Boris Flach

Combinatorial Image Analysis

This volume presents the proccedings of the 11th International Workshop on Combinatorial Image Analysis. IWCIA 2006 was the 11th in a series of international workshopfs devoted to combinatorial image analysis. Prior meetings took place in Paris (France 1991), Ube (Japan 1992), Wahington DC (USA 1994), Lyon (France 1995), Hiroshima (Japan 1997), Madras (India 1999), Philadelphia (USA 2001), Palermo (Italy 2003) and Auckland (New Zealand 2004). For this workshop we received 59 papers from all over the world. Each paper was assigned to three independent referees and carefully revised. Finally, we selected 34 papers for the conference based on content, significance, relevance, and presentation. Conference papers are presented in this volume in the order they were presented at the conference. The topics of the conference covered combinatorial image analysis, grammars and models for analysis and recognition of scenes or images, combinatorial topology and geometry for images, digital geometry of curves or surfaces, algebraic approaches to image processing, image, point-clouds or surface registration as well as fuzzy and probabilistic image analysis. The programm followed a single-track format with presentations of all published conference papers. Non-overlapping oral and poster sessions ensured that all attendees had opportunities to interact personny with presenters. Among the highlights of the meeting were the talks of our two invited speakers, renowned experts in the field of descrete geometry, digital topology, and image analysis. - David Coeurjolly (University of Lyon, France): Computational Aspects of Digital Plane and Hyperplane Recognition - Longin Jan Latecki (Temple University, Philadelphia, USA): Polygonal Approximation of Point Sets.

Unifying Registration and Segmentation for Multi-sensor Images

We propose a method for unifying registration and segmentation of multi-modal images assuming that the hidden scene model is a Gibbs probability distribution.

Combining Shape Priors and MRF-Segmentation

We propose a combination of shape prior models with Markov Random Fields. The model allows to integrate multiple shape priors and appearance models into MRF-models for segmentation. We discuss a recognition task and introduce a general learning scheme. Both tasks are solved in the scope of the model and verified experimentally.

A Probabilistic Segmentation Scheme

We propose a probabilistic segmentation scheme, which is widely applicable to some extend. Besides the segmentation itself our model incorporates object specific shading. Dependent upon application, the latter is interpreted either as a perturbation or as meaningful object characteristic. We discuss the recognition task for segmentation, learning tasks for parameter estimation as well as different formulations of shading estimation tasks.

Polarized actin and VE-cadherin dynamics regulate junctional remodelling and cell migration during sprouting angiogenesis

VEGFR-2/Notch signalling regulates angiogenesis in part by driving the remodelling of endothelial cell junctions and by inducing cell migration. Here, we show that VEGF-induced polarized cell elongation increases cell perimeter and decreases the relative VE-cadherin concentration at junctions, triggering polarized formation of actin-driven junction-associated intermittent lamellipodia (JAIL) under control of the WASP/WAVE/ARP2/3 complex. JAIL allow formation of new VE-cadherin adhesion sites that are critical for cell migration and monolayer integrity. Whereas at the leading edge of the cell, large JAIL drive cell migration with supportive contraction, lateral junctions show small JAIL that allow relative cell movement. VEGFR-2 activation initiates cell elongation through dephosphorylation of junctional myosin light chain II, which leads to a local loss of tension to induce JAIL-mediated junctional remodelling. These events require both microtubules and polarized Rac activity. Together, we propose a model where polarized JAIL formation drives directed cell migration and junctional remodelling during sprouting angiogenesis.The formation of new blood vessels requires both polarized cell migration and coordinated control of endothelial cell contacts. Here, Cao and colleagues describe at the sub-cellular level the cytoskeletal and cell junction dynamics regulating these processes upon VEGF-induced cell elongation.

Modelling composite shapes by Gibbs random fields

We analyse the potential of Gibbs Random Fields for shape prior modelling. We show that the expressive power of second order GRFs is already sufficient to express spatial relations between shape parts and simple shapes simultaneously. This allows to model and recognise complex shapes as spatial compositions of simpler parts.

Joint non-rigid motion estimation and segmentation

Usually object segmentation and motion estimation are considered (and modelled) as different tasks. For motion estimation this leads to problems arising especially at the boundary of an object moving in front of another if e.g. prior assumptions about continuity of the motion field are made. Thus we expect that a good segmentation will improve the motion estimation and vice versa. To demonstrate this we consider the simple task of joint segmentation and motion estimation of an arbitrary (non-rigid) object moving in front of a still background. We propose a statistical model which represents the moving object as a triangular (hexagonal) mesh of pairs of corresponding points and introduce an provably correct iterative scheme, which simultaneously finds the optimal segmentation and corresponding motion field.

Objektsegmentierung durch Textur- und Randextraktion

Diese Arbeit beschaftigt sich mit der Segmentierung von einfach zusammenhangenden texturierten Objekten unbekannter Form in Bildern mit verrauschtem Hintergrund. Dabei wird vorausgesetzt, das die Objekte Rander haben, d.h. an ihren Grenzen treten Gradienten auf, die im Mittel starker als im Hintergrund sind. Eine weitere Annahme besteht darin, das die zu segmentierenden Objekte eine (nicht unbedingt homogene) Texturierung aufweisen, die sich von der im Hintergrund im Mittel unterscheidet. Unterscheidung im Mittel bedeutet hier, das es keine lokalen Mase gibt, die es erlauben die Textur bzw. den Rand eindeutig zu klassifizieren. Die Segmentierung der Objekte mus unabhangig von absoluten Grauwerten sowie absoluten Gradientenstarken sein und moglichst wenige nichtadaptive Parameter (Schwellen, etc.) enthalten.

Multiple Object Segmentation and Tracking by Bayes Risk Minimization

Motion analysis of cells and subcellular particles like vesicles, microtubules or membrane receptors is essential for understanding various processes, which take place in living tissue. Manual detection and tracking is usually infeasible due to large number of particles. In addition the images are often distorted by noise caused by limited resolution of optical microscopes, which makes the analysis even more challenging. In this paper we formulate the task of detection and tracking of small objects as a Bayes risk minimization. We introduce a novel spatio-temporal probabilistic graphical model which models the dynamics of individual particles as well as their relations and propose a loss function suitable for this task. Performance of our method is evaluated on artificial but highly realistic data from the 2012 ISBI Particle Tracking Challenge [8]. We show that our approach is fully comparable or even outperforms state-of-the-art methods.

Joint Segmentation and Registration Through the Duality of Congealing and Maximum Likelihood Estimate.

In this paper we consider the task of joint registration and segmentation. A popular method which aligns images and simultaneously estimates a simple statistical shape model was proposed by E. Learned-Miller and is known as.congealing. It considers the entropy of a simple, pixel-wise independent distribution as the objective function for searching the unknown transformations. Besides being intuitive and appealing, this idea raises several theoretical and practical questions, which we try to answer in this paper. First, we analyse the approach theoretically and show that the original congealing is in fact the DC-dual task (difference of convex functions) for a properly formulated Maximum Likelihood estimation task. This interpretation immediately leads to a different choice for the algorithm which is substantially simpler than the known congealing algorithm. The second contribution is to show, how to generalise the task for models in which the shape prior is formulated in terms of segmentation labellings and is related to the signal domain via a parametric appearance model. We call this generalisation unsupervised congealing. The new approach is applied to the task of aligning and segmenting imaginal discs of Drosophila melanogaster larvae.