Image processing and analysis using graphs

Back to Falcão's home page

Community Ordered Formation Theory and its Applications in Image Analysis (Uppsala University): Selected talks on Image Processing using Graphs

15th Iberoamerican Congress on Pattern Recognition (CIARP 2010): Design of pattern classifiers using optimum-path forest with applications in image analysis.

São Paulo Advanced School in Computing (2010): Graph-based image processing

Lecture 1: The Image Foresting Transform.

Lecture 2: Connected filters.

Lecture 3: Interactive and automatic image segmentation.

Lecture 4: Shape representation and description.

Lecture 5: Clustering and classification.

This course covers the image foresting transform and its applications in all steps of an image processing and analysis pipeline: filtering, segmentation, description and categorization.

Video of interactive segmentation by live-wire-on-the-fly.
Video of differential IFT segmentation by seed competition.
Video of the ordered optimum-path propagation during the IFT computation.
Video of object tracking based on automatic IFT segmentation by seed competition and motion estimation.

Video of automatic image segmentation using cloud system model and IFT delineation.

The Image Foresting Transform: Recent Advances and Perspectives.

The most recent talk about the IFT with pointers to the key works in the past 10 years and applications involving object tracking, image segmentation (interative and automatic --- segmentation based on cloud bank model) and patter recognition systems in biometry, remote sensing, and biomedical data analysis. This lecture was presented at the 16th International Conference on Digital Signal Processing in 2009. The following videos were presented during the talk.

The Image Foresting Transform from the Image Domain to the Feature Space.

This lecture reviews previous works on the IFT and presents its extension from the image domain to the feature space, where optimum-path forest classifiers can be projected. This talk was presented at the 8th International Symposium on Mathematical Morphology in 2007, at ESIEE in 2008 and at the University of Minnesota in 2008.

Image Foresting Transform: A Graph-Based Approach to Image Processing.

First lecture that introduces the Image Foresting Transform (IFT) and presents its use in the design of image processing operators. This talk was presented at the University of Iowa and University of Pennsylvania in 2004.

Last time this page was updated and we remembered to update this line: Jul 14th, 2009

Back to Falcão's home page