Ariana/Odyssée

"Extraction de contours et de régions dans les images"

Séminaire dans le cadre des doctoriales 2007

11 mai 2007
14 heures
Inria Salle Euler violet

format des présentations : 45 mn + 10mn questions

Jérôme Piovano, Odyssée :
"Efficient Segmentation of Piecewise Smooth Images"

Résumé :
We propose a fast and robust segmentation model for piecewise smooth images. Rather than modeling each region with global statistics, we introduce local statistics in an energy formulation. The shape gradient of this new functional gives a contour evolution controlled by local averaging of image intensities inside and outside the contour. To avoid the computational burden of a direct estimation, we express these terms as the result of convolutions. This makes an efficient implementation via recursive filters possible, and gives a complexity of the same order as methods based on global statistics. This approach leads to results similar to the general Mumford-Shah model but in a faster way, without solving a Poisson partial differential equation at each iteration. We apply it to synthetic and real data, and compare the results with the piecewise smooth and piecewise constant Mumford-Shah models.

Peter Horvath, projet Ariana
The "gas of circles" higher-order active contour model

Résumé :
Many image processing problems involve identifying the region in the image domain occupied by a given entity in the scene. Automatic solution of these problems requires models that incorporate significant prior knowledge about the shape of the region. Many methods for including such knowledge run into difficulties when the topology of the region is unknown a priori, for example when the entity is composed of an unknown number of similar objects. Higher-order active contours (HOACs) represent one method for the modelling of non-trivial prior knowledge about shape without necessarily constraining region topology, via the inclusion of non-local interactions between region boundary points in the energy defining the model.

The case of an unknown number of circular objects arises in a number of domains, e.g. medical, biological, nanotechnological, and remote sensing imagery. Regions composed of an a priori unknown number of circles may be referred to as a `gas of circles'. We present a HOAC model of a `gas of circles'. In order to guarantee stable circles, we conduct a stability analysis via a functional Taylor expansion of the HOAC energy around a circular shape, fixing one of the model parameters in terms of the others. Further analyzing the circle energy, we fix all but one of the parameters and solve the problem of 'phantom circles' by using an inflexion point instead of an energy minimum at the desired radius. We present the phase field version of our model, which gives more topological freedom and two orders of magnitude faster computation time than the contour version. In conjunction with a suitable likelihood energy, we apply the model to the extraction of tree crowns from aerial imagery, and show that the new model outperforms other techniques.