Search Engine

Custom Search

Monday, July 14, 2008



Challenging time require new security imperatives to ensure that right level of security exist in all the right places. Now more than ever their is a vide range of interest in identifying and verifying the identity of individual and protecting national assets.
An identity authentification system is required to provide for homeland security including applications for improving airport security, strengthen our national borders, in travel documents, etc. their are many needs for biometric beyond homeland security and are already benefiting from this technology. Biometric based authentification applications include data protection, remote access to resources, transaction security and web security. Utilized alone or integrated with other technologies such as smart card, encryption keys and digital signatures, biometrics are set to pervade nearly all aspects of the economy in our daily lives.

"The automated use of physiological or behavioral characteristics to determine or verify identity."
To elaborate on this definition, physiological biometrics is based on measurements and data derived from direct measurement of a part of the human body. Fingerprint, iris scan, retina scan, hand geometry and facial recognition are the leading physiological biometrics.

Physiological biometric technologies are similarly informed by user behavior, such as the manner in which a user presents a finger or looks at a camera. However, the physiological distinction is a helpful tool in understanding how biometrics work and how they can be applied in the real world.

The integrated biometric hardware and software used to conduct biometric identification or verification is called a biometric system.

Present capture create reference store match
Biometric template
Verification compare
Present capture create match non match
Biometric template

Biometric decision-making is frequently misunderstood. For the vast majority of technologies and systems, there is no such thing as 100% match, though the system can provide a very high degree of certainty. The biometric decision making process is comprised of various components as indicated below.

The comparison of biometric templates to determine their degree of similarity or correlation. A match attempt results in a score that in most systems is compared against a threshold. If the score exceeds the threshold the result is a match, if the score falls below the threshold the result is a non-match.
Biometric comparison takes place when appropriate algorithm process biometric templates. This algorithm manipulates the data contained in the templates in order to make valid comparisons accounting for variations in placement, background noise, etc. Without the vendor algorithm, there is no way to compare biometric templates-comparing bits which comprise the templates does not indicate if they came from the same user. The vendor as a precondition of comparison must process the bit.
The matching process involves the comparison the matched template, created upon sample submission, with the reference templates already on file. In 1:1 verification system there is generally a single match template matched against a reference template. In 1:N identification system, the single matched template can be matched against dozens, thousands, even millions of reference templates.

A predefined number count often controlled by a biometric administrator, which establishes a degree of correlation necessary for a comparison to be deemed a match. If the score resulting from template comparison exceeds the threshold, the templates are a match.
The leading biometric technologies are,
Facial recognition
Voice recognition
Iris recognition
Hand recognition
Signature scan

Iris recognition has many advantages over the other form of biometric identification system.

Iris recognition is the most accurate form of identification known to man, more accurate than DNA matching. Due to the process of chaotic morph genesis, every iris is unique to the degree that probability of two irises being identical is 1 in 10 to the power of 78. Additionally our iris recognition system captures over 240 degree of freedom. This is more data than collected by most hand, face and voice recognition systems combined.
Other system has the potential to be fooled by replicas and duplicates. Our iris cameras has built in countermeasures to ensure that it is a live eye being presented meaning that high quality 3-D or 2-D reproduction pose no threat to iris recognition system.

Our IRS is capable of making a match from a database of over 1 million records in less than a second. Conversely fingerprint, hand, voice system are challenged by large database. Not only the time taken to register a match increase, but also the accuracy of the system falls unlike iris recognition system.

Iris recognition identifies people rather than verifying their identity.
a) Verification asks, is this person who they say they are? This is one to one matching which means person must first suggest their identity through a password, card or name and then the system seeks to determine whether or not there is a match or not.
b) Identification asks, who this person is? This is one to many matching that a person is not required to carry anything or any information.

The iris image remains stable from the age of 10 month till death. This means that an iris image needs only to be capturing once and need not to be updated. Other biometric measure change over time, hand & finger grow, our voice change, our skin degrades and other biometric are subject to change according to age and climate.

User wearing gloves, protective wear; glasses, safety goggles and even contact lenses can operate IRS. No contact is required with touch pad or screen meaning that IRS is ideal in condition where hygiene is at premium. It is also important to note that IRS is completely different from retinal scanning. No bright light or laser is used only a digital photo is taken.

Capture digital image of the iris.
Prepare process image for analysis.
Use iris code template for authentication.

During the verification or identification process error can occur. There are two critical measurement factors, which indicate the level of accuracy, or reliability, of any given, biometric. They are false reject rate (FRR) and false accept rate (FAR).

When a biometric measurement from a live subject is compared to that subject-enrolled template and the system fails to match the two, a false reject event occurs. The theoretical probability of this happening, or the actual frequency with which it occur is known as the FALSE REJECT RATE (FRR).

There is always a probability that the measurement from a live subject will be sufficiently to a template from another, different, person that a much will be declared. This second type of error is called a "false accept" event and the associated probability is called the FALSE ACCEPT RATE (FAR).

IRS technology is the ideal solution in any environment whether you have one door to protect or one hundred. The unique processing capabilities of the Know-how server mean that IRS is the only technology capable of operating efficiently in situations where thousands or even millions of persons must be enrolled.

One of the major challenges of automatic IRS is to capture a high quality image of iris while remaining non-invasive to the human operator. Given that the iris is relatively small (1cm in diameter), dark object and that human operator are very sensitive about their eyes, this matter requires careful engineering.
The following points should be considered;
The images should be well framed.
Noise in the acquired image should be eliminated as much as possible.
The human eye should be 9 cm far away from the camera as shown below. The halogen lamp is in a fixed position to get the same illumination effect overt all the images, thus excluding the illuminate part of the iris while getting the iris code is easier, to acquire a more clear image through a camera and minimize the effect of reflected light caused surrounding illumination.
After edge detection step we have two images of the same iris and the coordinates of the center and the location of the inner and the outer boundary. Our motive is to match these two images.
One more point of attention is that the position of the inner boundary i.e., boundary of the pupil, it changes with the intensity of the illumination source.
Once we have two boundaries we start moving from outer boundary toward the inner boundary, and simultaneously match the rings one-by-one.
Matching of the rings means we take a pixel on a ring in the acquired image and compare the hamming distance of the two points or the pixels i.e., we match its intensity (value) with the intensity of the same corresponding pixel in the stored image. If the value is same then we go for next pixel in clockwise or counter clockwise direction depending on the direction specified in the code.

The matching output depends upon the threshold as set by the design engineer and can be viewed as and when required which increases flexibility of the system.

If the result of match is above 80% then the result is match otherwise non-match. Since there is no 100% match in biometric system.

We have observed the following books & web sites for collecting the
different information related to the topic IRIS RECOGNITION SYSTEM .
1. The new system’s in SECURITY.
2. Industrial Electronics. (Magazine)


No comments: