.

In the 1970s, 21 specific subjective markers such as hair color and lip thickness were used to automaterecognition [5]. The problem with both of these early solutions was that the measurements and locations weremanually computed.

In 1987, the principle component analysis which is a standard linear algebra technique is also appliedto solving face recognition problem [6]. This is an improvement over the work carried out by Goldstein,Harmon, and Lesk in the 70s.

In 1991, Turk and Pentland discovered that while using the eigenfaces techniques, the residual errorcould be used to detect faces in images

a discovery that enabled reliable real-time automated face recognitionsystems [7]. This approach was affected by environmental factors. Nonetheless, it created significant interest infurthering development of automated face recognition technologies.

The technology first captured the publics

attention from the media reaction to a trial implementation at the January 2001 Super Bowl, which capturedsurveillance images and compared them to a database of digital mug shots. This demonstration initiated much-needed analysis on how to use the technology to support national needs while being considerate of the publicssocial and privacy concerns. Today, face recognition technology is being used to combat passport fraud, supportlaw enforcement, identify missing children, and minimize benefit/identity fraud.

2.1 Principal Components Analysis (PCA)

Principal component analysis (PCA) involves a mathematical procedure that transforms a number of(possibly) correlated variables into a (smaller) number of uncorrelated variables called principal components[8]. The mathematical technique used in PCA is called eigen analysis: we solve for the eigenvalues andeigenvectors of a square symmetric matrix with sums of squares and cross products. The eigenvector associated

with the largest eigenvalue has the same direction as the first principal component. The eigenvector associatedwith the second largest eigenvalue determines the direction of the second principal component. The sum of theeigenvalues equals the trace of the square matrix and the maximum number of eigenvectors equals the numberof rows (or columns) of this matrix. With PCA, the probe and gallery images must be the same size and mustfirst be normalized to line up the eyes and mouth of the subjects within the images. The PCA approach is thenused to reduce the dimension of the data by means of data compression basics

and reveals the most effective lowdimensional structure of facial patterns.

The primary advantage of this technique is that it can reduce the data needed to identify the individual

to 1/1000th

of the data presented.

2.2 PCA Algorithms

Given a symmetric matrix such as the covariance matrix, a householder reduction technique is used tosolve for the eigenvalue and followed by the QL algorithm with implicit shifts.

On the other hand, if data matrix A is the starting point , we do not have to form explicitly the matrix with sumsof squares and cross products, AA. Instead, we proceed by a numerically more stable method, and formthe singular value decomposition ofA,UV. The matrixV then contains the eigenvectors, and the squareddiagonal elements of contain the eigenvalues [8].

3. Methodology

The block and schematic representation of this work is detailed in figure 1 and 2 below. The block diagram

shows the image capturing at the point of entry via the surveillance camera. The necessary features areextracted and processed/compared with the information stored in the data base, processed by computer and


3/8


15

gives out logic instructions for the control of the gate system through the switching relays that dictate the bi-directional movement of the gate.

Figure 1: Block diagram of an intelligent gate controller system

Figure 2: The full schematic of an intelligent gate controller system

Feature

PROGRAMMINGSTAGE

Database

Matching

Identification

FeatureImage

Bi-directional

Controlled

Switching

Rela

Image

Logic

Control


4/8


16

Three software tools were used as highlighted hereunder:

1. LUXAND SDK (Face Recognition)2. OCR Tools (Character Recognition)3. Visual Studio. Net (2008)The face and character recognition software were combined in visual studio environment. The Luxandsoftware was used to analyze the face captured from the camera for faces while the OCR tools were usedtoconvert the plate number pictures into characters. Figure 3 below shows the interface of the setup.

Figure 3: The software interface.

3.1 Electronic Lock System

The design of an electronic lock system used for the opening and closing of the gate system is shown infigure 4 below:

Figure 4: The Block diagram of an electronic lock

The electronic lock system comprise of the power supply unit, the sensing unit, the door unit, the control unit,

and the computer interface unit.

Power Supply Unit

Door UnitControl UnitSensing Unit

Computer Interface


5/8


17

3.2 Power Supply Unit

The power supply unit comprises of the transformer TR1, full-wave bridge rectifier DR1, a filtercapacitor C1, a regulator U1 and a smoothing capacitor C2.

Figure 5: Power supply unit schematic

The transformer is a 500mA/12V step down transformer. This 12V AC supply is converted to 12V DCsupply and is regulated by a 3-terminal regulating power transistor. Smoothing of the resulting voltage iscarried out by the capacitor C1. The output of the regulator is connected to a smoothing capacitor C2 to preventthe effect of voltage spike from having effect on the functionality of the circuit.

3.3 Sensing Unit

The sensing unit for the system is incorporated into the software which means that the sensingoperation is automatically controlled.

3.4 The Control Unit

The major active component in the control unit is the PIC16F84A, which is a programmable interface controllershown in figure 6 below:

Figure 6: The Control Unit Schematic

TR1

DR1

C11000u

VI1

VO3

GND

2C2100u


6/8


18

The IC is programmed using the MicroBasic Integrated Development Environment (IDE) and the ICprog IDEsoftware. This software is used to program the IC in the basic language and then transferred into the memory ofthe PIC. The control unit gets the input from the entry unit, decodes them and then takes the following steps:

Generate the timing signal for the system Decodes the input On receiving signal from the sensing unit will activate the computer Receive Signal from the signal Control the gate opening and closingThe rate at which the IC executes the instruction in its memory will depend on the value of the crystal

oscillator connected to the PIC.The number of instructions executed by the microcontroller per second is calculated as given below:

Value of the crystal oscillator (XT) used =8MHzNumber of instructions/second =Value of XT oscillator

4

3.5 The Gate Unit

Figure 7: The Gate Unit Schematic

The gate unit consists of the electromechanical switch and the dc motor as shown in figure 7. The doorunit is made up of the rack and the pinion which helps in moving the door mechanism. The electromechanicalswitch (relay) is responsible for control of the motor to the desired direction.

4. Results and Discussion

Having programmed the microcontroller using the mikroBasic IDE interface, the hexadecimalrepresentation of the code is transferred into the memory of the PIC through a linker as displayed below infigure 8 and 9.


7/8


19

Figure 8: The MicroBasic IDE interface

Figure 9: The PIC Program IDE interface


8/8


20

4.1 Discussion

Once the system is powered on, the PIC will resume continuous checking through the surveillancecamera used as sensors. Immediately the system identifies a vehicle, the control unit sends a signal to capturethe face and the plate number of the incoming or outgoing vehicles. If the vehicle is coming in, the system only

captures the face of the driver and plate number and does comparison with what is stored in the data bank. Thegate opens or remains closed as to the authenticity of the input data. For areas where visitors vehicle areallowed, at the entry point, the system only captures the face of the driver and the plate number then opens thegate. At the exit point, the system does the capturing again and compares the data with what it captured at theentry point. If the images or patterns match the exit gate opens. Otherwise, it remains closed.

5. Conclusions

The innovative power of soft computing when combined with suitable applications should be wellutilized to bring about a safe environment for all to live in. As could be seen in this work, pattern recognitionprotocols, if well applied, play a key role in security issues. Precious lives could be saved and properties

protected from destruction coming from intruders. An intelligent controller of this nature is therefore a faithfulservant that could be employed to solving many security lapses that are usually associated with the vehicularpoint of entry or exit. This could also be applied to other areas, such as auditorium protection, malls protection,schools and many other private and public infrastructures.

Future research could concentrate on the use of mobile devices to achieve the remote control andmonitoring of the entry points.

References

[1] Robles R. J. and Kim T., (2010), Applications, Systems and Methods in Smart Home Technology: AReview, International Journal of Advanced Science and Technology, Vol. 15, pp 37 47.

[2] Shoewu O. and Baruwa O. T., (2006), Design of a Microprocessor Based Automatic Gate, Pacific

Journal of Science and Technology, 7(1): 31 44.[3] Onut V., Aldridge D., Mindel M., and Perelgut S., (2010), Smart surveillance system applications,

CASCON 10 Proceedings of the 2010 Conference of the Center for Advanced studies onCollaborative Research, pp. 430 432.

[4] Free dictionary.www.thefreedictionary.com/automatic +face +recognition. Article retrieved on the15th January, 2013.

[5] Goldstein A.J , Harmon L.D, and Lesk A.B., (1971), Identification of Human Faces, Proc. IEEE,Vol. 59, No. 5, 748-760.

[6] Sirovich L. and Kirby M., (1987), A Low-Dimensional Procedure for the Characterization of HumanFaces, J. Optical Soc. Am. A, Vol. 4, No.3, 519-524.

[7] Turk M.A and Pentland A.P., (1991), Face Recognition Using Eigenfaces, Proc. IEEE, 586-591.[8] Principal component analysis. An article by djmw(May 10, 2012) retrieved from

www.fon.hum.uva.nl/praat/manual/Principal_component_analysis.html
http://www.thefreedictionary.com/automatichttp://www.thefreedictionary.com/automatichttp://www.thefreedictionary.com/automatic

Paper-2 an Intelligent Gate Controller Using a Personal Computer and Pattern Recognition Protocols

Documents

Transcript of Paper-2 an Intelligent Gate Controller Using a Personal Computer and Pattern Recognition Protocols