An Automatic Algorithm for Evaluating the Precision of Iris Segmentation

Abstract

Recent developments in the field of nonideal iris recognition have shown that the presence of the degradations such as insufficient contrast, unbalanced illumination, out-offocus, motion blur, specular reflections, and partial area affect performance of iris recognition systems. Most iris recognition systems are designed to implement a number of processing steps with iris segmentation being one of the first steps. If segmentation is not performed at a certain precision, the error of segmentation will further propagate and will be amplified during the proceeding processing, encoding, and matching steps. This emphasizes a critical need in designing robust iris segmentation algorithms and together with it a need of automatic algorithms evaluating the precision (accuracy) of iris segmentation. Automatic algorithm evaluating the precision of segmentation plays important role for two reasons: (1) it can be placed into a feedback loop to enforce another run of segmentation algorithm that may include more sophisticated steps for high precision segmentation and (2) the outcome of this evaluation can be treated as a quality factor and thus can be used to design a quality driven adaptive iris recognition system.This work analyzes effects of degradations on iris segmentation and proposes and tests an automatic algorithm evaluating the precision of iris segmentation.

Eye detection by complex filtering for periocular recognition

“…This is to ensure that it captures the different size of the eyes present in the databases due to small variations in the distance to the sensor. Detection accuracy is evaluated by the distance of the detected eye center with respect to the annotated pupil and sclera centers [27]. Distances are normalized by the radius of the annotated circles for size and dilation invariance, as shown in the inner sub-figure of Figure 5.…”

Quality factors affecting iris segmentation and matching

“…Segmentation accuracy is evaluated in terms of the maximum offset of the detected circle w.r.t. the annotated one [21]. The offset is normalized by the radius of Figure 7.…”

“…Also, the SIFT matcher is observed to be more resilient to segmentation inaccuracies. In this sense, errors in the segmentation may be hidden by the matcher, pointing out the importance of evaluating also the precision of iris segmentation, rather than focusing on recognition accuracy only [21].…”

“…Several quality factors can degrade iris images [12]. However, evaluation in the segmentation performance is quite limited [21], with most of the works focused on its impact in the recognition accuracy [12,17]. Here, we evaluate the impact of 8 quality measures in the performance of iris segmentation.…”

Robust Feature Extraction and Iris Recognition for Biometric Personal Identification

“…In the second stage Mumford-Shah function is used to detect exact boundaries. Authors of (Zuo et al,2008) explained robust automatic segmentation algorithm. One of the most important characteristics of iris localization system is its processing speed.…”