Segmentation-Level Fusion for Iris Recognition

Abstract

This paper investigates the potential of fusion at normalisation/segmentation level prior to feature extraction. While there are several biometric fusion methods at data/feature level, score level and rank/decision level combining raw biometric signals, scores, or ranks/decisions, this type of fusion is still in its infancy. However, the increasing demand to allow for more relaxed and less invasive recording conditions, especially for onthe-move iris recognition, suggests to further investigate fusion at this very low level. This paper focuses on the approach of multi-segmentation fusion for iris biometric systems investigating the benefit of combining the segmentation result of multiple normalisation algorithms, using four methods from two different public iris toolkits (USIT, OSIRIS) on the public CASIA and IITD iris datasets. Evaluations based on recognition accuracy and ground truth segmentation data indicate high sensitivity with regards to the type of errors made by segmentation algorithms.

Quality-based iris segmentation-level fusion

“…The type of fusion method (combination of boundary points for fitting routine vs. interpolating fitted boundaries) did not have a pronounced impact on accuracy. While in [4], for the employed data outliers were not an issue; they were rather critical in [5], where combinations of automated segmentation algorithms did not improve in all cases. Therefore, this work focuses on integrating quality prediction for more efficient fusion at segmentation-level.…”

“…Segmentation fusion can be grouped into approaches combining detected boundaries prior to any rubbersheet transformation [4,5] and after normalisation, where normalised texture is combined [18,19]. The latter requires multiple execution of the iris unwrapping and normalisation (slower), hiding potential segmentation errors and therefore making their elimination more complex (combination of texture).…”

“…For vendorneutral comparison, this form of fusion has certain advantages over more common multi-algorithm fusion, where each algorithm uses its own segmentation routine: it facilitates data exchange offering access to the normalised texture, increases usability of existing segmentation routines, and allows faster execution requiring only a single module *Correspondence: peter.wild@ait.ac.at 1 AIT Austrian Institute of Technology GmbH, 2444 Seibersdorf, Austria Full list of author information is available at the end of the article rather than entire processing chains. In [5], which is extended by this work, a fusion framework for the automated combination of segmentation algorithms is presented, but without taking segmentation quality into account. The reference method in [5] was shown to improve results in many cases, but no systematic improvement could be achieved.…”

“…In [5], which is extended by this work, a fusion framework for the automated combination of segmentation algorithms is presented, but without taking segmentation quality into account. The reference method in [5] was shown to improve results in many cases, but no systematic improvement could be achieved. A more efficient combination technique can be obtained when inaccurate information can be discarded from the fusion stage, which is the scope of work in this paper.…”

“…The contributions of this paper are as follows: (1) a generalised fusion framework for combining iris segmentation results extending [5] towards including qualitybased predictors of segmentation performance guiding the selection of contributing information (see Fig. 1); (2) a reference implementation based on neural networks and augmented model-based combination of segmentation evidence using iris mask post-processing (such that the only input needed is a segmentation mask file by each algorithm to be considered); and (3) an evaluation of proposed methods analysing pairwise combinations of algorithms with regard to two aspects: first, conformity with ground truth is inspected focusing on the question whether segmentation fusion concepts indeed improve ground truth accuracy in terms of E 1 and E 2 segmentation errors.…”