Accurate Iris Localization Using Edge Map Generation and Adaptive Circular Hough Transform for Less Constrained Iris Images

Abstract

This paper proposes an accurate iris localization algorithm for the iris images acquired under near infrared (NIR) illuminations and having noise due to eyelids, eyelashes, lighting reflections, non-uniform illumination, eyeglasses and eyebrow hair etc. The two main contributions in the paper are an edge map generation technique for pupil boundary detection and an adaptive circular Hough transform (CHT) algorithm for limbic boundary detection, which not only make the iris localization more accurate but faster also. The edge map for pupil boundary detection is generated on intersection (logical AND) of two binary edge maps obtained using thresholding, morphological operations and Sobel edge detection, which results in minimal false edges caused by the noise. The adaptive CHT algorithm for limbic boundary detection searches for a set of two arcs in an image instead of a full circle that counters iris-occlusions by the eyelids and eyelashes. The proposed CHT and adaptive CHT implementations for pupil and limbic boundary detection respectively use a two-dimensional accumulator array that reduces memory requirements. The proposed algorithm gives the accuracies of 99.7% and 99.38% for the challenging CASIA-Iris-Thousand (version 4.0) and CASIAIris-Lamp (version 3.0) databases respectively. The average time cost per image is 905 msec. The proposed algorithm is compared with the previous work and shows better results.

Pupil Detection Based on Color Difference and Circular Hough Transfor

“…Hough Transform used for detecting the center of the pupil of an iris, the accuracy of this method reaches to 92%. Vineet Kumar.et al [16] presented a method for iris localization, the proposed algorithm for iris localization divided into two phases which are pupil boundary detection and limbic boundary detection, they used edge map and circural hough transform for pupil boundary detection, the accuracy of this method reach to 99.7% for CASIA-Iris-Thousand (version 4.0) and 99.38% for CASIAIris-Lamp (version 3.0) databases. Teddy et al [17] presented a method for secure smart phone using iris verification, they used wavelet packet and hamming distance for recognition, the accuracy of this method reach to 100% identification rate.…”

Eyelids, eyelashes detection algorithm and houghtransform method for noise removal in iris recognition

“…To detect the pupil and boundaries in the iris image, we can use Hough transform method. Hough transforms method works on the basis of parametric equations [19][20]. Hough Transform method can find geometric shapes such as circles, or lines within an image [19].…”

Real-Time Fatigue Analysis of Driver through Iris Recognition

“…A circle might seem easy to represent using three parameters. The equation of a circle is r 2 = (x-a) 2 + (y-b) 2 and it has three parameters r, a and b where, r is the radius of circle, a and b are the centre in X and Y direction. The parameter space of a circle belongs to R 3 .…”

“…To address this, Mr.Venkatarama Phani Kumar [1] describes the Modular two-dimensional Principle Component Analysis in which, the image is partitioned into four four equal segments and then the Histogram equalization is applied to reduce the illumination impact due to the varing conditions. However the accuracy of Ires recognition in presence of the noise can be improved as described by Mr.Vineet Kumar et al [2], in their paper describe about the Iris localization using edge map genetration and adaptive circular Houghtransform for less constrained Iris images. Figure 1 shows the block diagram of the proposed system.…”