Faculty of Informatics Vienna University of Technology Institute of Computer Aided Automation PRIP Home PRIP Home
Personal tools
You are here: Home Events Past Presentations

Past Presentations

Event Diplomanden-/ Dissertantenseminar 183.293, 183.304, SS2011 (Sem. 183/2, from May 03, 2011 04:00 PM to May 03, 2011 05:00 PM)
Termin: 03.05.2011 - 16:00 Uhr Ort:
Event Pawel Dlotko: Brainstorm of ideas, what we can do in the near future. (Library HC 04 07, from Feb 28, 2011 04:00 PM to Feb 28, 2011 05:00 PM)
Abstract: In this talk I am going to present a number of new ideas somewhere in between topology and pattern recognition. Among others, I will be talking about patterns in multidimensional data, topological idea in object tracking, applications of cohomology generators in avoiding obstacles and the common ideas between rectangular CW complexes and irregular graph pyramids. I hope the talk will trigger out a long discussion and some paper and common application of PRIP and Kraków group for some common project.
Event Cristian Smochina: Microscopic image processing techniques and segmentation evaluation (Library HC 04 07, from Feb 15, 2011 05:00 PM to Feb 15, 2011 05:30 PM)
The presentation contains two parts. In the first part a quality measure for evaluating the performance of segmentation algorithms is presented. This discrepancy method is based on object-by-object comparison of a segmented image (machine segmentation) versus ground-truth segmentation (reference image). The error measure takes into consideration the interior of the object and eliminates the inconveniences that appear in the case of the concave objects. A weighted shape fitting score is used: the score of the segmented contour is enhanced by a factor which indicates the similarity between these two curves. The second part contains automatic segmentation techniques for detecting cell nuclei in images taken from tissues with colon carcinoma. The region growing method is used to obtain accurate background detection. New approaches are proposed to detect the separation areas between clustered/touching cell nuclei. These regions are validated based on their link with the background. The watershed segmentation algorithm followed by a merging criterion is used to completely delimit the nuclei boundaries.
Event Hubert Wagner: Efficient Computation of Persistent Homology for Cubical Data (Library HC 04 07, from Feb 15, 2011 04:00 PM to Feb 15, 2011 05:00 PM)
Abstract of the related paper: In this paper we present an efficient framework for computation of persistent homology of cubical data in arbitrary dimensions. An existing algorithm using simplicial complexes is adapted to the setting of cubical complexes. The proposed approach enables efficient application of persistent homology in domains where the data is naturally given in a cubical form. By avoiding triangulation of the data, we significantly reduce the size of the complex. We also present a data-structure designed to compactly store and quickly manipulate cubical complexes. By means of numerical experiments, we show high speed and memory efficiency of our approach. We compare our framework to other available implementations, showing its superiority. Finally, we report persistent homology results for selected 3D and 4D data sets.
Event DiplDiss (Favoritenstr. 9 - 11, 4. Stock, Bibliothek, , from Nov 05, 2010 10:00 AM to Nov 05, 2010 12:00 PM)
Dieses Seminar bietet ein Forum für Diskussion über die Arbeit von Diplomanden und Dissertanten und die Möglichkeit zum Austausch von Ideen und Neuigkeiten unter den Studierenden.
Event Object recognition and reconstruction in presence of noise (Seminarraum 183/2, from Jun 22, 2010 04:15 PM to Jun 22, 2010 06:00 PM)
Event Georg Nebehay: Evaluation of a self-calibration method for smart video cameras (Sem 183/2, from Mar 15, 2010 04:15 PM to Mar 15, 2010 04:35 PM)
Abschlussvortrag Praktikum
Event Lukas Fischer: Optimizing Shape Particle Filters for the Detection and Segmentation of Medical Images (Sem 183/2, from Mar 15, 2010 04:15 PM to Mar 15, 2010 04:25 PM)
Abschlussvortrag DA
Event Andreas Zweng: Unexpected Human Behavior Recognition in Image Sequences (Sem 183/2, from Mar 04, 2010 02:15 PM to Mar 04, 2010 02:15 PM)
Abschlussvortrag DA
Event Fabian Hollaus: Automated inpainting of unknown palimpsest regions (Sem 183/2, from Mar 04, 2010 02:15 PM to Mar 04, 2010 02:15 PM)
Spezifikationsvortrag DA
Event Markus Diem: Recognizing Degraded Handwritten Characters (Sem 183/2, from Mar 04, 2010 02:15 PM to Mar 04, 2010 02:35 PM)
Abschlussvortrag DA
Event Harald Reingruber: An asynchronous Stereo Vision Concept for Event-based Vision Systems (Sem 183/2, from Dec 15, 2009 04:35 PM to Dec 15, 2009 04:55 PM)
Spezifikationsvortrag Diplomarbeit
Event Georg Zankl: Eccentricity Transform of Polygonal Shapes (Sem 183/2, from Dec 15, 2009 04:15 PM to Dec 15, 2009 04:35 PM)
Endvortrag Bakkalaureatsarbeit
Event Andreas Zweng: Unexpected Human Behavior Recognition in Image Sequences (Sem 183/2, from Nov 24, 2009 04:35 PM to Nov 24, 2009 04:55 PM)
Spezifikationsvortrag Diplomarbeit
Event Andreas Zweng: Motion Detection Framework & ZIP-Lib (Sem 183/2, from Nov 24, 2009 04:15 PM to Nov 24, 2009 04:35 PM)
Abschlussvortrag Praktikum
Event Karl-Heinz Nenning: Analysis of fMRI data using functional parcellation and functional connectivity (Sem 183/2, from Nov 10, 2009 05:15 PM to Nov 10, 2009 05:35 PM)
Spezifikationsvortrag DA
Event Timo Kropp: Visualisierung von Trajektorien live in Microsoft Bing Maps (Sem 183/2, from Oct 20, 2009 04:15 PM to Oct 20, 2009 04:35 PM)
Präsentation Bachelorarbeit
Event Jana Banova: Affective Image Classification (Sem 186, from Oct 09, 2009 11:15 AM to Oct 09, 2009 11:25 AM)
Abschlussvortrag Diplomarbeit
Event Marcin Grzegorzek: Integrating Domain Specific Knowledge into the Process of Digital Image Analysis (Sem 186, from Oct 09, 2009 10:30 AM to Oct 09, 2009 11:30 AM)
Event Eva Dittrich: Automatic Segmentation of Retinal Vessels and Measurement of Doppler Flow Velocity in Optical Coherence Tomography Data (Sem 183/2, from Sep 21, 2009 03:15 PM to Sep 21, 2009 03:35 PM)
Abschlussvortrag Diplomarbeit
Event Oliver Hörbinger: Object Identification in non overlapping views (Sem 183/2, from Jul 07, 2009 04:15 PM to Jul 07, 2009 04:35 PM)
Spezifikationsvortrag DA
Event Dmitry Goldgof: Facial Motion Characterization through Strain Maps Analysis (Sem 183/2, from Jul 07, 2009 10:15 AM to Jul 07, 2009 11:00 AM)
Professor Dmitry Goldgof University of South Florida, Tampa, FL, USA
Event Angelika Garz: Texture based document layout analysis of glagolitic manuscripts (Sem 183/2, from Jun 30, 2009 04:15 PM to Jun 30, 2009 04:35 PM)
Spezifikationsvortrag DA
Event Thomas Hofer: Tracking von Peroxisomen in Neuronen (Sem 183/2, from Jun 23, 2009 04:15 PM to Jun 23, 2009 04:35 PM)
Event Georg Tanzmeister: Techniques for Image Forgery Detection (Sem 183/2, from Jun 09, 2009 04:35 PM to Jun 09, 2009 04:55 PM)
Abschlussvortrag Praktikum
Event Julian Stöttinger: Lonely but Attractive: Sparse Color Salient Points for Object Retrieval and Categorization (Sem 183/2, from Jun 09, 2009 04:15 PM to Jun 09, 2009 04:35 PM)
Test Talk
Event Martin Kampel: Recognition and Reconstruction in Archaeology and Surveillance (Sem 183/2, from Jun 03, 2009 10:00 AM to Jun 03, 2009 10:45 AM)
Event Andreas Ritzberger: Digitalization of Picture Frames (Sem 183/2, from Jun 02, 2009 04:35 PM to Jun 02, 2009 04:55 PM)
Abschlussvortrag Praktikum
Event Helmut Steiner: Fully Automated Modelling, Localization and Segmentation of 3D CT Hand Data (Sem 183/2, from Jun 02, 2009 04:15 PM to Jun 02, 2009 04:35 PM)
Spezifikationsvortrag DA
Event Lukas Fischer: From 2D to 3D Robust Medical Image Detection and Segmentation using Shape Particle Filters (Sem 183/2, from May 26, 2009 05:00 PM to May 26, 2009 05:30 PM)
Abschlussvortrag Praktikum + Spezifikationsvortrag DA
Event Tanacs Attila: Registration methods in medical image processing (Sem 183/2, from May 26, 2009 04:00 PM to May 26, 2009 04:45 PM)
Event Wieland Zellinger: TSP in 3D: A Computational Model for Human Performance on Surfaces? (Sem 183/2, from May 20, 2009 04:15 PM to May 20, 2009 04:35 PM)
Bachelor Spezifikationsvortrag
Event Karsten Lambers: The Nasca Geoglyphs of Palpa, Peru: New Insights from Archaeology, Photogrammetry, and GIS (, from May 18, 2009 03:00 PM to May 18, 2009 03:00 PM)
Event Florian Kromp: Automated Detection of Leucemic Populations Based on Minimal Residual Disease (MRD) Diagnostics Using Meanshift-Clustering (, from May 12, 2009 04:55 PM to May 12, 2009 05:15 PM)
(Abschlussvortrag Projektpraktikum)
Event David Major: Observation of the Dynamics of Autonomous Underwater Vehicles (Sem 183/2, from May 12, 2009 04:15 PM to May 12, 2009 04:35 PM)
Abschlussvortrag Informatikpraktikum
Event Christian Liensberger: Content-Based Skin Detection and its Application in Video Annotation (, from Apr 28, 2009 03:20 PM to Apr 28, 2009 03:40 PM)
Abschlussvortrag Diplomarbeit
Event Christian Liensberger: Reconstruction of high resolution images by super-resolution (, from Apr 28, 2009 03:00 PM to Apr 28, 2009 03:20 PM)
Abschlussvortrag Praktikum
Event Eric Andres: Adaptive Pixel Size Reconstruction (Sem 183/2, from Apr 27, 2009 04:00 PM to Apr 27, 2009 05:00 PM)
Event Johannes Schmid: Various Image Analysis Approaches for Cytometry of Biological Signaling Processes (Sem 183/2, from Mar 10, 2009 04:15 PM to Mar 10, 2009 05:00 PM)
Ao.Univ.Prof. Johannes A. Schmid, Zentrum f. Biomolekulare Medizin und Pharmakologie, Inst. f. Gefäßbiologie und Thromboseforschung, Medizinische Universität Wien
Event Peter Widhalm: Robuste Beinachsenbestimmung mittels Acitve Shape Models (, from Jan 20, 2009 04:00 PM to Jan 20, 2009 04:00 PM)
DA-Abschlussvortrag: Automatic Assessment of the Knee Alignment Angles on Full-limb Radiographs
Event Spherical Wavelets - A new tool for 3D shape representation (Sem 183/2, from Nov 28, 2008 02:00 PM to Nov 28, 2008 03:00 PM)
Praktikums-Abschlussvortrag Ernst Schwartz
Event Evaluierung der Auswirkungen einer Transposition der super-aortischen Gefässe auf die postoperative Bewegungsdynamik der Aorta (Sem 183/2, from Nov 28, 2008 02:00 PM to Nov 28, 2008 03:00 PM)
DA-Definitionsvortrag Ernst Schwartz
Event Automatic Segmentation of Capillary Vessels and Measurement of Doppler Flow Speed in OCT Data (Sem 183/2, from Nov 28, 2008 02:00 PM to Nov 28, 2008 03:00 PM)
DA-Defintion Eva Dittrich
Event Thinning Based Eccentricity on Volumetric Data (Sem 183/2, from Nov 28, 2008 02:00 PM to Nov 28, 2008 03:00 PM)
Bakk-Abschlussvortrag Martin Reiterer
Event Stefan Reiterer: Enhancement of the Readability in Historical Documents (SEM 183-2, from Nov 04, 2008 04:00 PM to Nov 04, 2008 05:00 PM)
Historical documents contain a lot of useful and important but, because of their low quality, hardly readable information. To make the text readable to philologists, the pages of the manuscripts are digitized and in a following step their quality is enhanced. Depending on the kind and age of the documents, different techniques from the domain of digital image processing can be applied to enhance them. For example, the high-frequency noise can be removed, miscellaneous thresholding approaches applied, uneven background of the documents removed, and much more. This presentation contains a comparison of previously proposed methods as well as a special approach, specific to multispectral recordings of the documents. The methods are tested on real and synthetic data. To evaluate the results, a set of synthetically generated test-data was used. After the enhancement of the testdata with the proposed methods, an OCR-program was applied to analyze the readability of the resulting images.
Event Marco Ross: Computer aided analysis of ancient brick walls (SEM 183-2, from Nov 04, 2008 04:00 PM to Nov 04, 2008 05:00 PM)
This report is about a method to automatically segment colour images of brick walls, in order to classify regions as brick or mortar material. Furthermore geometrical features of bricks shall be extracted. A support vector machine is used to perform a pixel-based classification of colour images and standard statistical methods are applied to extract the requested features from the segmented regions. During the experimental phase different approaches (e.g. Support Vector Machines, watershed segmentation and morphological operations) were followed for the diffcult task of segmentation, since the quality of the segmentation is critical to the whole process. In general the pixel-based SVM classifier performed out best. As a bonus the SVM also was the computationally least expensive variant that was tested. A linear kernel function is used, so the classification can be done by a simple perceptron evaluation. For future applications it is proposed to exhaust the ease of computation by applying an online perceptron training during manual post-processing.
Event Sequence of Experts Transforms for Lossless Dimensionality Reduction (Seminarraum 183-2, from Oct 21, 2008 04:00 PM to Oct 21, 2008 04:30 PM)
Event Short Introduction of New PRIP members (Sem 183-2, from Oct 17, 2008 04:40 PM to Oct 17, 2008 05:10 PM)
Event CG-Konversatorium (PRIP-talks) (Sem186, from Oct 17, 2008 10:00 AM to Oct 17, 2008 11:45 AM)
Event Using Spectral and Spatial Information for Character Segmentation in Multispectral Images (Seminarraum 183/2, from Oct 07, 2008 04:15 PM to Oct 07, 2008 05:00 PM)
This PhD specification talk first reviews the work done so far in document image analysis, along them especially the enhancement of the readability in multispectral images. The next contribution and main part of the work covers the segmentation of characters in multispectral images. Since the application is based on ancient manuscripts there are challenges which are not encountered in “modern” document images, above all the fading out of ink, injuries through humidity and so on. These vitiations are caused through the aging process. Therefore multispectral imaging has been proven to be of value for the cquisition of such degraded documents. The segmentation of the characters is then based on the combination of spectral and spatial information. The main contribution is to model the character behaviour in the multispectral image data. A solution includes the usage of Markov Random Fields (MRF) and Conditional Random Fields (CRF) where local and global features are taken into account. The approach will combine local classification, local features and global features.
Event A Character Recognition System of Ancient Manuscripts (Seminarraum 183/2, from Oct 07, 2008 04:15 PM to Oct 07, 2008 05:00 PM)
Optical Character Recognition (OCR) has been a regarded research topic in the last century. Nowadays the main issues of OCR are solved. Since OCR systems are base upon binary images of the text, their results are still poor if the text is degraded. In this thesis a codex consisting of ancient manuscripts is investigated. Due to environmental effects the characters of the analyzed codex are washed out which leads to poor results gained by state of the art binarization methods. Hence, a segmentation free approach based on local descriptors is being developed. Regarding local information allows for recognizing characters that are only partially visible and have a high interclass variance due to different writers. In order to recognize a character the local descriptors are initially classified with a Support Vector Machine (SVM) and then identified by a voting scheme of neighboring local descriptors. In this talk preliminary results of the proposed method are presented and future developments will be discussed.
Event Digital Bayon Project (Sem183-2, from Sep 08, 2008 02:00 PM to Sep 08, 2008 03:00 PM)
Event Morphological Processing and Segmentation of Colour Images (Seminar Room 183/2, from Jun 11, 2008 09:00 AM to Jun 11, 2008 11:00 AM)
Habilitation Colloquium
Event Long Term Motion Detection (Sem 183, from May 20, 2008 05:05 AM to May 20, 2008 05:30 AM)
Florian Dorn (Praktikumsabschlussvortrag)
Event Hierarchical Annotation Tool (Sem 183/2, from Apr 21, 2008 03:00 PM to Apr 21, 2008 03:45 PM)
Martin Hoch
Event Bildkategorisierung anhand von Farb- und Texturmerkmalen (Sem 183, from Mar 11, 2008 04:00 PM to Mar 11, 2008 04:30 PM)
Name: Thomas Pönitz Art: Praktikumsendbericht
Event Transparent Software Methodologies for Image Processing (Sem 183, from Dec 20, 2007 01:00 PM to Dec 20, 2007 02:00 PM)
Event Automatische Erkennung der Partikelgrößenverteilung von Wolfram-Carbid-Kristalliten in REM-Bildern (Sem183-2, from Nov 13, 2007 04:15 PM to Nov 13, 2007 05:00 PM)
Die automatische Ermittlung der Partikelgrößenverteilung von Hartmetallen ist eine Zeit und Kosten sparende Möglichkeit der Materialanalyse. Dazu werden die zu prüfenden Metalle mit chemischen Verfahren vorbereitet und per Rasterelektronenmikroskop-(REM-)Aufnahmen untersucht. Ausschlaggebend für eine gute Materialqualität sind eine möglichst konstante Partikelgröße sowie Partikelform. In dieser Arbeit werden zwei Methoden vorgestellt welche die Analyse der Partikelgrößenverteilung von Wolfram-Carbid-(WC-)Kristalliten automatisieren. Beide Methoden bauen auf der Distanztransformation auf. Der erste Segmentierungsansatz verwendet eine Watershedtransformation, der zweite eine Funktion, die den Umfang der Partikel eruiert. Die Ergebnisse beider Methoden werden mit den manuell gewonnenen Resultaten verglichen.
Event Sparse MRF Appearance Models for Fast Anatomical Structure Localisation (, from Oct 28, 2007 05:42 PM to Oct 28, 2007 05:42 PM)
Image segmentation methods like active shape models, active appearance models or snakes require an initialisation that guarantees a considerable over- lap with the object to be segmented. In this paper we present an approach that localises anatomical structures in a global manner by means of Markov Ran- dom Fields (MRF). It does not need initialisation, but finds the most plausible match of the query structure in the image. It provides for precise, reliable and fast detection of the structure and can serve as initialisation for more detailed segmentation steps. Sparse MRF Appearance Models (SAMs) encode a priori information about the geometric configurations of interest points, local features at these points and local features along the edges of adjacent points. This information is used to formulate a Markov Random Field and the mapping of the modeled object (e.g. a sequence of vertebrae) to the query image interest points is performed by the MAX- S UM algorithm. The local image information is captured by novel symmetry-based in- terest points and local descriptors derived from Gradient Vector Flow. Ex- perimental results are reported for two data-sets showing the applicability to complex medical data.
Event Riverbed Grain Size Distribution Estimation from Photographic Images (Seminarraum 183-2, from Oct 23, 2007 05:00 PM to Oct 23, 2007 05:30 PM)