archive-nl.com » NL » T » TUDELFT.NL

Total: 79

Choose link from "Titles, links and description words view":

Or switch to "Titles and links view".
  • Advanced School for Computing and Imaging
    parameterized models and implicitly parameterized models In the first class of models often referred to as snakes a parameterized curve or surface is evolved in time to capture object boundaries In the second class of models often referred to as level sets the curve or surface is represented by the zero level set of a higher dimensional function This representation has certain advantages most notably that a change in topology of the curve or surface during the evolution is effectively facilitated For both classes issues related to initialization optimization user interaction and the incorporation of prior knowledge will be discussed Furthermore a large number of applications will be shown 2 Statistical models Lecturer dr ir B P F Lelieveldt Statistical models capture the shape of an object from a training population as an average shape and a number of characteristic variations These models have been initially developed for shape analysis and gaining insight into typically occurring anatomical variations Apart from shape analysis the trained eigenvariations can also be applied to image segmentation by restricting the search space for the model matching to statistically plausible directions Contrary to the deformable models mentioned earlier they integrate population based a priori knowledge about shape and image appearance into the segmentation further increasing robustness During this course two types of statistical models will be treated Active shape models describe the distribution of a set of characteristic landmark points ASMs can be used for image segmentation by using local intensity models to find update points for each landmark and deforming the model within the statistically trained limits Active Appearance Models simultaneously describe the shape and the intensity of the object of interest as seen in an image patch Like Active Shape Models a model of the landmark distribution captures the shape variability whereas intensities are modeled by mapping the object patches to the shape average and determining gray value eigenvariations Model matching is realized by deforming the model in such a way that it blends in with the target image again constraining the deformation to the statistically trained limits The course will treat the basic concepts behind Active Shape and Appearance models 2D and 3D and will discuss several medical and non medical applications facial recognition object tracking In addition a more superficial overview of alternative statistical modeling methods such as medial models statistical deformation models and probabilistic atlases is provided 3 Pattern recognition approaches to image segmentation Lecturer dr M de Bruijne IT University Copenhagen Image segmentation can be formulated as a pattern recognition problem Once an image is divided into elements one can segment an object of interest by classifying each element as belonging to the object or not To this end features need to be computed for each element and a classifier must be trained to map feature vectors into object labels The elements can be simply voxels or pixels or other primitives such as the output of a watershed segmentation or line elements obtained by ridge detection etc The basic concepts

    Original URL path: http://www.asci.tudelft.nl/pages/courses.php?course_id=3 (2016-01-09)
    Open archived version from archive


  • Advanced School for Computing and Imaging
    of Twente ir Robert de Groote University of Twente Duration 4 full days Lectures half of each day Computer laboratories other half of the day using dataflow analysis tools and real time multiprocessor systems to exercise the course material and tasks Registration Costs Register through the ASCI website PhD students of research schools ASCI DISC ImagO IPA OzsL and SIKS can take part of the regular ASCI courses free of charge The course fee for other PhD students amounts to 500 The course fee for non PhD students amounts to 1200 Closing date registration November 6 2015 Description In this course we present dataflow analysis methods that have shown to be useful for the analysis and optimization of real time stream processing applications We explain the basics of the dataflow analysis theory as well as state of the art analysis techniques will be explained We furthermore present software and hardware techniques that improve the system s analysability and the accuracy of the analysis results Practical examples will be used to demonstrate the effectiveness of the presented theory Small exercises and hands on sessions with tools and practical multiprocessor systems after each lecture help the participant to evaluate and master the presented methods Examples of safety critical real time stream processing applications are software defined radios for car to car communication and car radars for automatic emergency breaking These applications are executed on embedded multiprocessor systems Programming of these systems is challenging because despite that these applications are concurrent dynamic and share the system s resources they must deliver the correct information at predefined points in time Dataflow models and tools simplify the design analysis and optimization of these applications The course is intended for computer scientists electrical engineers and PhD students or researchers in the related disciplines that are interested

    Original URL path: http://www.asci.tudelft.nl/pages/courses.php?course_id=19 (2016-01-09)
    Open archived version from archive

  • Advanced School for Computing and Imaging
    University of Technology Maastricht University Prof Nicolai Petkov PhD University of Groningen Computer Lab assistants To be announced Dates 2 fulltime weeks Lectures half day from Monday 9 November 2015 till Friday 13 November 2015 and from Monday 16 November 2015 till Thursday 19 November 2015 Computer laboratories other half day using Mathematica 10 to exercise the course material and tasks Total duration 27 oral lectures of 45 minutes each and 27 hours hands on training Registration Register through the ASCI website Registration for course and exam is free for TU e ASCI ImagO students and employees of industries officially collaborating with TU e BME For registration as contractant with TU e to do an official exam for 2 5 ECTS as non TU e student see STU registration form Costs 500 per course Costs for industrial participants 1200 invoice will be sent by ASCI after registration Description In this course we give a modern mathematical and brain inspired approach to geometric reasoning exploiting multi scale differential geometry for medical image analysis as a branch of computer vision We try to keep the analogy with stages in the human visual system as close as possible We design image analysis algorithms by carefully studying the requirements physical analogies and from first principles Modern often optical brain imaging methods will be discussed and recent discoveries of functional brain mechanisms in visual perception Among the topics covered are robust high order derivative operators for 2D and 3D images detecting invariant features such as ridges corners T junctions etc multi scale analysis of 2D and 3D shape motion from image sequences depth from stereo multi orientation analysis for contextual operations and the use of contemporary well understood mathematical tools from differential geometry and tensor analysis The majority of the examples discussed are from 2D

    Original URL path: http://www.asci.tudelft.nl/pages/courses.php?course_id=20 (2016-01-09)
    Open archived version from archive

  • Advanced School for Computing and Imaging
    45 17 30 Afternoon Matlab exercises Course contents This graduate course is intended for Ph D students that use or are planning to use pattern recognition of their own research They are facing a research problem that may partly be solved by automatic classifiers but also requires field specific knowledge to obtain an acceptable solution The statistical pattern recognition techniques will be examined with an emphasis on the generalization capabilities of learning systems The course is given for Ph D students of the Advanced School for Computing and Imaging ASCI Postdocs and external Ph D students may also attend against a moderate fee It is assumed that the student has some background in linear algebra and statistics but not specifically in pattern recognition The course will be given once a year in a one week block More than half of the time will be used for hands on experience using Matlab The students are expected to work in groups of two on these Matlab exercises on one of the 10 computers that are available In case you want to use your own laptop the Matlab software should be installed beforehand see the section Course material for the required software The

    Original URL path: http://www.asci.tudelft.nl/pages/courses.php?course_id=5 (2016-01-09)
    Open archived version from archive

  • Advanced School for Computing and Imaging
    Nicolai Petkov PhD University of Groningen Computer Lab assistants To be announced Dates 2 fulltime weeks Lectures half day from Monday 9 February 2015 till Friday 13 February 2015 and from Monday 23 February 2015 till Thursday 26 February 2015 Computer laboratories other half day using Mathematica 10 to exercise the course material and tasks Total duration 27 oral lectures of 45 minutes each and 27 hours hands on training Registration Register through the ASCI website here Registration for course and exam is free for TU e ASCI ImagO students and employees of industries officially collaborating with TU e BME For registration as contractant with TU e to do an official exam for 2 5 ECTS as non TU e student see see STU registration form Costs 500 per course Costs for industrial participants 1200 invoice will be sent by ASCI after registration Description In this course we give a modern mathematical and brain inspired approach to geometric reasoning exploiting multi scale differential geometry for medical image analysis as a branch of computer vision We try to keep the analogy with stages in the human visual system as close as possible We design image analysis algorithms by carefully studying the requirements physical analogies and from first principles Modern often optical brain imaging methods will be discussed and recent discoveries of functional brain mechanisms in visual perception Among the topics covered are robust high order derivative operators for 2D and 3D images detecting invariant features such as ridges corners T junctions etc multi scale analysis of 2D and 3D shape motion from image sequences depth from stereo multi orientation analysis for contextual operations and the use of contemporary well understood mathematical tools from differential geometry and tensor analysis The majority of the examples discussed are from 2D 3D and 4D 3D

    Original URL path: http://www.asci.tudelft.nl/pages/courses.php?course_id=2 (2016-01-09)
    Open archived version from archive

  • Advanced School for Computing and Imaging
    The workshop starts with 5 companies and 1 governmental organization who will present their practical business challenges to be followed by an intense week of analyzing discussing modeling and accelerating solutions for the business cases Why participate In a collaborative and creative environment as ICT with Industry there will be many opportunities to expand your research and industrial network The workshop is expected to lead to a number of new

    Original URL path: http://www.asci.tudelft.nl/pages/events.php?event_id=17 (2016-01-09)
    Open archived version from archive

  • Advanced School for Computing and Imaging
    IPN ICT OPEN 2015 ASCI track Call for Participation All abstracts must be submitted no later than 15 31 December 2014 UTC 02 00 TIME SCHEDULE 15 December 2014 deadline submission abstracts 31 December 2014 EXTENDED deadline submission abstracts 30 January 2015 notification of outcome evaluation 24 25 March 2015 ICT OPEN 2015 at De Flint Amersfoort ICT OPEN 2015 ASCI track COMMITTEE Clemens Grelck Universiteit van Amsterdam chair Alexandru

    Original URL path: http://www.asci.tudelft.nl/pages/events.php?event_id=15 (2016-01-09)
    Open archived version from archive

  • Advanced School for Computing and Imaging
    of research contributions as an extended abstract to ICT Open and as a full paper to ASCI Open is explicitly encouraged Costs ASCI will reimburse the conference fee and accommodation expenses up to EUR 60 00 per person per night for all members participating in ICT Open and ASCI Open 2015 First claim such cost from your own university after the conference ASCI will contact your group in order to settle this PROGR AMME ASCI Open 2015 20th Annual Conference of the Advanced School for Computing and Imaging http www asci tudelft nl De Flint Amersfoort March 23 2015 PROGRAMME 10 00 Arrival at De Flint with coffee and snacks 10 30 Welcome Clemens Grelck University of Amsterdam 10 40 Opening Talk Rob van Nieuwpoort Netherlands eScience Center 15 Years of Divide and Conquer on the DAS System 11 30 Coffee 12 00 Session 1 Norman Jaklin Utrecht University Path cost Analysis and Real Time Path Computation in Weighted Regions Zhenyang Li University of Amsterdam Attributes Make Sense on Segmented Objects Alexandru Uta VU Amsterdam MemEFS an Elastic In Memory Runtime File System 13 00 Lunch 14 00 Session 2 Samaneh Abbasi TU Eindhoven Automated Orientation Score based Retinal Vessel Segmentation of Scanning Laser Ophthalmoscope Immages short talk Fan Huang TU Eindhoven Multiple Fundus Features in Early Diabetes Detection short talk Alexey Ilyushkin TU Delft Scheduling Workloads of Workflows with Unknown Task Runtimes Song Wu Leiden University RIFF Retina inspired Invariant Fast Feature Descriptor Zhongyu Lou University of Amsterdam Extracting Primary Objects by Video Co Segmentation Nicolae Vladimir Bozdog VU Amsterdam PeerMatcher Decentralized Partnership Formation 15 30 Coffee 16 00 Session 3 Wouter van Toll Utrecht University Towards Believable Crowds A Generic Multi Level Framework for Agent Navigation Jiong Zhang TU Eindhoven Numerical Approaches for Linear Left invariant Diffusions on

    Original URL path: http://www.asci.tudelft.nl/pages/events.php?event_id=16 (2016-01-09)
    Open archived version from archive