Iris Recognition: An Emerging Biometric Technology

Moving Average Filter Iris Recognition

Download now Matlab source code
Requirements: Matlab, Matlab Image Processing Toolbox.

A moving average filter averages a number of input samples and produce a single output sample. This averaging action removes the high frequency components present in the signal. Moving average filters are normally used as low pass filters. In recursive filtering algorithm, previous output samples also are taken for averaging. This is the reason why it's impulse response extends to infinity. We have developed a low computational approach for iris recognition based on 1D moving average filter. Simple averaging is used to reduce the effects of noise and a significative improvement in computational efficiency can be achieved if we perform the calculation of the mean in a recursive fashion.

This code uses an optimized version of Libor Masek's routines for iris segmentation available here.

Libor Masek, Peter Kovesi. MATLAB Source Code for a Biometric Identification System Based on Iris Patterns. The School of Computer Science and Software Engineering, The University of Western Australia, 2003.

Index Terms: Matlab, source, code, iris, recognition, moving, average, filter, low, computational.

Release 1.0 Date 2008.11.08
Major features:

• Iris recognition based on moving average filter
• Matching module
• Easy and intuitive GUI
• Low computational algorithm
• Demo code (protected P-files) available for performance evaluation