Detecting Iris Lacunae Based on Gaussian Filter

Abstract

Lacunae is a typical sign of iris, and the detection of lacunae is of great importance in automatic iris diagnosis. In this paper, we first introduce the lacunae detection in iris images. Although current literature has a variety of edge detection algorithms, they do not always lead to acceptable results in extracting various features in an image. Lacunae usually have poor local contrast and the application of existing edge detection algorithms yield results which are not satisfactory. Thus, we proposed a lacunae detecting approach based on Gaussian filters, which is robust to noise. When the Gaussian filter in the vertical orientation is implemented to normalized iris image, the time complexity of this approach is reduced considerably. Experimental results show the validity of this approach.