Improving Iris Recognition Performance Using Segmentation, Quality Enhancement, Match Score Fusion, and Indexing

This paper proposes algorithms for iris segmentation, quality enhancement, match score fusion, and indexing to improve both the accuracy and the speed of iris recognition. A curve evolution approach is proposed to effectively segment a nonideal iris image using the modified Mumford-Shah functional. Different enhancement algorithms are concurrently applied on the segmented iris image to produce multiple enhanced versions of the iris image. A support-vector-machine-based learning algorithm selects locally enhanced regions from each globally enhanced image and combines these good-quality regions to create a single high-quality iris image. Two distinct features are extracted from the high-quality iris image. The global textural feature is extracted using the 1-D log polar Gabor transform, and the local topological feature is extracted using Euler numbers. An intelligent fusion algorithm combines the textural and topological matching scores to further improve the iris recognition performance and reduce the false rejection rate, whereas an indexing algorithm enables fast and accurate iris identification. The verification and identification performance of the proposed algorithms is validated and compared with other algorithms using the CASIA Version 3, ICE 2005, and UBIRIS iris databases.

I. Introduction

Current iris recognition systems claim to perform with very high accuracy. However, these iris images are captured in a controlled environment to ensure high quality. Daugman [1]–[4] proposed an iris recognition system representing an iris as a mathematical function. Wildes [5], Boles and Boashash [6], and several other researchers proposed different recognition algorithms [7]–[32]. With a sophisticated iris capture setup, users are required to look into the camera from a fixed distance, and the image is captured. Iris images captured in an uncontrolled environment produce nonideal iris images with varying image quality. If the eyes are not properly opened, certain regions of the iris cannot be captured due to occlusion, which further affects the process of segmentation and, consequently, the recognition performance. Images may also suffer from motion blur, camera diffusion, presence of eyelids and eyelashes, head rotation, gaze direction, camera angle, reflections, contrast, luminosity, and problems due to contraction and dilation. Fig. 1 from the UBIRIS database [26], [27] shows images with some of the aforementioned problems. These artifacts in iris images increase the false rejection rate (FRR), thus decreasing the performance of the recognition system. Experimental results from the Iris Challenge Evaluation (ICE) 2005 and ICE 2006 [30], [31] also show that most of the recognition algorithms have a high FRR. Table I compares existing iris recognition algorithms with respect to image quality, segmentation, enhancement, feature extraction, and matching techniques. A detailed literature survey of iris recognition algorithms can be found in [28]. Fig. 1.

Iris images representing the challenges of iris recognition. (a) Iris texture occluded by eyelids and eyelashes. (b) Iris images of an individual with a different gaze direction. (c) Iris images of an individual showing the effects of contraction and dilation. (d) Iris images of the same individual at different instances: the first image is of good quality; the second image has motion blurriness, and limited information is present. (e) Images of an individual showing the effect of the natural luminosity factor [26].

Table I Comparison of Existing Iris Recognition Algorithms

Research paper	Quality assessment	Iris segmentation	Image enhancement	Feature extraction and matching	Additional comments
Daugman [1]-[4]	Frequency approach	Integro-differential operator	-	Neural network + 2D Gabor transform + Hamming distance	First iris recognition algorithm
Wildes [5]	Using high contrast edges	Image intensity gradient and Hough transform	-	Laplacian of Gaussian filters + normalized correlation	-
Boles and Boashash [6]	-	Edge detection	-	Wavelet transform zero crossing + dissimilarity function	Does not perform for non-ideal iris images
Ma et al. [12]	Frequency based SVM classification	Gray-level information and canny edge detection	Background subtraction	Multichannel spatial filter + fisher-linear discriminant classification	Does not work with occluded images
Ma et al. [13]	-	Gray-level information and canny edge detection	Background subtraction	ID iris signal operated on Dyadic wavelet + similarity function	Local features are used for recognition
Avila and Reillo [16]	-	Intensity based detection	-	Gabor filter and multiscale zero-crossing + Euclidean and Hamming distance	Does not unwrap the iris image
Vatsa et al. [18]		Intensity based detection		ID log polar Gabor and Euler number + Hamming distance and LI distance	Rule based decision strategy is used to improve accuracy
Monro et al. [24]	-	Heuristic gray-level edge feature	Background subtraction	ID DCT + Hamming distance	Fast feature extraction and matching
Poursaberi and Araabi [25]	-	Morphological operators and thresholds	Wiener 2D filter	Daubechies 2 wavelet + Hamming distance and harmonic mean	-
Daugman [32]		Active contours and generalized coordinates	-	Iris Code	Gaze deviation correction, second rank in ICE 2006 and low time complexity