Privacy is one of the most important social and political issues in our information society, characterized by a growing range of enabling and supporting technologies and services. Amongst these are communications, multimedia, biometrics, big data, cloud computing, data mining, internet, social networks, and audio–video surveillance. Each of these can potentially provide the means for privacy intrusion. De-identification is one of the main approaches to privacy protection in multimedia contents (text, still images, audio and video sequences and their combinations). It is a process for concealing or removing personal identifiers, or replacing them by surrogate personal identifiers in personal information in order to prevent the disclosure and use of data for purposes unrelated to the purpose for which the information was originally obtained. Based on the proposed taxonomy inspired by the Safe Harbour approach, the personal identifiers, i.e., the personal identifiable information, are classified as non-biometric, physiological and behavioural biometric, and soft biometric identifiers. In order to protect the privacy of an individual, all of the above identifiers will have to be de-identified in multimedia content. This paper presents a review of the concepts of privacy and the linkage among privacy, privacy protection, and the methods and technologies designed specifically for privacy protection in multimedia contents. The study provides an overview of de-identification approaches for non-biometric identifiers (text, hairstyle, dressing style, license plates), as well as for the physiological (face, fingerprint, iris, ear), behavioural (voice, gait, gesture) and soft-biometric (body silhouette, gender, age, race, tattoo) identifiers in multimedia documents.

The paper introduces a novel approach to face recognition based on the recently proposed low-dimensional probabilistic linear discriminant analysis (LD-PLDA). The proposed approach is specifically designed for complex recognition tasks, where highly nonlinear face variations are typically encountered. Such data variations are commonly induced by changes in the external illumination conditions, viewpoint changes or expression variations and represent quite a challenge even for state-of-the-art techniques, such as LD-PLDA. To overcome this problem, we propose here a patch-wise form of the LDPLDA technique (i.e., PLD-PLDA), which relies on local image patches rather than the entire image to make inferences about the identity of the input images. The basic idea here is to decompose the complex face recognition problem into simpler problems, for which the linear nature of the LD-PLDA technique may be better suited. By doing so, several similarity scores are derived from one facial image, which are combined at the final stage using a simple sum-rule fusion scheme to arrive at a single score that can be employed for identity inference. We evaluate the proposed technique on experiment 4 of the Face Recognition Grand Challenge (FRGCv2) database with highly promising results.

Illumination induced appearance changes represent one of the open challenges in automated face recognition systems still significantly influencing their performance. Several techniques have been presented in the literature to cope with this problem; however, a universal solution remains to be found. In this paper we present a novel normalization scheme based on the nuisance attribute projection (NAP), which tries to remove the effects of illumination by projecting away multiple dimensions of a low dimensional illumination subspace. The technique is assessed in face recognition experiments performed on the extended YaleB and XM2VTS databases. Comparative results with state-of-the-art techniques show the competitiveness of the proposed technique.

Subspace projection techniques are known to be susceptible to the presence of partial occlusions in the image data. To overcome this susceptibility, we present in this paper a confidence weighting scheme that assigns weights to pixels according to a measure, which quantifies the confidence that the pixel in question represents an outlier. With this procedure the impact of the occluded pixels on the subspace representation is reduced and robustness to partial occlusions is obtained. Next, the confidence weighting concept is improved by a local procedure for the estimation of the subspace representation. Both the global weighting approach and the local estimation procedure are assessed in face recognition experiments on the AR database, where encouraging results are obtained with partially occluded facial images.

Person recognition using facial features, e.g., mug-shot images, has long been used in identity documents. However, due to the widespread use of web-cams and mobile devices embedded with a camera, it is now possible to realize facial video recognition, rather than resorting to just still images. In fact, facial video recognition offers many advantages over still image recognition; these include the potential of boosting the system accuracy and deterring spoof attacks. This paper presents an evaluation of person identity verification using facial video data, organized in conjunction with the International Conference on Biometrics (ICB 2009). It involves 18 systems submitted by seven academic institutes. These systems provide for a diverse set of assumptions, including feature representation and preprocessing variations, allowing us to assess the effect of adverse conditions, usage of quality information, query selection, and template construction for video-to-video face authentication.

An edit-distance model that can be used for the approximate matching of contiguous and non-contiguous timed strings is presented. The model extends the concept of the weighted string-edit distance by introducing timed edit operations and by making the edit costs time dependent. Special attention is paid to the timed null symbols that are associated with the timed insertions and deletions. The usefulness of the presented model is demonstrated on the classification of phone-recognition errors using the TIMIT speech database.

Until recently, most of the effort for providing security in information systems has been focused on technology. However, it turned out during the last years that human factors have played a central role. Therefore, to ensure appropriate security in contemporary information systems, it is necessary to address not only technology-related issues, but also human behaviour and organisation-related issues that are usually embodied in security policies. This paper presents a template model, which is intended to support risk management for information systems, and which is concentrated on human factors. The model is based on business dynamics that provide the means for qualitative and quantitative treatment of the above-mentioned issues.

The paper presents our experiences with the phone transition acoustical models.The phone transition models were compared to the traditional context dependent phone models.We put special attention on the speech signal segmentation analysis to provide a better insight i n to certain segmentation eects when using the dierent acoustical models.Experiments with the HMM-based models were performed using the HTK toolkit, which w as extended to allow proper state parameter tying for the phone transition models.All the model parameters were estimated on the GOPOLIS speech database.The annotation confusions concerning two-phone speech units are discussed.Finally, the overall word recognition score is presented.The better score was achieved using the diphone models even when comparing them to the triphone models.

The performance degradation of automatic speech recognition system due to acoustic mismatch in training and testing environment is a severe problem for practical use of speech recognizer [1]. In this paper, we explore the effects of noise on individual speech feature vector statistics, and several feature normalization methods are used to compensate environment influence on feature vectors. We try to find out what kind of normalization is most effective and which feature vectors should be normalized in order to achieve robust features under adverse noise.

Within the EC-funded project SQEL, the German EVAR spoken dialogue system has been extended with respect to multilinguality and multifunctionality. The current demonstrator can handle four different languages and domains: German, Slovak, and Czech (and their national train connections), and Slovenian (European flights). The SQEL demonstrator can also access databases on the WWW, which enables users without an internet connection to meet their information needs by just using the phone. The system starts up with a German opening phrase and the user is free to use any of the implemented languages. Amultilingual word recognizer implicitly identifies the language, which is then associated with the appropriate domain and database. For the remainder of the dialogue, the corresponding monolingual recognizer is used instead. Experiments to date have shown that the multilingual and the (respective) monolingual recognizers attain comparable word accuracy rates, although the former is less efficient. The existence of language-independent task parameters, such as goal and source location, has meant that porting the system to a new language involves mainly the development of lexica and grammars (apart from the word recognizers) and not an extensive restructuring of the interpretation process within the Dialogue Manager. The latter is sufficiently flexible to switchbetween the different domains and languages.

In this paper, a method of generating structural descriptions of stereo image pairs and their matching to recover 3D form of objects in space, is discussed. The method consists of the following steps: 1) straight line segments are extracted in both images and the relational among them are investigated; and 2) the relational subgraphs are constructed and the correspondence graph is created. Using the "stable marriage" searching algorithm the features in one image corresponding to features in the other image are found. The method was tested on a set of aerial stereo images of urban scenes.