18-04-2011, 10:14 AM
Presented By
Swati G. Manikpure
[attachment=12267]
Introduction
What is Biometrics?
Why Biometrics is used?
How Biometrics is today?
Broad Classification
Why Iris Recognition?
The only INTERNAL organ EXTERNALLY visible
Stable for a life time
Eye injuries or operations cannot change the Iris pattern what so ever
Iris Recognition systems
The iris-scan process begins with a photograph. A specialized camera, typically very close to the subject, not more than three feet, uses an infrared imager to illuminate the eye and capture a very high-resolution photograph. This process takes 1 to 2 seconds.
Creating an Iris code
The picture of eye first is processed by software that localizes the inner and outer boundaries of the iris.
And it is encoded by image-processing technologies.
Iris recognition
In less than few seconds, even on a database of millions of records, the iris code template generated from a live image is compared to previously enrolled ones to see if it matches to any of them.
Example of iris recognition system
Typical iris system configuration
Typical iris system configuration for taking a picture
An iris recognition camera takes a black and white picture from 5 to 24 inches away.
The camera uses non-invasive, near-infrared illumination that is barely visible and very safe.
Techniques used
Iris Localization
Iris Normalization
Image Enhancement
Iris Localization
Purpose: to localize that portion of the acquired image that corresponds to an iris
In particular, it is necessary to localize that portion of the image derived from the border between the sclera and the iris and outside the pupil.
Desired characteristics of iris localization:
◦ Sensitive to a wide range of edge contrast
◦ Robust to irregular borders
◦ Capable of dealing with variable occlusions
The Daugman system fits the circular contours via gradient ascent on the parameters so as to maximize
Iris Normalization
The size of the pupil may change due to the variation of the illumination and the associated elastic deformations in the iris
Texture may interface with the results of pattern matching.
For the purpose of accurate texture analysis, it is necessary to compensate this deformation.
Iris Enhancement
Pattern Matching
• Bringing the recent iris pattern into alignment with a candidate data base entry.
• Evaluating the goodness of match between the newly acquired and data base representations.
• Deciding if the newly acquired data and the data base entry were derived from the same iris based on the goodness of match.
Comparison
Can we fool this technique?
present a high resolution picture of a person.. just wear a mask!
wear a specs or colored contact lens.. what if I have naturally dark black eyes ?
Pupil dilation or Disorders or diabetes or natural aging ?
Conclusion
Combines computer vision, pattern recognition , statistical inference, and optics
Purpose - real-time, high confidence recognition of a person’s identity
The iris technology is expanding into the most reliable biometrics feature---data rich of physical structure, accurate, secure, stable, and safe
The only disadvantage was the designing and manufacturing cost