Demodulation by complex-valued wavelets for stochastic pattern recognition
read more
Citations
Biometric template security
Personal identification based on iris texture analysis
Efficient iris recognition by characterizing key local variations
Iris Segmentation Using Geodesic Active Contours
Local intensity variation analysis for iris recognition
References
High confidence visual recognition of persons by a test of statistical independence
Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters.
Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression
Two-dimensional spectral analysis of cortical receptive field profiles.
Related Papers (5)
Frequently Asked Questions (13)
Q2. How can the authors accept iris comparisons of poor quality?
The authors can accept matches of very poor quality, say up to 30% of the bits being wrong, and still make decisions about personal identity with very high confidence.
Q3. What is the spectral energy peak of the Gabor wavelet?
Its spectral energy peak is at orientation θ0 and spatial frequency ω0 as defined above, and so it serves to extract image structure in a particular band of the 2D Fourier spectrum.
Q4. What are the main characteristics of the wavelets that will be discussed here?
The particular family of 2D wavelets that will be discussed here are closed under dilation, translation, and rotation, and they also form a complete image basis, or frame.
Q5. How can the authors compute the False Match rate?
By calculating the area under the curve fitted to the observed distribution of Hamming Distances for different eyes (Fig. 7), the authors can compute the theoretical False Match rate as a function of the decision criterion employed.
Q6. What is the right-side distribution of hamming distances?
The left-side distribution of Hamming Distances seen in Fig. 9 is not stable, since it depends on the imaging conditions; therefore the Failure-to-Match rate is not a fixed property of these algorithms.
Q7. How many degrees of freedom are there between irises?
The mean Hamming Distance is 0.497 with standard deviation 0.031, indicating 259 degrees-of-freedom between genetically identical irises.
Q8. What is the significance of a test of statistical independence?
The failure of a test of statistical independence can thereby serve as a basis for recognizing patterns very reliably, provided they possess enough degrees-of-freedom.
Q9. What is the expected distribution of IrisCodes?
The solid curve fitted to the data is a binomial distribution with 249 degrees-of-freedom; this is the expected distribution from tossing a fair coin 249 times in a row, and tallying up the fraction of heads in each such run.
Q10. What is the way to exclude a photograph of someone else’s iris?
Other tests to exclude a photograph of somebody else’s iris involve tracking eyelid movements, or examining corneal reflections of infrared LEDs illuminated in random sequences.
Q11. What is the problem with the expansion coefficients of Gabor wavelets?
A complication arises from the fact that these wavelets are non-orthogonal (the inner product of any two of them is in general nonzero), and so the expansion coefficients required do not correspond simply to the inner product projections of the image onto the wavelets.
Q12. What is the significance of a False Match?
The practical importance of such high odds against a chance False Match is that it permits huge databases (even of “planetary” size) to be searched exhaustively, without accumulating significant probability of a False Match despite the large number of opportunities.
Q13. What is the expected standard deviation of the iris code?
(If every bit in an IrisCode were independent, then the distribution in Fig. 5 would be very much sharper,with an expected standard deviation of only √ pq/N = 0.011; thus the Hamming Distance interval between 0.49 and 0.51 would contain most of its area.)