Publications

From neonatal to adult brain MR image segmentation in a few seconds using 3D-like fully convolutional network and transfer learning

By Yongchao Xu, Thierry Géraud, Isabelle Bloch

2017-06-12

In Proceedings of the 23rd IEEE international conference on image processing (ICIP)

Abstract

Brain magnetic resonance imaging (MRI) is widely used to assess brain developments in neonates and to diagnose a wide range of neurological diseases in adults. Such studies are usually based on quantitative analysis of different brain tissues, so it is essential to be able to classify them accurately. In this paper, we propose a fast automatic method that segments 3D brain MR images into different tissues using fully convolutional network (FCN) and transfer learning. As compared to existing deep learning-based approaches that rely either on 2D patches or on fully 3D FCN, our method is way much faster: it only takes a few seconds, and only a single modality (T1 or T2) is required. In order to take the 3D information into account, all 3 successive 2D slices are stacked to form a set of 2D color images, which serve as input for the FCN pre-trained on ImageNet for natural image classification. To the best of our knowledge, this is the first method that applies transfer learning to segment both neonatal and adult brain 3D MR images. Our experiments on two public datasets show that our method achieves state-of-the-art results.

Continue reading

Parallel learning portfolio-based solvers

By Tarek Menouer, Souheib Baarir

2017-06-01

In Proceedings of the international conference on computational science (ICCS)

Abstract

Exploiting multi-core architectures is a way to tackle the CPU time consumption when solving SAT- isfiability (SAT) problems. Portfolio is one of the main techniques that implements this principle. It consists in making several solvers competing, on the same problem, and the winner will be the first that answers. In this work, we improved this technique by using a learning schema, namely the Exploration- Exploitation using Exponential weight (EXP3), that allows smart resource allocations. Our contribution is adapted to situations where we have to solve a bench of SAT instances issued from one or several sequence of problems. Our experiments show that our approach achieves good results.

Continue reading

Well-composedness in Alexandrov spaces implies digital well-composedness in $Z^n$

By Nicolas Boutry, Laurent Najman, Thierry Géraud

2017-06-01

In Discrete geometry for computer imagery – proceedings of the 20th IAPR international conference on discrete geometry for computer imagery (DGCI)

Abstract

In digital topology, it is well-known that, in 2D and in 3D, a digital set $X \subseteq Z^n$ is digitally well-composed (DWC), i.e., does not contain any critical configuration, if its immersion in the Khalimsky grids $H^n$ is well-composed in the sense of Alexandrov (AWC), i.e., its boundary is a disjoint union of discrete $(n-1)$-surfaces. We show that this is still true in $n$-D, $n \geq 2$, which is of prime importance since today 4D signals are more and more frequent.

Continue reading

Explicit state model checking with generalized büchi and rabin automata

By Vincent Bloemen, Alexandre Duret-Lutz, Jaco van de Pol

2017-05-22

In Proceedings of the 24th international SPIN symposium on model checking of software (SPIN’17)

Abstract

In the automata theoretic approach to explicit state LTL model checking, the synchronized product of the model and an automaton that represents the negated formula is checked for emptiness. In practice, a (transition-based generalized) Büchi automaton (TGBA) is used for this procedure.This paper investigates whether using a more general form of acceptance, namely transition-based generalized Rabin automata (TGRAs), improves the model checking procedure. TGRAs can have significantly fewer states than TGBAs, however the corresponding emptiness checking procedure is more involved. With recent advances in probabilistic model checking and LTL to TGRA translators, it is only natural to ask whether checking a TGRA directly is more advantageous in practice.We designed a multi-core TGRA checking algorithm and performed experiments on a subset of the models and formulas from the 2015 Model Checking Contest. We observed that our algorithm can be used to replace a TGBA checking algorithm without losing performance. In general, we found little to no improvement by checking TGRAs directly.

Continue reading

Object tracking by hierarchical decomposition of hyperspectral video sequences: Application to chemical gas plume tracking

By Guillaume Tochon, Jocelyn Chanussot, Mauro Dalla Mura, Andrea Bertozzi

2017-04-20

In IEEE Transactions on Geoscience and Remote Sensing

Abstract

It is now possible to collect hyperspectral video sequences at a near real-time frame rate. The wealth of spectral, spatial and temporal information of those sequences is appealing for various applications, but classical video processing techniques must be adapted to handle the high dimensionality and huge size of the data to process. In this article, we introduce a novel method based on the hierarchical analysis of hyperspectral video sequences to perform object tracking. This latter operation is tackled as a sequential object detection process, conducted on the hierarchical representation of the hyperspectral video frames. We apply the proposed methodology to the chemical gas plume tracking scenario and compare its performances with state-of-the-art methods, for two real hyperspectral video sequences, and show that the proposed approach performs at least equally well.

Continue reading

Seminator: A tool for semi-determinization of omega-automata

By František Blahoudek, Alexandre Duret-Lutz, Mikuláš Klokočka, Mojmír Křetínský, Jan Strejček

2017-04-03

In Proceedings of the 21th international conference on logic for programming, artificial intelligence, and reasoning (LP<AR’17)

Abstract

We present a tool that transforms nondeterministic $\omega$-automata to semi-deterministic $\omega$-automata. The tool Seminator accepts transition-based generalized Büchi automata (TGBA) as an input and produces automata with two kinds of semi-determinism. The implemented procedure performs degeneralization and semi-determinization simultaneously and employs several other optimizations. We experimentally evaluate Seminator in the context of LTL to semi-deterministic automata translation.

Continue reading

La pseudo-distance du dahu

By Edwin Carlinet, Yongchao Xu, Nicolas Boutry, Thierry Géraud

2017-03-21

In Actes d’ORASIS

Abstract

La distance de la barrière minimum est définie comme le plus petit intervalle de l’ensemble des niveaux de gris le long d’un chemin entre deux points dans une image. Pour cela, on considère que l’image est un graphe à valeurs sur les sommets. Cependant, cette définition ne correspond pas à l’interprétation d’une image comme étant une carte d’élévation, c’est-à-dire, un paysage continu d’une manière ou d’une autre. En se plaçant dans le cadre des fonctions multivoques, nous présentons une nouvelle définition pour cette distance. Cette définition, compatible avec l’interprétation paysagère, est dénuée de problèmes topologiques bien qu’en restant dans un monde discret. Nous montrons que la distance proposée est reliée à la structure morphologique d’arbre des formes, qui permet de surcroît un calcul rapide et exact de cette distance. Cela se démarque de sa définition classique, pour laquelle le seul calcul rapide n’est qu’approximatif.

Continue reading

Parallel satisfiability solver based on hybrid partitioning method

By Tarek Menouer, Souheib Baarir

2017-03-01

In Proceedings of the 25th euromicro international conference on parallel, distributed and network-based processing (PDP)

Abstract

This paper presents a hybrid partitioning method used to improve the performance of solving a Satisfiability (SAT) problems. The principle of our approach consist firstly to apply a static partitioning to decompose the search tree in finite set of disjoint sub-trees, than assign each sub-tree to one computing core. However it is not easy to choose the relevant branching variables to partition the search tree. We propose in this context to partition the search tree according to the variables that occur more frequently then others. The advantage of this method is that it gives a good disjoint sub- trees. However, the drawback is the imbalance load between all computing cores of the system. To overcome this drawback, we propose as novelty to extend the static partitioning by combining with a new dynamic partitioning that assure a good load balancing between cores. Each time a new waiting core is detected, the dynamic partitioning selects automatically using an estimation function the computing core which has the most work to do in order to partition dynamically its sub-tree in two parts. It keeps one part and gives the second part to the waiting core. Preliminary result show that a good speedup is achieved using our hybrid method.

Continue reading

Introducing the Dahu pseudo-distance

By Thierry Géraud, Yongchao Xu, Edwin Carlinet, Nicolas Boutry

2017-02-23

In Mathematical morphology and its application to signal and image processing – proceedings of the 13th international symposium on mathematical morphology (ISMM)

Abstract

The minimum barrier (MB) distance is defined as the minimal interval of gray-level values in an image along a path between two points, where the image is considered as a vertex-valued graph. Yet this definition does not fit with the interpretation of an image as an elevation map, i.e. a somehow continuous landscape. In this paper, based on the discrete set-valued continuity setting, we present a new discrete definition for this distance, which is compatible with this interpretation, while being free from digital topology issues. Amazingly, we show that the proposed distance is related to the morphological tree of shapes, which in addition allows for a fast and exact computation of this distance. That contrasts with the classical definition of the MB distance, where its fast computation is only an approximation.

Continue reading

Morphological analysis of brownian motion for physical measurements

By Élodie Puybareau, Hugues Talbot, Noha Gaber, Tarik Bourouina

2017-02-23

In Mathematical morphology and its application to signal and image processing – proceedings of the 13th international symposium on mathematical morphology (ISMM)

Abstract

Brownian motion is a well-known, apparently chaotic mo- tion affecting microscopic objects in fluid media. The mathematical and physical basis of Brownian motion have been well studied but not often exploited. In this article we propose a particle tracking methodology based on mathematical morphology, suitable for Brownian motion analysis, which can provide difficult physical measurements such as the local temperature and viscosity. We illustrate our methodology on simulation and real data, showing that interesting phenomena and good precision can be achieved.

Continue reading

Search

Tags