• Explore Membership
  • Student Services
  • Student Events
    Student Chapters
    MKS Instruments Awards
    Student Author Travel Grants
    Visiting Lecturers
    Lecturer Directory
    Travel Policies
  • Early Career Resources
  • Corporate Membership
  • SPIE Professional Magazine
Print PageEmail Page

Jacob Scharcanski

Prof. Jacob  Scharanski

Professor of Computer Science

UFRGS - Federal University of Rio Grande do Sul
Institute of Informatics
Av. Bento Goncalves 9500, Bloco 4

Porto Alegre  91509-900

tel: +55-51-3308-7128
fax: +55-51-3308-7308
E-mail: jacobs@inf.ufrgs.br
Web: http://www.inf.ufrgs.br/~jacobs

Area of Expertise

Image Processing, Computer Vision, Pattern Recognition, Image-based Measurements and Applications


Jacob Scharcanski received his BSEE and MSc from the Federal University of Rio Grande do Sul (Brazil), and his PhD in Systems Design Engineering from the University of Waterloo, Canada. Currently, he is a Professor (full) in Computer Science at the Federal University of Rio Grande do Sul (UFRGS), Brazil. He holds a cross appointment with the Department of Electrical Engineering at UFRGS, and is also an Adjunct Professor with the Department of Systems Design Engineering, University of Waterloo, Canada. He has graduated over 30 MS/PhD students, authored and co-authored over 150 refereed journal and conference papers, book chapters and books on image processing, computer vision, and image-based measurements. He delivered over 30 invited presentations worldwide including keynote addresses. Presently, he serves as an Associate Editor for two journals and has served on dozens of International Conference Committees. In addition to his academic activities, he has several technology transfers to the private sector. Prof. Scharcanski is a licensed professional engineer (PEO, Canada), Senior Member of IEEE, Member of SPIE, and serves as the Chair of the Technical Committee IEEE IMS TC-17 (Materials in Measurement) and as the Co-Chair of the Technical Committee IEEE IMS TC-19 (Imaging Measurements and Systems).

Lecture Title(s)

Medical Imaging and Measurements

Medical imaging measurements often involve modeling and modeling errors, and estimating the expected error of a model can be important in several applications (e.g. when estimating a tumor size and its potential growth, or shrinkage, in response to treatment). Typically, a model has tuning parameters, and these tuning parameters may change the model complexity. Often, we wish to minimize modeling errors and the model complexity, in other words, to get the 'big picture' we often sacrifice some of the small details. For example, estimating tumor growth (or shrinkage) in response to treatment requires modeling the tumor shape and size, which can be challenging for real tumors, and simplified models may be justifiable if the predictions obtained are informative (e.g. to evaluate the treatment effectiveness). This issue is closely related to machine learning and pattern recognition, and techniques of these areas can be adapted to resolve problems in medical imaging measurements. In this talk, we provide an overview of this area, and discuss open problems in medical imaging measurements and model selection in some detail.


From Imaging Data to Useful Visual Information and Measurements

In this talk, we address the problems of extracting relevant information from image data. We also introduce briefly the concepts and techniques often used in the automatic interpretation of phenomena based on imagery, or to make inferences based on models of such imagery data. When modeling and representing imaging measurements, we often are trying to describe the world (or a real world phenomenon) based on one or more images, and reconstruct some of its properties based on imagery data (like shape, texture or color). Actually, this is an ill-posed problem that humans can learn to solve effortlessly, but computer algorithms are prone to errors. Nevertheless, in some cases computers can surpass humans and interpret imagery more accurately, given the proper choice of data representations (i.e. features), as we discuss in this talk. In order to illustrate this presentation, several applications are discussed, focusing on areas such as medicine, biometrics, pulp and paper, soil sciences, porous media, surveillance, and human-machince interfaces.

Ready for the benefits of individual SPIE membership?
Join or Renew
Already a member? Get access to member-only content.
Sign In

Member-only Content:

These articles are available only to SPIE Members as a valuable resource.
Member-only content Icon
Icon denotes member-only content.

The Joe and Agnete Yaver Memorial Scholarship

SPIE Online Courses

At Your Pace - On Your Schedule

SPIE t-shirts, ties, and scarves are now available. Get free shipping for a limited time. Shop now.

2018 Salary Report