Liste der Fachpublikationen

Show publication details
Krispel, Ulrich; Ullrich, Torsten; Fellner, Dieter W.

Fast and Exact Plane-based Representation for Polygonal Meshes

2014

Blashki, Katherine (Ed.) et al.: Proceedings of the International Conferences on Interfaces and Human Computer Interaction 2014, Game and Entertainment Technologies 2014 and Computer Graphics, Visualization, Computer Vision and Image Processing 2014 : Part of the Multi Conference on Computer Science and Information Systems, MCCSIS 2014. IADIS Press, 2014, pp. 189-196

IADIS International Conference Computer Graphics, Visualization, Computer Vision and Image Processing (CGVCVIP) <8, 2014, Lisbon, Portugal>

Boolean operations on meshes tend to be non-robust, due to the rounding of newly constructed vertex coordinates. Plane-based mesh representations are known to circumvent the problem for meshes with planar faces: geometric information is stored by face equations, and vertices (as well as newly constructed vertices) are expressed as plane triplets. We first review the properties of plane-based mesh representations and discuss a variant that is optimized for fast evaluation using fixed integer precision and give some practical insights on implementing search structures for indexing of planes and vertices in this representation.

Show publication details
Wesarg, Stefan; Wichmann, Julian L.; Booz, Christian; Erdt, Marius; Kafchitsas, Konstantinos; Khan, M. Fawad

First Clinical Experience with BMD Assessment in Vertebrae Using Dual-Energy CT

2014

Erdt, Marius (Ed.) et al.: Clinical Image-Based Procedures. Translational Research in Medical Imaging : Second International Workshop, CLIP 2013. Held in Conjunction with MICCAI 2013. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8361), pp. 151-159

International Workshop on Clinical Image-based Procedures (CLIP) <2, 2013, Nagoya, Japan>

Dual-energy CT (DECT) can be performed with state-of-the- art dual-source CT (DSCT) scanners and allows for assessing bone mineral density (BMD). In this work, we present first clinical experience with in vivo BMD assessment of vertebrae based on DECT data which has been acquired with a state-of-the-art DSCT scanner in the clinical routine. In contrast to previous work where we did in vitro tests of our method, we apply it her for the first time to in vivo data and prove the feasibility of our technique in a clinical setting. For 25 patients, DXA as well as DECT data have been acquired and BMD of vertebrae was assessed. Advantages of DECT are its 3D capabilities allowing to compute the spatial BMD distribution and to focus the examination on the trabecular bone. Correlations between both imaging techniques regarding the averaged BMD values per vertebra are only moderate.

Show publication details

Follow-Me: Smartwatch Assistance on the Shop Floor

2014

Nah, Fiona Fui-Hoon (Ed.): HCI in Business : HCIB 2014. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8527), pp. 279-287

International Conference on Human-Computer Interaction in Business (HCIB) <1, 2014, Heraklion, Crete, Greece>

The growing complexity of manufacturing calls for new approaches to support the human workforce with situation-aware information and tools which in consequence ease the process of understanding and applying work related knowledge. With this paper we introduce a theoretical model for a systematic information transfer between assistance system and worker. It defines assistance objectives and reviews the role of artifacts during the assistance process focusing on the cognitive aspects of work. Our approach was implemented using smartwatches for application in industrial assembly environments extending the Plant@Hand manufacturing performance support system.

Show publication details
Ladenhauf, Daniel; Berndt, Rene; Eggeling, Eva; Ullrich, Torsten; Battisti, Kurt; Gratzl-Michlmair, Markus

From Building Information Models to Simplified Geometries for Energy Performance Simulation

2014

Lazarevic, Eva Vanista (Ed.) et al.: Proceedings of International Academic Conference on Places and Technologies : Keeping up with Technologies to Improve Places [online]. [cited 16 December 2014] Available from: http://placesandtechnologies.eu/about.html: University of Belgrade, 2014, pp. 669-676

International Academic Conference on Places and Technologies <1, 2014, Belgrade, Serbia>

A major future challenge in the building industry is to reduce primary energy use of buildings. EU law now requires energy performance certificates to be issued for all buildings. Hence, energy performance simulation becomes an increasingly important topic. Accurate, yet efficient simulation depends on simple building models. Most of the required data can be found in Building Information Models (BIM), following the buildingSMART alliance's Industry Foundation Classes (IFC) schema. IFC has become an ISO standard and enjoys increasing support by CAD software. However, typical IFC models contain a lot of irrelevant data, in particular geometric representations, which are too detailed for energy performance simulation. Therefore, an algorithm is proposed for extracting input models for simulations directly from IFC models in a semi-automatic process, to overcome the current situation where simple models are manually built from scratch. The key aspect of the algorithm is geometry simplification subject to semantic and functional groups; more specifically, the 3D representations of walls, slabs, windows, doors, etc. are reduced to a collection of surfaces describing the building's thermal shell on one hand, and the material layers associated with it on the other hand. Test models from simple fictitious houses to complex models of real-world buildings have been provided to guide the development of the algorithm in an incremental manner. This paper presents the resulting algorithm and the current status of prototype software implementing it.

Show publication details

From Raw Data to Rich Visualization: Combining Visual Search with Data Analysis

2014

Wahlster, Wolfgang (Ed.) et al.: Towards the Internet of Services: The THESEUS Research Program. Berlin, Heidelberg, New York: Springer, 2014. (Cognitive Technologies), pp. 203-209

Visual analytics is an interdisciplinary field of research at the boundary between data mining, statistics and visualization. Patterns and relations in the data complement a semantic representation of knowledge on a lower level of abstraction. One important goal of visual analytics is to find relations hidden in vast amounts of data, which can be turned into useful knowledge. Analysis needs to be "visual", because human's visual cognitive abilities are important for the identification and refinement of the analytical process. Further the results of the analysis have to be presented in a way to match the user's perspective on the proposed task. However, typical users are not experts in statistics or data mining. The challenge of visual analytics is to keep domain experts in charge of the analytical process while reducing the workload due to the complexity of the techniques. While search and analysis usually arc mentioned in different contexts, they are highly interdependent processes. In fact, every exploratory analysis is a search for new knowledge. In turn, this knowledge can be used to refine future searches by introducing new concepts or relations to draw from. This article will show how automated and visual methods can be combined to connect knowledge artifacts on multiple levels of abstraction.

Show publication details

Fundamental Aspects for E-Government

2014

Sonntagbauer, Peter et al.: Handbook of Research on Advanced ICT Integration for Governance and Policy Modeling. Hershey, Pennsylvania: IGI Global, 2014, pp. 1-18

The upcoming initiatives using ICT in the government process should strengthen the benefit of E-Government in most countries. Since E-Government among other e-related terms is a widely (interpreted) term, it is sometimes challenging to understand the objective and goals of an initiative. Therefore in this paper we introduce and explain the most E-Government related terms. Even more, we outline some interesting initiatives and implementations to explain the benefits of using ICT in the government domain. So next to the term description, concrete activities will be aligned to the terms to explain the practical use in a better way. We conclude with several challenges that arise when thinking of the implementation of E-Government services. Overall this chapter should give a good overall view about E-Government and the relating issues.

Show publication details
Sonntagbauer, Susanne; Sonntagbauer, Peter; Nazemi, Kawa; Burkhardt, Dirk

The FUPOL Policy Lifecycle

2014

Sonntagbauer, Peter et al.: Handbook of Research on Advanced ICT Integration for Governance and Policy Modeling. Hershey, Pennsylvania: IGI Global, 2014, pp. 61-87

The purpose of this chapter is to outline an advanced policy lifecycle, the FUPOL model with its ability to link technical features in the area of policy modeling. The FUPOL Policy Lifecycle is based on six stages, which are further divided into ten main tasks. These main tasks are split up into eighteen subtasks to provide a very detailed policy lifecycle structure. The detailed breakdown allows to link each task to various technical features, such as opinion maps, policy indicator dashboard, knowledge data base, simulation and visualization tools. It is further argued that the methodology applied is future proof and has the potential of accommodating new technologies in the future.

Show publication details
Ginters, Egils; Aizstrauts, Artis; Baltruks, Mikelis; Nazemi, Kawa; Burkhardt, Dirk; Sonntagbauer, Peter; Sonntagbauer, Susanne; Gutierrez, Jorge Martin

Fupol Simulators and Advanced Visualization Framework Integration

2014

Affenzeller, Michael (Ed.) et al.: 26th European Modeling and Simulation Symposium : EMSS 2014. Italy: CAL-TEK S.r.l., 2014, pp. 523-529

European Modeling and Simulation Symposium (EMSS) <26, 2014, Bordeaux, France>

FP7 FUPOL project No.287119 (see www.fupol.eu) aims at a new approach to traditional politics modeling. The FUPOL will be able to automatically collect, analyze and interpret opinions expressed on a large scale from the Internet and social networks. This will enable governments to gain a better understanding of the needs of citizens. Likewise the software will have the capabilities to simulate the effects of policies and laws and to assist governments in the whole policy design process. Basic visualization of the simulation results are supported by the simulators however visualization facilities are limited, therefore for detailed visual analysis of simulation data SemasVis environment is used.

Show publication details

Fusing Web Technologies & Augmented Reality

2014

Julier, Simon (Ed.) et al.: IEEE International Symposium on Mixed and Augmented Reality - Science & Technology 2014 : ISMAR 2014. Piscataway, NJ: IEEE Service Center, 2014, 1 p.

IEEE International Symposium on Mixed and Augmented Reality (ISMAR) <13, 2014, Munich, Germany>

Within the German research project ARVIDA a large consortium of industrial Virtual and Augmented Reality users, of technology providing companies and research institutes cooperate on the establishment of highly flexible web-based reference architecture for Augmented Reality applications. The use of web technologies is motivated by modern web standards as WebGL or WebRTC supporting e.g. real time rendering of 3D-content of video streaming within Web-Browsers. Thereby, the use of Web technologies not only offers the possibility to develop applications platform and OS independent but it also facilitates the integration of Augmented Reality into industrial workflows or PDM environments. The developed reference architecture offers RESTful tracking, rendering and interaction services that foster the combination and exchange of different algorithms with the aim to fit the technology to the specific requirements of an AR-applications in an optimal way.

Show publication details
Preiss, Jens; Fairchild, Mark D.; Ferwerda, James A.; Urban, Philipp

Gamut Mapping in a High-Dynamic-Range Color Space

2014

Eschbach, Reiner (Ed.) et al.: Color Imaging XIX: Displaying, Processing, Hardcopy, and Applications. Bellingham: SPIE Press, 2014. (Proceedings of SPIE 9015), pp. 90150A-1 - 90150A-7

Color Imaging: Processing, Hardcopy, and Applications <19, 2014, San Francisco, CA, USA>

In this paper, we present a novel approach of tone mapping as gamut mapping in a high-dynamic-range (HDR) color space. High- and low-dynamic-range (LDR) images as well as device gamut boundaries can simultaneously be represented within such a color space. This enables a unified transformation of the HDR image into the gamut of an output device (in this paper called HDR gamut mapping). An additional aim of this paper is to investigate the suitability of a specific HDR color space to serve as a working color space for the proposed HDR gamut mapping. For the HDR gamut mapping, we use a recent approach that iteratively minimizes an image-difference metric subject to in-gamut images. A psychophysical experiment on an HDR display shows that the standard reproduction workflow of two subsequent transformations - tone mapping and then gamut mapping - may be improved by HDR gamut mapping.

Show publication details

GCH 2014: Eurographics Workshop on Graphics and Cultural Heritage

2014

Eurographics Symposium on Graphics and Cultural Heritage (GCH) <12, 2014, Darmstadt, Germany>

Focus of this year's forum is to present and showcase new developments within the overall process chain, from data acquisition, 3D documentation, analysis and synthesis, semantical modelling, data management, to the point of virtual museums or new forms of interactive presentations and 3D printing solutions. GCH 2014 therefore provides scientists, engineers and CH managers a possibility to discuss new ICT technologies applied to data modelling, reconstruction and processing, digital libraries, virtual museums, interactive environments and applications for CH, ontologies and semantic processing, management and archiving, standards and documentation, as well as its transfer into practice.

Show publication details

GCH 2014. Short Papers - Posters: Eurographics Workshop on Graphics and Cultural Heritage

2014

Eurographics Symposium on Graphics and Cultural Heritage (GCH) <12, 2014, Darmstadt, Germany>

Focus of this year's forum is to present and showcase new developments within the overall process chain, from data acquisition, 3D documentation, analysis and synthesis, semantical modelling, data management, to the point of virtual museums or new forms of interactive presentations and 3D printing solutions. GCH 2014 therefore provides scientists, engineers and CH managers a possibility to discuss new ICT technologies applied to data modelling, reconstruction and processing, digital libraries, virtual museums, interactive environments and applications for CH, ontologies and semantic processing, management and archiving, standards and documentation, as well as its transfer into practice. Short papers present preliminary results and work-in-progress or focusing on on-going projects, the description of project organization, use of technology, and lesson learned.

Show publication details
Dreißig, Martin; Deistung, Eik (Betreuer)

Generative Schiffsmodellierung

2014

Wismar, Hochschule, Master Thesis, 2014

Die dreidimensionale Modellierung ist ein sehr verbreitetes Werkzeug um mediale Inhalte zu schaffen. Es wird in vielen verschiedenen Bereichen, wie z.B. der Spiele und Nachrichtenbranche genutzt, um 3D-Objekte und -Szenen zu generieren. Ziel dieser 3D-Graffiken ist es, dem Betrachter Informationen anschaulicher übermitteln zu können - durch beispielsweise Inszenierungen von Zukunftsvisionen, dreidimensionaler Diagrammen oder Trainingssimulationen. Ziel dieser Thesis soll es sein, ein möglichst realistisches Schiffsmodell mit einer nicht herkömmlichen Methodik zu erstellen: der generativen Modellierung. Der größte Unterschied zu konventionellen Modellierungsmethoden besteht darin, dass nicht das fertige Modell, sondern der Prozess zum Modell im Fokus steht. Die genutzte Programmiersprache GML ermöglicht es daher in die Prozesse einzugreifen und theoretisch unendlich viele Variationen der Objekte mit geringem Aufwand zu erstellen. Anhand der Vorlage eines realen Schiffes wurde diese Aufgabe umgesetzt und auf den Einsatz im übergeordneten Projekt MarOpTra-3D geprüft.

Show publication details
Ladenhauf, Daniel; Berndt, Rene; Krispel, Ulrich; Eggeling, Eva; Ullrich, Torsten; Battisti, Kurt; Gratzl-Michlmair, Markus

Geometry Simplification According to Semantic Constraints: Enabling Energy Analysis Based on Building Information Models

2014

Computer Science - Research and Development, (2014), Online first: November 2014

The building industry and facility management is in a state of upheaval: The complexity of the realworld is now represented in its digital counterpart. The established object-based file format "Industrial Foundation Classes (IFC)" developed by the International Alliance for Interoperability facilitates interoperability in the context of Building Information Modeling. Unfortunately, there is no feasible workflow for filtering energy-related information, e.g. a streamlined version of the building geometry. Simplification methods often fail on CAD data that is ignorant of domain specific semantic information (i.e. functional differences between a door and stucco are not reflected in the geometry and are therefore often ignored). With EU law now requiring energy performance certificates to be issued for all buildings, energy performance analysis becomes an increasingly important topic. Accurate, yet efficient calculation depends on simple building models. However, typical IFC models contain a lot of irrelevant data, in particular geometric representations, which are too detailed for energy performance analysis. Therefore, we propose an algorithm that extracts input models suitable for calculations directly from IFC models in a semi-automatic process. The key aspect of the algorithm is geometry simplification subject to semantic and functional groups; more specifically, the 3D representations of walls, slabs, windows, doors, etc. are reduced to a collection of surfaces describing the building's thermal shell on one hand, and the material layers associated with it on the other hand. This simplification takes into account semantic constraints and expert knowledge. Furthermore, it works on "real-world" data; i.e. it is robust towards incomplete, imperfect and inconsistent data.

Show publication details
Melzer, Marianne; Damer, Naser (Betreuer)

Gesichtserkennungssoftware in Bildarchiven - Eine Untersuchung zur Nutzung von Gesichtserkennungsprogrammen für die archivische Kernaufgabe "Erschließung"

2014

Potsdam, FH, Bachelor Thesis, 2014

Diese Arbeit betrachtet zunächst die theoretischen Grundlagen für die Gesichtserkennung. Das sind zum einen Erklärungen zur Archivale Foto, auch unter dem Aspekt der Fotoarchivierung und der archivischen Erschließung und die Biometrie bzw. Biometrik. Zum anderen ist es der Ablauf der Gesichtserkennung sowie die Algorithmen, welche häufig Anwendung hierbei finden. Mit Hilfe dieser Informationen werden verschiedene Softwareprogramme einer Untersuchung, die vorab ausführlich erläutert wird, zur Nutzung von Gesichtserkennungsprogrammen für die archivische Kernaufgabe "Erschließung" unterzogen. Die Ergebnisse dieser Untersuchung sollen aufzeigen, ob und inwiefern Gesichtserkennungsprogramme eine qualitative und quantitative Verbesserung in Bezug auf die Datensicherung (Personennennung) und Vereinfachung der Erschließung in Bildarchiven erzielen könnten. Eine Empfehlung resp. ein Ausblick zu diesem Thema vollenden die Arbeit.

Show publication details
Gäde, Michael; Bieber, Gerald (Betreuer); Urban, Bodo (Betreuer)

Gestenerkennung auf Smartwatches

2014

Rostock, Univ., Studienarbeit, 2014

Virtual Environment und Smart Homes ermöglichen eine komfortable Privatsphäre. Per Fernsteuerung lassen sich Fenster öffnen, Licht an- und ausschalten, oder Zimmertemperaturen regeln. Zur bequemen und natürlichen Bedienung dieser eignen sich Sprache oder Gesten. Diese Literaturarbeit befasst sich mit den gängigen Methoden und Techniken, Handgesten zu erkennen und zu klassifizieren. Es werden einige bereits verfügbare Systeme erläutert, wozu vor allem visuelle und beschleunigungs-basierte zählen. Im Anschluss werden einige Einsatzgebiete für eine Gestensteuerung beschrieben, wobei hier der Fokus auf beschleunigungs-basierter Sensorik am Handgelenk liegt.

Show publication details
Gäde, Michael; Urban, Bodo (Betreuer); Bieber, Gerald (Betreuer)

Gestenerkennung auf Smartwatches

2014

Rostock, Univ., Bachelor Thesis, 2014

Virtual Environment und Smart Homes ermöglichen eine alternative Interaktion mit der Umgebung. Per Fernsteuerung lassen sich Fenster öffnen, Licht an- und ausschalten, oder Zimmertemperaturen regeln. Zur bequemen und natürlichen Bedienung einer solchen Steuerung eignen sich Sprache oder Gesten. Diese Bachelorarbeit befasst sich mit den gängigen Methoden und Techniken, Handgesten zu erkennen und zu klassifizieren wobei hier der Fokus auf beschleunigungs-basierter Sensorik am Handgelenk liegt. Es wird eine Gestenerkennung mit einer Smartwatch konzipiert, umgesetzt und evaluiert. Des Weiteren wird die Tauglichkeit einer permanent aktiven Erkennung überprüft.

Show publication details
Zeiß, Steeven; Marinc, Alexander; Braun, Andreas; Große-Puppendahl, Tobias; Beck, Sebastian

A Gesture-Based Door Control Using Capacitive Sensors

2014

Streitz, Norbert (Ed.) et al.: Distributed, Ambient, and Pervasive Interactions : DAPI 2014. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8530), pp. 207-216

International Conference on Distributed, Ambient and Pervasive Interactions (DAPI) <2, 2014, Heraklion, Crete, Greece>

In public places sanitary conditions are always of concern, particularly of surfaces that are touched by a multitude of persons, such as door handles in rest rooms. Similar issues also arise in medical facilities. Doors that open based on presence are common in environments such as shopping malls; however they are not suited for sensitive areas, such as toilet stalls. Capacitive proximity sensors detect the presence of the human body over a distance and can be unobtrusively applied in order to enable hidden gesture-based interfaces that work without touch. In this paper we present a concept for a gesture controlled automated door based on this sensor technology. We introduce the underlying technology and present the concept and electronic components used in detail. Novel interaction patterns and data processing methods allow to open, close, lock and unlock the door using simple gestures. A prototype device has been created and evaluated in a user study.

Show publication details
Hadlak, Steffen; Schumann, Heidrun (Betreuer); Urban, Bodo (Betreuer); Kerren, Andreas (Betreuer)

Graph Visualization in Space and Time

2014

Rostock, Univ., Diss., 2014

The visual analysis of graphs plays an important role in many fields and includes a diversity of aspects such as the graphs' structure and associated attributes in their spatial and temporal context. Because of their increasing size, their visualization becomes more and more difficult and necessitates a multitude of different visualization techniques. This problem becomes even more severe as with a changing analysis focus on the graph, the analyst needs to flexibly switch between different visualizations at any time. This thesis aims at solving these three challenges. First, the handling of the diversity and emerging problems are discussed exemplary for two approaches each providing a multitude of differently suited tree visualizations. Here, a family of point-based tree layouts is introduced that consists of layouts with a similar layout scheme. And an implicit tree visualization design space is derived by identifying common design decisions. For a scalable analysis of large graphs, new reduction approaches are introduced. These approached are based on the one hand on clustering techniques abstracting either the structural or temporal aspect of the graphs. And on the other hand they rely on Degree-of-Interest functions to discern interesting nodes, edges and time points. Finally, to bring the different visualizations together and thus allow a flexible analysis, novel approaches for their combination and synchronization are introduced. These approaches include the in situ visualization that is based on portals to allow a local combination of visualizations and a novel abstract overview of all aspect allowing the synchronization of multiple visualizations.

Show publication details
Fietkau, Julian; Urban, Bodo (Betreuer)

Grundlagen von subjektiven Videoqualitätstests: Literaturarbeit

2014

Rostock, Univ., Studienarbeit, 2014

Show publication details
Hilpert, Julia; Jung, Florian (Betreuer)

Halbautomatische Segmentierung von Lymphknoten aus Magnetresonanztomographiedaten des Kopf- und Halsbereichs

2014

Mannheim, Hochschule, Bachelor Thesis, 2014

Die Größe und das Aussehen von Lymphknoten kann bei Krebspatienten Aufschluss über die Streuung eines Tumors geben. Deshalb ist ihre Vermessung bei der Behandlung sowie Nachsorge von großer Bedeutung. Der erste Schritt ist hierbei die Segmentierung der Lymphknoten. Bisher sind jedoch nur wenige Ansätze zur automatisierten Segmentierung von Lymphknoten auf MRT-Daten bekannt. In dieser Arbeit wird deshalb ein Verfahren vorgestellt, welches Lymphknoten aus MRT-Daten des Kopf- und Halsbereichs segmentiert. Diese Segmentierung findet mit minimaler Nutzerinteraktion, nur durch Setzen eines Punktes innerhalb des Lymphknotengewebes, statt. Die Hauptkomponente der gewählten Methode zur Segmentierung ist eine Wasserscheidentransformation, die das Bild über seine Gradienten in verschiedene Segmente einteilt. Mittels eines Radialstrahlverfahrens wird zusätzlich die Oberfläche des Lymphknotens angenähert. Diese Oberfläche dient nach weiteren, untergeordneten Verarbeitungsschritten dazu, aus der Menge der Bildsegmente jene auszuwählen, die den Lymphknoten repräsentieren. Evaluiert wurde das entwickelte Verfahren an 95 Lymphknoten aus 17 verschiedenen, T1- gewichteten MRT-Datensätzen. Es ergab sich ein durchschnittlicher Dice Similarity Coefficient von 0,69±0,15. Auf dem Weg zu einer vollautomatischen Segmentierung von Lymphknoten stellt das entwickelte Verfahren somit einen vielversprechenden ersten Schritt dar.

Show publication details
Sonntagbauer, Peter; Nazemi, Kawa; Sonntagbauer, Susanne; Burkhardt, Dirk

Handbook of Research on Advanced ICT Integration for Governance and Policy Modeling

2014

As governments and policy makers take advantage of information and communication technologies, leaders must understand how to navigate the ever-shifting landscape of modern technologies in order to be most effective in enacting change and leading their constituents. Advanced ICT Integration for Governance and Policy Modeling builds on the available literature, research, and recent advances in e-governance to explore advanced methods and applications of digital tools in government. This collection of the latest research in the field presents an essential reference for academics, researchers, and advanced-level students, as well as government leaders, policy makers, and experts in international relations.

Show publication details

Helper Data Scheme for 2D Cancelable Face Recognition Using Bloom Filters

2014

Mustra, Mario (Ed.) et al.: IWSSIP 2014. Proceedings : 21st International Conference on Systems, Signals and Image Processing. Zagreb: Faculty of Electrical Engineering and Computing, University of Zagreb, 2014, pp. 271-274

International Conference on Systems, Signals and Image Processing (IWSSIP) <21, 2014, Dubrovnik, Croatia>

Biometrics provide a source of automated recognition of individuals based on their physiological and behavioral characteristics. As per Directive 95/46/EC, biometric data is considered to be personal data. And according to article 8 of the European Convention on Human Rights, personal data needs to be privacy preserved. Biometric template protection mechanisms provide a privacy preserved biometric authentication. Such mechanisms assist irreversibility, revocability and unlinkability of biometric templates. Recently, a bloom filter based approach was proposed to generate irreversible iris template. In this paper, a helper data scheme for 2D cancelable face verification using bloom filters is proposed. The positions of most representative features (stable features) are used as helper data, which helps in the face recognition. The features used are extracted using Local Binary Linear Discriminant Analysis. The effect of stable features on recognition performance under scenarios of with and without using bloom filters is investigated. In addition, recognition performance after compressing multiple features into a single bloom filter is presented. The results are experimentally proved on two benchmark databases namely LFW and ORL datasets.

Show publication details
Yoon, Sang Min; Graf, Holger; Kuijper, Arjan

Hierarchical Image Representation using 3D Camera Geometry for Content-based Image Retrieval

2014

Engineering Applications of Artificial Intelligence, Vol.30 (2014), pp. 235-241

In this paper we present a hierarchical image representation methodology by clustering images with 3D camera geometry in order to efficiently retrieve the images according to user's viewpoint. The framework of our proposed technique is composed of two steps: first the visual correlation analysis between images in a large database is determined by the estimated 3D camera geometry and second images are classified using a constrained agglomerative hierarchical image clustering method to retrieve the images the users search. The constrained agglomerative hierarchical image clustering method provides balanced hierarchical layers, independent of the number of images within the cluster. It also provides a convenient way to browsing, navigating, and categorizing of the images with various viewpoints, illumination, and partial occlusion.

Show publication details
Förster, Tim; Thum, Simon (Betreuer); Kuijper, Arjan (Betreuer)

Hochverfügbarkeit (Analytisch) von Big-Geo-Data als Platform as a Service

2014

Darmstadt, TU, Bachelor Thesis, 2014

Es gibt stetig wachsende Herausforderungen in der Entwicklung von Geodaten. Die Datenzunahme steigt kontinuierlich. Durch den starken Anstieg dieser Informationsansammlungen wird immer mehr Datenspeicher benötigt. Des Weiteren sollen die Systeme eine hohe Verfügbarkeit aufweisen und unter Last eine akzeptable Reaktionszeit liefern. Die Erfüllung solcher Anforderung lassen sich nur begrenzt mit einem einfachen Client/Server-System realisieren, da diese nicht gut skalieren und unter schlechten Bedingungen langsam agieren. Daher werden immer mehr Applikationen in der Cloud als Service bereitgestellt. Dies bringt viele Vorteile; unter anderem die Verbesserung der Verfügbar- und Skalierbarkeit des Services. In dieser Arbeit wird anhand eines existierenden Server-Systems die Designentscheidungen gezeigt, die für eine Realisierung des Produktes in der Cloud notwendig sind. Dieses Produkt wird dann als "Platform as a Service" bereitgestellt. Dabei werden Punkte wie, Persistierung im verteilten System und Cloud-API Gestaltung besprochen. Anschließend wird dies in einem verteilten System getestet und gegenüber ein einfaches Client/Server-System verglichen. Ebenfalls wird ein Model vorgestellt, womit die Verfügbarkeit des Systems kalkuliert wird.