Skip to content. Skip to navigation
CIM Menus

AMAT: Medial Axis Transform for Natural Images

Stavros Tsogas
University of Toronto

June 20, 2017 at  11:00 AM
McConnell Engineering Room 437


The medial axis transform (MAT) is a powerful shape abstraction that has been successfully used in shape editing, matching and retrieval. Despite its long history, the MAT has not found widespread use in tasks involving natural images, due to the lack of a generalization that accommodates color and texture. In this talk I will present our recent work on Appearance-MAT (AMAT), an approach that frames the MAT of natural images as a weighted geometric set cover problem. We make the following contributions:
i) we extend previous medial point detection methods for color images, by associating each medial point with a local scale;
ii) inspired by the invertibility property of the binary MAT, we also associate each medial point with a local encoding that allows us to invert the AMAT, reconstructing the input image;
iii) we describe a clustering scheme that takes advantage of the additional scale and appearance information to group individual points into medial branches, providing a shape decomposition of the underlying image regions.
In our experiments, we show state of the art performance in medial point detection on Berkeley Medial AXes (BMAX500), a new dataset of medial axes based on the established BSDS500 database. We also measure the quality of reconstructed images from the same dataset, obtained by inverting their computed AMAT. Our approach delivers significantly better reconstruction quality with respect to three baselines, using just 10% of the image pixels.

Short bio:

I obtained my diploma in electrical and computer engineering from the National Technical University of Athens (NTUA) in 2011. After that I spent 5 years at the Center for Visual Computing (CVC) at CentraleSupelec in Paris, as a PhD student under the supervision of Prof. Iasonas Kokkinos, and as a research engineer, working with Prof. Nikos Paragios. As of October 2016, I am a postdoctoral fellow at the University of Toronto, working with Prof. Sven Dickinson. My interests include shape-based and part-based object representations, segmentation, and deep learning.