Abstract:.

In India we have I cards as the identification proof and we often see security guards in airports and high security region checking the individuals about their identification.

But for highly populated countries like India it is almost impossible to check every individual at very highly crowded and rushing areas like railway stations. So, we are in a great need to set up a unique security system that could put an eye to every individual and report accordingly to the administrator within moment.

Introduction

A RFID receiver receives the unique identification signal from the corresponding tags but this limits the rfid technology to totally depend on the particular rfid tags which are along with the objects, which sends the information about that object. If somehow the tag is being misplaced or not at its correct place it would convey a false message about that object.

Any how solving above mentioned constraint of rfid technology can give strong results to build our own security system with the help of some recognition technology, where identification is very much required such in places like bank, railway stations or other crowdedly and rushing areas.

Rfid URL contain the information about objects, if somehow we are able to identify the property of object physically,  we can check whether the particular rfid tags are along with their corresponding objects or not. And then we will able to get the correct information about those objects.

We know every human has a unique biometric configuration which can be used to identify humans uniquely               

Face recognition is the available technology which is very much efficient to recognize face within a moment of seconds.

Using above technology (RFID & Face Recognition) we will be able to identify the individuals.

  Working princlple

 Presented technology collects the biometric data of the individual and prepares a database of itself. On the other hand as a rfid tag come within the scanning antenna it gets activated and sends the url address corresponding to the tag. This url address contains the detailed information about the object which are already present within the host system. As soon as host gets both database, they matches them and check out for the truthfulness of the data. For the wrong matches it just flashes error signal and we hence can restrict them.

Illustration:-

Consider a room as 3D co-ordinate system, with above defined security system, where a transceiver with a decoder is place at the origin. Suppose four people basant ,pratool , mayank and amit enter in a room having their own rfid tags .

As they all enters in the room . Simultaneously their data corresponding  to their url address are collected and stored in the database of the administrator computer.

Sl.no	Tag id	Name	Age	address	designation	nationality	Biometric information
1	22a351	Amit	18	ranchi	manager	indian	=
2	22g432	Basant	21	Begusarai	director	indian
3	22t654	Mayank	35	Ranchi	CEO	nepali
4	22y543	Pratool	21	Kheraiya	Manging director	american

And another database is prepared by administrator computer through pictures obtained by the camera palced as follows:

 

Sl no.	Tag id	Biometric info
1	22a351
2	22g432
3	22t654
4	22y543

 

Here in both database tag id is considered as a primary key. Both databases are compared using the tag id and accordingly results are given out. As we get a +ve results matches. It will give green signals to the intruders.

 

 

Technology involved:

RFID acronym of Radio Frequency IDentification. A radio frequency identification system has three parts:

·         A scanning antenna.

·         A transceiver with a decoder to interpret the data.

·         A transponder – the RFID tag – that has been programmed with information. This chip typically is capable of carrying 2, 000 bytes of data. And are generally passive and gets activated by the radio signals by the scanning antenna

                                        

·         The scanning antenna puts out radio frequency signals in a certain range. The radio frequency does two things:

 

·         It provide a means of communicating with transponder (the RFID tag) and

 

 

·         It provides the RFID tag with the energy to communicate (in case of passive RFID tag

 

3D face recognition :  This technology  is for the identification of a person through the biometical information such as by capturing an image of  the face in visible spectrum using an optical camera or by the using  infrared patterns of facial heat emmision , or through  finger prints , skin texture etc.

This technique uses 3-D sensors to capture information about the shape of a face. This information is then used to identify distinctive features on the surface of a face, such as the contour of the eye sockets, nose, and chin. One of the main advantages of 3-D facial recognition is that it is not affected by changes in lighting like other techniques. It can also identify a face from a range of viewing angles, including a profile view.

                                

 

To illustrate the minute expression of face is mainly illustrated through eigenface algorithm.

Eigenface algorithm

This algorithm mainly works on principal of component analysis (PCA). With the help of this principle we calculate the eigen vectors of the eigen pictures that stored in our database then after we match these eigen vectors with the pictures which are instantly obtained from the camera. The matching technique is totally based on eigen vectors. Every eigen images has some egien vectors. For instance, if we are working with a 100 x 100 image, then we will obtain 10,000 eigenvectors.    

For performing the PCA we need to calculate the covariance matrix involve between the eigen values and eigen vectors related with corresponding eigen faces.

Mathematically saying,

Let T be the matrix of preprocessed training examples, where each row contains one mean-subtracted image. The covariance matrix can then be computed as S = T^T T and the eigenvector decomposition of S is given by

(where λ is an eigen constant )

However T^TT is a large matrix, and if instead we take the eigenvalue decomposition of

Then we notice that by pre-multiplying both sides of the equation with T^T, we obtain

 

Meaning that, if u_i is an eigenvector of TT^T, then v_i=T^Tu_i is an eigenvector of S. If we have a training set of 300 images of 100 x 100 pixels, the matrix TT^T is a 300 x 300 matrix, which is much more manageable than the 10000 x 10000 covariance matrix.

Conclusion:

Using this technology we can build our own security system which will not only able to restrict the anti-social elements from our socialized society but will be also able to track down their location in the specified rfid field. This technology will be also open the new area of research  where  identification is required such as in banks ,auto ticketing.

References:

1.       RFID by steven Shepard, published by Mcgraw-Hill professional,2005

2.       ‘Face recognition ‘by smith, Kelly, a document retrived by NSTC subcommittee on biometrics on 4/6/2008. (www.biometrics.gov)

3.       wikipedia, the encyclopedia

 

    Author:

1 Basant