Heinz Hofbauer

A Ground Truth for Iris Segmentation

Classical iris biometric systems assume ideal environmental conditions and cooperative users for image acquisition. When conditions are less ideal or users are uncooperative or unaware of their biometrics being taken the image acquisition quality suffers. This makes it harder for iris localization and segmentation algorithms to properly segment the acquired image into iris and non-iris parts. Segmentation is a critical part in iris recognition systems, since errors in this initial stage are propagated to subsequent processing stages. Therefore, the performance of iris segmentation algorithms is paramount to the performance of the overall system. In order to properly evaluate and develop iris segmentation algorithm, especially under difficult conditions like off angle and significant occlusions or bad lighting, it is beneficial to directly assess the segmentation algorithm. Currently, when evaluating the performance of iris segmentation algorithms this is mostly done by utilizing the recognition rate, and consequently the overall performance of the biometric system. In order to streamline the development and assessment of iris segmentation algorithms with the dependence on the whole biometric system we have generated a iris segmentation ground truth database. We will show a method for evaluating iris segmentation performance base on this ground truth database and give examples of how to identify problematic cases in order to further analyse the segmentation algorithms.

An effective and efficient visual quality index based on local edge gradients

The structural similarity index measure is a well known and widely used full reference visual quality index. In this paper we introduce a new full reference visual quality index based on local edges and edge gradients in the wavelet domain. The proposed metric corresponds better to human judgement and is more efficient, in terms of computational complexity, than the structural similarity index measure. Furthermore, the proposed metric is more efficient than other state of the art metrics and surpasses them for certain visual impairment classes.

Transparent encryption for HEVC using bit-stream-based selective coefficient sign encryption

We propose a selective encryption scheme for HEVC which allows for transparent encryption in a wide range of quantization parameters. Our approach focusses on the AC coefficient signs, since they can be altered directly in the bit stream without entropy reencoding. This allows for fast encryption and decryption while retaining full format-compliance and length-preservation. Furthermore, we show our approachs applicability for a number of use cases by evaluating the quality degradation and robustness against attacks.

Iris Recognition in Image Domain: Quality-Metric Based Comparators

Traditional iris recognition is based on computing efficiently coded representations of discriminative features of the human iris and employing Hamming Distance (HD) as fast and simple metric for biometric comparison in feature space. However, the International Organization for Standardization (ISO) specifies iris biometric data to be recorded and stored in (raw) image form (ISO/IEC FDIS 19794-6), rather than in extracted templates (e.g. iris-codes) achieving more interoperability as well as vendor neutrality. In this paper we propose the application of quality-metric based comparators operating directly on iris textures, i.e. without transformation into feature space. For this task, the Structural Similarity Index measure (SSIM), Local Edge Gradients metric (LEG), Natural Image Contour Evaluation (NICE), Edge Similarity Score (ESS) and Peak Signal to Noise ratio (PSNR) is evaluated. Obtained results on the CASIA-v3 iris database confirm the applicability of this type of iris comparison technique.

Selective encryption of the MC EZBC bitstream for DRM scenarios

Universal Multimedia Access (UMA) calls for solutions where content is created once and subsequently adapted to given requirements. With regard to UMA and scalability, which is required often due to a wide variety of end clients, the best suited codecs are wavelet based (like the MC-EZBC) due to their inherent high number of scaling options. However, we do not only want to adapt the content to given requirements but we want to do so in a secure way. Through DRM we can ensure that the actual content is safe and copyright is observed. However, traditional encryption removes the option of scalability in the encrypted domain which is opposed to what we want to achieve for UMA. The solution is selective encryption where only a part of the content is encrypted, enough to ensure safety but at the same time little enough to keep scalability intact. Towards this goal we discuss various methods of applying encryption to the bitstream produced by the MC-EZBC in order to keep scalability intact in the encrypted domain while also keeping security intact with regard to various DRM scenarios.

Identifying deficits of visual security metrics for images

Visual security metrics are deterministic measures with the (claimed) ability to assess whether an encryption method for visual data does achieve its defined goal. These metrics are usually developed together with a particular encryption method in order to provide an evaluation of said method based on its visual output. However, visual security metrics themselves are rarely evaluated and the claim to perform as a visual security metric is not tied to the specific encryption method for which they were developed. In this paper, we introduce a methodology for assessing the performance of security metrics based on common media encryption scenarios. We systematically evaluate visual security metrics proposed in the literature, along with conventional image metrics which are frequently used for the same task. We show that they are generally not suitable to perform their claimed task. HighlightsIntroduction of a formal method to evaluate security metrics.An evaluation of state-of-the-art image and security metrics.Currently there are not security metrics without deficits.

Design Decisions for an Iris Recognition SDK

Open-source software development kits are vital to (iris) biometric research in order to achieve comparability and reproducibility of research results. In addition, for further advances in the field of iris biometrics the community needs to be provided with state-of-the-art reference systems, which serve as adequate starting point for new research. This chapter provides a summary of relevant design decisions for software modules constituting an iris recognition system. The proposal of general criteria and adequate concepts is complemented by a detailed description of how according design decisions are implemented in the University of Salzburg Iris Toolkit, an open-source iris recognition software which contains diverse algorithms for iris segmentation, feature extraction, and comparison. Building upon a file-based processing chain, the provided open-source software is designed to support rapid prototyping as well as integration in existing frameworks achieving enhanced usability and extensibility. In order to underline the competitiveness of the presented iris recognition software, experimental evaluations of segmentation and feature extraction algorithms are carried out on a publicly available iris database and compared to a commercial product.

Experimental analysis regarding the influence of iris segmentation on the recognition rate

In this study the authors will look at the detection and segmentation of the iris and its influence on the overall performance of the iris-biometric tool chain. The authors will examine whether the segmentation accuracy, based on conformance with a ground truth, can serve as a predictor for the overall performance of the iris-biometric tool chain. That is: If the segmentation accuracy is improved will this always improve the overall performance? Furthermore, the authors will systematically evaluate the influence of segmentation parameters, pupillary and limbic boundary and normalisation centre (based on Daugmans rubbersheet model), on the rest of the iris-biometric tool chain. The authors will investigate if accurately finding these parameters is important and how consistency, that is, extracting the same exact region of the iris during segmenting, influences the overall performance.

Segmentation-Level Fusion for Iris Recognition

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 on-the-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.

Subjective and objective quality assessment of transparently encrypted JPEG2000 images

Transparent encryption has two main requirements, i.e. security and perceived quality. The perceptual quality aspect has never been thoroughly investigated. In this work, three variants to transparently encrypt JPEG2000 images are compared from a perceptual quality viewpoint. The assessment is based on subjective and objective quality assessment of the transparently encrypted images and if the requirements with respect to desired functionalities can be met by the respective techniques. In particular, we focus on the question if it is possible to predict the subjective quality of the encrypted (and attacked) images as given by the Mean Opinion Score (MOS) with state-of-the-art objective quality metrics. Additionally, we answer the question which objective quality measure is suited best to determine an image quality for which a certain subjective quality is required.