Date: Monday, February 10th 2014
rof. Alexandre Xavier Falcao Institute of Computing, Univ. of Campinas, Brazil
Room: 5161.0267 (Bernoulliborg)
The Image Foresting Transform: From the image domain to the feature space
The image foresting transform (IFT) is a tool for the design of image operators by choice of an adjacency relation and a connectivity function between image elements. An adjacency relationtransforms the image into a graph, whose image elements are the nodes and the arcs connect adjacent elements. A connectivity function assigns a value to any path in the graph. Several image operators are then simply reduced to a local processing operation on attributes of the forest (e.g., paths, path-values, root labels.
This framework has been successfully applied to image filtering, segmentation, representation, and analysis. The unification of some image operators helped to understand their relation, to create improved hybrid approaches, and to develop parallel implementation in hardware. We have also extended it from the image domain to the feature space, where data samples may be images, their objects, or other abstract entities. The choice of adjacency relation and connectivity function in this case led to supervised and unsupervised learning methods for pattern classification, with successful applications in biomedicine, biometry, geology, electricalengineering, remote sensing, and metallurgy. More recently, we have developed semi-supervised and active learning solutions for efficient annotation of large image datasets.
This lecture will start with motivation, definitions, and a short overview of how to choose adjacency relations and connectivity functions for some image processing problems. It will then present the IFT extension from the image domain to the feature space and concludewith open problems and on-going works on the IFT.
Biography:Alexandre Xavier Falcao is professor at the Institute of Computing, University of Campinas (UNICAMP), Brazil. He received a B.Sc. in Electrical Engineering from the Federal University of Pernambuco, Brazil, in 1988. He has worked in biomedical image processing, visualization, and analysis since 1991. In 1993, he received a M.Sc. in Electrical Engineering from UNICAMP. During 1994-1996, he worked with the Medical Image Processing Group at the Department ofRadiology, University of Pennsylvania, USA. He got his doctorate in Electrical Engineering from UNICAMP in 1996. In 1997, he worked in a research center (CPqD-TELEBRAS) developing methods for video quality assessment. He is professor of Computer Science at UNICAMP since1998. His main research interests include graph algorithms for image processing, image segmentation, volume visualization, content-based image retrieval, mathematical morphology, digital video processing, remote sensing image analysis, machine learning, pattern recognition, and biomedical image analysis.
Colloquium coordinators are Prof.dr. M. Aiello (e-mail :
Prof.dr. M. Biehl (e-mail:
This year, the University of Groningen has submitted four research projects to compete for the national Klokhuis Science Prize. The aim of this prize is to introduce a young and wide audience to academic research. The winning project will be...
Het project WIJS, het initiatief dat de Gemeente Groningen en de Hanzehogeschool in 2014 startten, is uitgebreid met vier partners: WIJ-Groningen, de Rijksuniversiteit Groningen, Alfa-college en Noorderpoort. Vandaag wordt de komst van de vier...
Non-executive directors (hereafter: directors) have to take a critical stance towards the top managers they supervise. This has been the dominant perspective among researchers and the media after the financial crisis of 2008 and recent major...