Robust Iris Recognition Based on Statistical Properties of Walsh Hadamard Transform Domain

Free registration required

Executive Summary

In this paper, a new approach of iris image feature extraction technique based on the statistical properties of Walsh Hadamard Transform (WHT) domain is proposed. A Canny Edge Detection followed by Hough Transform is used to detect the iris boundaries in the digital image of an eye. The segmented and normalized iris region is divided into 8x8 non-overlapping blocks and WHT is applied to each block. Unique iris features are obtained by computing Mean Value of Energy (MVE) and Mean value of Standard Deviations (MSD) of WHT coefficients. The energy-compaction characteristics of WHT are used to capture iris texture variations.

  • Format: PDF
  • Size: 738.95 KB