Iris Recognition Algorithm Using Effective Localized Fuzzy Features

Ankarao Ittadi, Manoj Jain

Abstract


The iris has a particularly interesting structure and provides abundant texture information. In this paper we propose a novel fuzzy
feature extraction method, which can provide robust and effective iris feature vectors. The IR System consists of automatic segmentation
algorithm which is based on Hough Transform which is able to localize the circular iris and pupil region. The extracted iris region is normalized
into a rectangular block with constant dimensions to account for dimensional inconsistencies. Image enhancement is done by using fuzzy
adaptive filter and is divided into non overlapping sub blocks to capture local iris characteristics. The fuzzy features of neighbourhood are
aggregated to yield a representative called cumulative response that represents the texture.


Keywords: Hough Transform, iris segmentation, Fuzzy adaptive filter, Fuzzy features.


Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v4i5.1662

Refbacks

  • There are currently no refbacks.




Copyright (c) 2016 International Journal of Advanced Research in Computer Science