VISUM: 1st edition

The visum summer school 2013 will take place in Faculdade de Engenharia da Universidade do Porto between 5-12 of July, 2013.

Created with flickr slideshow.


Introduction to Image Processing and Machine Intelligence

This introductory course on Image Processing and Machine Intelligence aims to give the student the adroitness to understand and apply some of these following topics:

  • Basics
    • What’s is an image? Discrete and continuous images. Color images.
    • Filters.
    • Image alignment.
    • Image representation.
  • Image processing
    • Enhancement.
    • Restoration.
    • Segmentation.
    • Recognition.
  • Visualization

Professor Jaime S. Cardoso
INESC TEC, Faculdade de Engenharia, Universidade Porto


  • R.C. Gonzalez, R.E. Woods, Digital Image Processing, Prentice Hall, 2002.
  • A. Bovik, ed., Handbook of Image and Video Processing, Academic Press, 2000.
  • Forsyth and Ponce, Computer Vision: A Modern Approach, Prentice Hall, 2002.

Blind Image Restoration

In most experimental observations, the observed data is an imperfect representation of the original object degraded by the instrumental and environmental response. The aim of this lecture is provide an overview of proposed methodologies to restore linearly degraded observation with a special focus on inverses problems approaches.

After a brief description of the degraded data formation, the lecture will address the two main categories of problems:

  1. Non blind restoration: when the instrumental function is known,
  2. The blind restoration: when both original object and instrumental function are unknown and how to calibrate the instrumental function using only the observations.

This lecture will be illustrated with the special case of image deconvolution (i.e. when the instrumental function is linear and shift invariant) but more general linear problems will also be presented with experimental results in many applications (hyper-spectral astrophysical imaging, 3D microscopy imaging, medical video sequences, non destructive testing...).

Doctor Ferréol Soulez
Centre de Recherche Astrophysique de Lyon (CRAL), Université Claude Bernard - Lyon 1, Ecole Normale Supérieure de Lyon, Université de Lyon


  • Ferréol Soulez, Loïc Denis, Yves Tourneur, Eric Thiébaut: Blind deconvolution of 3D data in wide field fluorescence microscopy. ISBI 2012.
  • P Campisi, K Egiazarian, Blind image deconvolution: theory and applications, 2007.

Haptic Augmented Reality

Augmented Reality (AR) supplements our real world through visual cues and interaction with artificial objects. Recent technological advancements gave new sights to this discipline. Its applications are uncountable spanning medicine, robotics, entertainment, defence and security, among others.

Professor Matthias Harders
Computer Vision Laboratory, Department Information Technology and Electrical Engineering, Swiss Federal Institute of Technology Zurich (ETH Zurich)


  • Seokhee Jeon; Seungmoon Choi; Harders, M.; , "Rendering Virtual Tumors in Real Tissue Mock-Ups Using Haptic Augmented Reality," Haptics, IEEE Transactions on , vol.5, no.1, pp.77-84, Jan.-March 2012

Colour in Computer Vision

Colour information contained within an image can present with great detail data of scenes that it captures. Though its usage comprehends several different difficulties, the gains can be considerable. In this course it will be taught mainly the following topics:

  • Colour Basics.
  • Colour Representation.
  • Colour Constancy.

Professor Theo Gevers
Intelligent Systems Lab Amsterdam, Faculty of Science, University of Amsterdam


  • A. Gijsenij, Th. Gevers and J. van de Weijer, Computational Color Constancy: Overview and Experiments, IEEE Trans. on Image Processing (TIP), 2011.
  • Theo Gevers, Arjan Gijsenij, Joost van de Weijer, Jan-Mark Geusebroek, Color in Computer Vision: Fundamentals and Applications, Wiley, 2012.

Feature Detectors

A local feature is an image pattern which differs from its immediate neighborhood. It is usually associated with a change of an image property or several properties simultaneously. Local features can be points, but also edges or small image patches.
Feature detection is used in many computer vision algorithms as the initial step, so, a very large number of feature detectors have been developed. At an overview level, these feature detectors can be divided into the following groups: edge detectors, corner detectors and blob detectors. In this course, an overview of feature detectors is to be made, especially those whom are relevant in biomedical applications.

Professor Krystian Mikolajczyk
Faculty of Engineering & Physical Sciences, University of Surrey


  • T. Tuytelaars and K. Mikolajczyk, Local Invariant Feature Detectors: A Survey, Computer Graphics and Vision, Vol.3, No. 3, pp.177-280, 2007.
  • K. Mikolajczyk and T. Tuytelaars, Local Invariant Features, In Encyclopedia of Biometrics edited by Stan Li, Springer, 2008.

RGB-D cameras

The prevalence of affordable RGB-D cameras, such as Microsoft's Kinect and ASUS’s Xtion Pro Live Sensors, is driving a revolution of the landscape of computer vision and vision related research. The availability of high-resolution depth and visual information at video frame rates enables fundamentally novel approaches for several research problems such as dense camera tracking, 3D reconstruction, object recognition and human motion capture. The goal of this course is to present recent advances in 3D processing techniques for RGB-D sensors. The course will cover the following topics:

  • Sensor technology and calibration
  • Dense tracking
  • 3D reconstruction
  • Object recognition
  • Human motion capture

Doctor Juergen Sturm
Computer Vision Group, Technical University of Munich


  • J. Sturm, N. Engelhard, F. Endres, W. Burgard, D. Cremers, A Benchmark for the Evaluation of RGB-D SLAM Systems, In Proc. of the International Conference on Intelligent Robot Systems (IROS), 2012.

  • F. Steinbruecker, J. Sturm, D. Cremers, Real-Time Visual Odometry from Dense RGB-D Images, In Proc. of the Workshop on Live Dense Reconstruction with Moving Cameras at the Intl. Conf. on Computer Vision (ICCV), 2011


Professor Miguel Coimbra
Instituto de Telecomunicações do Porto, Faculdade de Ciências, Universidade Porto


Critical Health, S.A.

Carlos Manta Oliveira
Image Processing Manager


Marco Soares and André Sousa
Joint CEO


Marcelino Silva

Social Programme

Welcome drink

VISUM Summer School 2013 welcome drink will take place at 17º Restaurante & Bar.
With an astonishing view over Oporto City, you will have the opportunity to meet your colleagues and classmates during an informal cocktail.

Gala dinner

VISUM Summer School 2013 gala dinner will take place at Taylor's Cellar.
After a tasteful journey around the beautiful city of Oporto, VISUM 2013 Gala dinner will take place at one of the few wine cellars that still belong to the original families.


To be elligible to apply in visum summer school 2013, send an email to under the subject "[APPLICATION VISUM]" following the name of the applicant, with the following information:

  • CV with only 2 pages describing the academic background, webpage, other information that you may consider important.
  • Motivation letter.
  • Student Certificate.
  • And if you want to participate in the poster session send a possible title and abstract of a poster.

Important Dates

Application March, 1 March, 15
Notification of Acceptance March, 10 March, 18
Application UP and Academic community from Porto April, 3
Early Registration April, 10 April, 30
Late Registration May, 10

All deadline times will be at 23:59, GMT+0

We invite all UP and Academic community from Porto to attend visum 2013, with a special price. For more details, please send an email to, until April, 3.

VISUM summer school fees

Until 30th April After 1st May
students 400€ 500€
researchers 450€ 550€
industry 550€ 650€
*companion attending theorical lectures adds 50€ per session
**social programme and banquet companion adds a quantity to be defined

Aforementioned fees cover:

  • Full participation in lectures and practical sessions.
  • Lunches, coffee breaks, welcome drink and banquet.
  • Social programme.

Acceptance Letter for VISA

Participants requiring a Visa to travel to Portugal need to send to us the following information:

  • Full name.
  • Passport information: number, issue date and place, and expiration date.
  • Address to which you would like the acceptance letter to be sent to.

Organizing Committee

Jaime S. Cardoso INESC TEC, Faculdade de Engenharia da Universidade do Porto
Hélder P. Oliveira INESC TEC, Faculdade de Engenharia da Universidade do Porto
Ana Rebelo INESC TEC, Faculdade de Engenharia da Universidade do Porto
Ana F. Sequeira INESC TEC, Faculdade de Engenharia da Universidade do Porto
Ricardo Sousa IT, Faculdade de Ciências da Universidade do Porto

External Committee

André Matos Faculdade de Ciências Sociais e Humanas da Universidade Nova de Lisboa

Local Committee

Lucian Ciobanu INESC TEC
Eduardo Marques INESC TEC, Faculdade de Engenharia da Universidade do Porto

Logistic Committee

Isidro Ribeiro Faculdade de Engenharia da Universidade do Porto
Renata Rodrigues INESC TEC