
S. Beucher (2010): Fast implementation of large erosions and dilations in Mamba.
This document explains how to implement fast erosions and dilations when large structuring elements are needed. These structuring elements can be squares, hexagons, octogons or dodecagons. This implementation, realized in the Mamba library brings a dramatic increase of the computation speed. This increase is all the more important as the size of the structuring element is large.
D. PetrovskaDelacrétaz, M.A. Mellakh, D. Zhou, G. Chollet, C. Riedinger, N. Khemakhem, S. Beucher, L. Naud, B. Stanciulecu, P. Bernas, B. Abboud, G. Neuez, S. VINSON (2010): Analyse de séquences vidéo : le projet ANR KIVAOU. WISG 2010 : Workshop Interdisciplinaire sur la Sécurité Globale, Troyes (France).
The KIVAOU project aims at developing innovative tools dedicated to two main goals: 1) Mobile facial identification and biometric indexation tool (suitcase), with realtime video analysis, and 2) Platform for offline multiple video analysis of an event (one place, one period). These videos are recorded during a particular event, and then collected for investigation purposes. After synchronisation between different sources, an analysis is performed in order to extract individual signatures, and to compute person's trajectories. The goal is to enable or to facilitate an offline analysis. The...
G. Noyel, J. Angulo, D. Jeulin (2010): A New SpatioSpectral Morphological Segmentation For MultiSpectral RemoteSensing Images. International Journal of Remote Sensing 31(22) 5895—5920.
A general framework of spatiospectral segmentation for multispectral images is introduced in this paper. The method is based on classificationdriven stochastic watershed (WS) by Monte Carlo simulations, and it gives more regular and reliable contours than standard WS. The present approach is decomposed into several sequential steps. First, a dimensionalityreduction stage is performed using the factorcorrespondence analysis method. In this context, a new way to select the factor axes (eigenvectors) according to their spatial information is introduced. Then, a spectral classification...
C. Peyrega, D. Jeulin (2010): Effects Of The Microstructure Of Fibrous Media On Their Acoustic Properties. Proceedings COMSOL Conference 53.
M. Jeandin, D.K. Christoulis, F. Borit, M.H. Berger, S. Guetta, G. Rolland, V. Guipont, F. N'Guyen, D. Jeulin, E. Irissou, J.G. Legoux, C. Moreau, M. Nivard, L. Berthe, M. Boustie, W. Ludwig, K. Sakaguchi, Y. Ichikawa, K. Ogawa, S. Costil (2010): A Socratic approach to surface modification: The example of Thermal Spray. Proceedings of the 24th International Conference on SURFACE MODIFICATION TECHNOLOGIES, SMT 24 12.
S. VelascoForero, J. Angulo (2010): Spatial Structures Detection In Hyperspectral Images Using Mathematical Morphology. Proc. of IEEE 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS'2010) 1—4.
J. Stawiaski, E. Decencière, F. Bidault (2010): SpatioTemporal Segmentation For Radiotherapy Planning. Progress in Industrial Mathematics at ECMI 2008.
S. Beucher (2010): Fast implementation of large erosions and dilations in Mamba.
This document explains how to implement fast erosions and dilations when large structuring elements are needed. These structuring elements can be squares, hexagons, octogons or dodecagons. This implementation, realized in the Mamba library brings a dramatic increase of the computation speed. This increase is all the more important as the size of the structuring element is large.
M. Faessel, D. Jeulin (2010): Segmentation of 3D microtomographic images of granular materials with the stochastic watershed. Journal of Microscopy 239(1) 17—31.
Segmentation of 3D images of granular materials obtained by microtomography is not an easy task. Because of the conditions of acquisition and the nature of the media, the available images are not exploitable without a reliable method of extraction of the grains. The high connectivity in the medium, the disparity of the object's shape and the presence of image imperfections make classical segmentation methods (using image gradient and watershed constrained by markers) extremely difficult to perform efficiently. In this paper, we propose a nonparametric method using the stochastic watershed,...
D. Knobel, J.L. Crawford, P.D. Nguyen, J. Tutela, V.D. Thanik, J.C. Klein, O. Eydlin, O. Cohen, E.H. Davidson, J.P. Levine (2010): Novel Mechanisms for Augmenting Diabetic Wound Healing. Journal of Surgical Research 158(2) 322.
Impaired diabetic wound healing is multifactorial and incompletely understood. Reactive oxygen species (ROS) and p53, a master gene regulator, are upregulated in diabetic wounds. We have demonstrated improved diabetic wound healing through a novel topical p53 silencing system. We hypothesized that topical silencing of p53 improves diabetic wound healing through a decrease in ROS.
L. Signor, T. De Rességuier, A. Dragon, G. Roy, A. Fanget, M. Faessel (2010): Investigation of Fragments Size Resulting from Dynamic Fragmentation in Melted State of Laser ShockLoaded Tin. International Journal of Impact Engineering 37(8) 887—900.
The understanding of dynamic fragmentation in shockloaded metals and the evaluation of geometrical and kinematical properties of the resulting fragments are issues of considerable importance for both basic and applied science, for instance to predict the evolution of engineering structures submitted to highvelocity impact or explosive detonation. Among dynamic failure processes, spall fracture in solid materials has been extensively studied for many years, while scarce data can be found yet about how such phenomenon could evolve after partial or full melting on compression or on release. In...
M. LuengoOroz, E. Faure, J. Angulo (2010): Robust Iris Segmentation on Uncalibrated Noisy Images Using Mathematical Morphology. Image and Vision Computing 28(2) 278—284.
This paper proposes a new approach for fast iris segmentation that relies on the closed nested structures of iris anatomy (the sclera is brighter than the iris, and the iris is brighter than the pupil) and on its polar symmetry. The described method applies mathematical morphology for polar/radialinvariant image filtering and for circular segmentation using shortest paths from generalized greylevel distances. The proposed algorithm obtained good results on the NICEI contest and showed a very robust behavior, especially when dealing with halfclosed eyes, different skin colours/illumination...
B. Dupas, T. Walter, A. Erginay, R. Ordonez, N. DebJoardar, P. Gain, J.C. Klein, P. Massin (2010): Evaluation of automated fundus photograph analysis algorithms for detecting microaneurysms, haemorrhages and exudates, and of a computerassisted diagnostic system for grading diabetic retinopathy. Diabetes and Metabolism 36(3) 213—220.
Aims: This study aimed to evaluate automated fundus photograph analysis algorithms for the detection of primary lesions and a computerassisted diagnostic system for grading diabetic retinopathy (DR) and the risk of macular edema (ME). Methods: Two prospective analyses were conducted on fundus images from diabetic patients. Automated detection of microaneurysms and exudates was applied to two small image databases on which these lesions were manually marked. A computerassisted diagnostic system for the detection and grading of DR and the risk of ME was then developed and evaluated, using a...
F. Courtois, M. Faessel, C. Bonazzic (2010): Assessing Breakage and Cracks of Parboiled Rice Kernels by Image Analysis Techniques. Food Control 21(4) 567—572.
This paper deals with the measurement of breakage ratio and the estimation of fissures on parboiled rice by image analysis on unarranged grain samples. Hardware cost of the apparatus is low since it is based on standard offtheshelf scanner. In addition, open source (free) software is used to complete the experimental setup. An innovative technique for segmentation of touching kernels is used, combined with breakage estimation based on geometric properties and crack estimation using a new image analysis technique. This inexpensive system is validated with reference measurements for breakage...
A. Cord, F. Bach, D. Jeulin (2010): Texture Classification By Statistical Learning From Morphological Image Processing: Application To Metallic Surfaces. Journal of Microscopy 239(2) 159—166.
A classification method based on textural information for metallic surfaces displaying complex random patterns is proposed. Because these kinds of textures show fluctuations at a small scale and some uniformity at a larger scale, a probabilistic approach is followed, considering textural variations as realizations of random functions. Taking into account information of pixel neighbourhoods, the texture for each pixel is described at different scales. By means of statistical learning, the most relevant textural descriptors are selected for each application. The performance of this approach is...
J. Angulo (2010): Geometric Algebra Colour Image Representations And Derived Total Orderings For Morphological OperatorsPart I: Colour Quaternions. Journal of Visual Communication and Image Representation 21(1) 33—48.
The definition of morphological operators for colour images requires a total ordering for colour points. A colour can be represented by different algebraic structures, in this paper we focus on real quaternions. The paper presents two main contributions. On the one hand, we have studied different alternatives to introduce the scalar part to obtain full colour quaternions. On the other hand, several total lexicographic orderings for quaternions have been defined, according to the various quaternion decompositions. The properties of these quaternionic orderings have been characterised to enable...
J. Angulo, J. Chanussot (2010): Couleur et images multivariées. Morphologie mathématique 2 : estimation, choix et mise en oeuvre 203—236 (Chapitre 5).
S. VelascoForero, J. Angulo (2010): Hitormiss transform in multivariate images. Advanced Concepts for Intelligent Vision Systems: Proceedings, 12th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2010 6474 452—463.
The HitorMiss transform (HMT) is a wellknown morphological operator for template matching in binary images. A novel approach for HMT for multivariate images is introduced in this paper. The generic framework is a generalization of binary case based on a hsupervised ordering formulation which leads to reduced orderings. In particular, in this paper we focus on the application of HMT for target detection on highresolution images. The visual results of the experiments show the performance of proposed approach.
J. Angulo (2010): Pseudomorphological Image Diffusion Using the CounterHarmonic Paradigm. Advanced Concepts for Intelligent Vision Systems: Proceedings, 12th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2010 6474 426—437.
Relationships between linear and morphological scalespaces have been considered by various previous works. The aim of this paper is to study how to generalize the diffusionbased approaches in order to introduce nonlinear filters which effects mimic morphological dilation and erosion. A methodology based on the counterharmonic mean is adopted here. Details of numerical implementation are discussed and results are provided to illustrate the behaviour of various studied cases: isotropic, nonlinear and coherenceenhanced diffusion. We also rediscover the classical link between Gaussian...
S. VelascoForero, J. Angulo (2010): Parameters Selection Of Morphological ScaleSpace Decomposition For Hyperspectral Images Using Tensor Modeling. SPIE Proceedings: Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVI 7695B 12 p..
Dimensionality reduction (DR) using tensor structures in morphological scalespace decomposition (MSSD) for HSI has been investigated in order to incorporate spatial information in DR.We present results of a comprehensive investigation of two issues underlying DR in MSSD. Firstly, information contained in MSSD is reduced using HOSVD but its nonconvex formulation implicates that in some cases a large number of local solutions can be found. For all experiments, HOSVD always reach an unique global solution in the parameter region suitable to practical applications. Secondly, scale parameters in...
J. Angulo, S. VelascoForero (2010): SemiSupervised Hyperspectral Image Segmentation Using Regionalized Stochastic Watershed. SPIE Proceedings: Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVI 7695F 12 p..
Stochastic watershed is a robust method to estimate the probability density function (pdf) of contours of a multivariate image using MonteCarlo simulations of watersheds from random markers. The aim of this paper is to propose a stochastic watershedbased algorithm for segmenting hyperspectral images using a semisupervised approach. Starting from a training dataset consisting in a selection of representative pixel vectors of each spectral class of the image, the algorithm calculate for each class a membership probability map (MPM). Then, the MPM of class k is considered as a regionalized...
R. Minetto, N. Thome, M. Cord, J. Fabrizio, B. Marcotegui (2010): Snoopertext: A multiresolution system for text detection in complex visual scenes. ICIP 2010  17th IEEE International Conference on Image Processing, HongKong (Hong Kong SAR China) 3861—3864.
Text detection in natural images remains a very challenging task. For instance, in an urban context, the detection is very difficult due to large variations in terms of shape, size, color, orientation, and the image may be blurred or have irregular illumination, etc. In this paper, we describe a robust and accurate multiresolution approach to detect and classify text regions in such scenarios. Based on generation/validation paradigm, we first segment images to detect character regions with a multiresolution algorithm able to manage large character size variations. The segmented regions are...
J. Angulo (2010): Nucleus Modelling And Segmentation In Cell Clusters. Progress in Industrial Mathematics at ECMI 2008 217—222.
This paper deals with individual nucleus modelling and segmentation, from fluorescence labelled images, of cell populations growing in complex clusters. The proposed approach is based on models and operators from mathematical morphology. Cells are individually marked by the ultimate opening and then are segmented by the watershed transformation. A cell counting algorithm based on classical results of Boolean model theory is heuristically used to detect errors in segmenting clustered nuclei.
J. Angulo, D. Jeulin (2010): Minisymposium Multivariate and/or Multidimensional Image Processing in Biomedical Applications. Progress in Industrial Mathematics at ECMI 2008 209—210.
Nowadays many different modalities are available in medical imaging, including computed tomography (CT) scans, functional or dynamic contrastenhanced magnetic resonance imaging (fMRI) or (DCEMRI), positron emission tomography (PET). The 2D/3D + time images produced by these advanced devices are useful for cancer diagnosis, radiotherapy or surgery planning, active study of human brain, tumour angiogenesis quantification, etc. In addition, the most recent microscope systems in biomedical laboratories are based on multi/hyperspectral imaging for brightfield or fluorescence microscopy.
G. Noyel, J. Angulo, D. Jeulin (2010): Regionalized Random Germs by a Classification for Probabilistic Watershed Application: Angiogenesis Imaging Segmentation. Progress in Industrial Mathematics at ECMI 2008 211—216.
New methods are presented to generate random germs regionalized by a previous classification in order to use probabilistic watershed on hyperspectral images. These germs are much more efficient than the standard uniform random germs.
S. VelascoForero, J. Angulo (2010): Statistical Shape Modeling Using Morphological Representations. 20th International Conference on Pattern Recognition (ICPR) 3537—3540.
The aim of this paper is to propose tools for statistical analysis of shape families using morphological operators. Given a series of shape families (or shape categories), the approach consists in empirically computing shape statistics (i.e., mean shape and variance of shape) and then to use simple algorithms for random shape generation, for empirical shape confidence boundaries computation and for shape classification using Bayes rules. The main required ingredients for the present methods are well known in image processing, such as watershed on distance functions or logpolar...
R. VerduMonedero, J. Angulo, J. LarreyRuiz, J. MoralesSanchez (2010): Comparison of orientated and spatially variant morphological filters vs mean/median filters for adaptive image denoising. 17th IEEE International Conference on Image Processing (ICIP) 113—116.
This paper shows a comparison of spatiallyvariant discrete operators for denoising graylevel images. These noniterative operators use a neighborhood that varies over space, adapting their shape and orientation according to the data of the image under study. The orientation of the neighborhood is computed by means of a diffusion process of the average square gradient field, which regularizes and extends the orientation information from the edges of the objects to the homogeneous areas of the image; and the shape of the orientated neighborhood can be either a linear segment or a rectangle of...
S. VelascoForero, J. Angulo (2010): Morphological Processing of Hyperspectral Images Using KrigingBased Supervised Ordering. 17th IEEE International Conference on Image Processing (ICIP) 1409—1412.
A novel approach for vectorial ordering is introduced in this paper. The generic framework is based on a supervised learning formulation which leads to reduced orderings. A training set for the background and another training set for the foreground are needed as well as a supervised method to construct the ordering mapping. In particular, we consider here a krigingbased vectorial ordering. This supervised ordering may then used for the extension of mathematical morphology to vectorial images. Application of morphological processing to hyperspectral image illustrates the performance of...
J. Angulo, S. VelascoForero (2010): Structurally adaptive mathematical morphology on nonlinear scalespace representations. 17th IEEE International Conference on Image Processing (ICIP) 121—124.
Standard formulation of morphological operators is translation invariant in the space and in the intensity: the same processing is considered for each point of the image. A current challenging topic in mathematical morphology is the construction of adaptive operators. In previous works, the adaptive operators are based either on spatially variable neighbourhoods according to the local regularity, or on size variable neighbourhoods according to the local intensity. This paper introduces a new framework: the structurally adaptive mathematical morphology. More precisely, the rationale behind the...
F. Meyer (2010): Shape Interpolation with Flattenings. 20th International Conference on Pattern Recognition (ICPR) 2094—2097.
This paper presents the binary flattenings of shapes, first as a connected operator suppressing particles or holes, second as an erosion in a particular lattice of shapes. Using this erosion, it is then possible to construct a distance from a shape to another and derive from it an interpolation function between shapes.
F. Meyer (2010): Levelings and Flat Zone Morphology. 20th International Conference on Pattern Recognition (ICPR) 1570—1573.
Successive levelings are applied on document images. The residues of successive levelings are made of flat zones for which morphological transforms are described.
E. ParraDenis, D. Jeulin (2010): Morphological analysis of complex threedimensional particles. Application to aluminium alloy 5xxx. Aluminum Alloys: Preparation, Properties and Applications 1—47.
N. Moulin, E. ParraDenis, D. Jeulin, C. Ducottet, A. Bigot, E. Boller, Maire, C. Barat, H. Klöcker (2010): Constituent particle breakup during hot rolling of AA 5182. Advanced Engineering Materials 12(12) 20—29.
Aluminum sheet is currently used for body panels on a number of massproduced vehicles, in particular for closure panels. AA5xxx alloys always contain coarse intermetallic particles (Al x(Fe,Mn) ySi, Mg 2Si) after casting. In the present work intermetallic particle breakup during hot reversible rolling of AA5182 alloy sheets has been analyzed. The sizes and shapes of intermetallic particles in ascast and industrially hot rolled AA5182 alloys sheets were characterized by 3D Xray tomography observations. The relation between particle breakup and particle morphology was then analyzed...
B. Hoffmann, M. Zaslavskiy, J.P. Vert, V. Stoven (2010): A new protein binding pocket similarity measure based on comparison of clouds of atoms in 3D: application to ligand prediction. BMC Bioinformatics 11(1) 99.
BACKGROUND: Predicting which molecules can bind to a given binding site of a protein with known 3D structure is important to decipher the protein function, and useful in drug design. A classical assumption in structural biology is that proteins with similar 3D structures have related molecular functions, and therefore may bind similar ligands. However, proteins that do not display any overall sequence or structure similarity may also bind similar ligands if they contain similar binding sites. Quantitatively assessing the similarity between binding sites may therefore be useful to propose new...
F. Meyer, J. Stawiaski (2010): A stochastic evaluation of the contour strength. Pattern Recognition, Proceedings of the 32nd DAGM Symposium, Darmstadt, Germany, 2010 6376/2010 513—522.
If one considers only local neighborhoods for segmenting an image, one gets contours whose strength is often poorly estimated. A method for reevaluating the contour strength by taking into account non local features is presented: one generates a fixed number of random germs which serve as markers for the watershed segmentation. For each new population of markers, another set of contours is generated. "Important" contours are selected more often. The present paper shows that the probability that a contour is selected can be estimated without performing the effective simulations. Copyright...
J. Bartovsky, P. Dokládal, E. Dokladalova, V. Georgiev (2010): Stream implementation of serial morphological filters with approximated polygons. Electronics, Circuits, and Systems (ICECS), 2010 17th IEEE International Conference on 706—709.
This paper describes an original stream implementation of serially composed morphological filters using approximated flat polygons. It strictly respects a sequential data access. Results are obtained with minimal latency while operating within minimal memory space; even for very large neighborhoods. This is interesting for serially composed advanced filters, such as Alternating Sequential Filters or granulometries. We show how the dedicated implementation on an FPGA allows obtaining a previously unequaled performance, opening an opportunity to use these operators in timecritical, highend...
J. Bartovsky, E. Dokladalova, P. Dokládal, V. Georgiev (2010): Pipeline architecture for compound morphological operators. 17th IEEE International Conference on Image Processing (ICIP) 3765—3768.
In this paper we present a new pipeline HW architecture for fast 2D erosions/dilations. The implementation is based on a recently proposed algorithm allowing to process 2D data in a stream, minimizing the use of memory and drastically reducing the computing latency. These elementary operators can be chained in an efficient pipeline to realize compound morphological operators (opening, closing, ASF filters, etc.) with no intermediate image storage and minimal latency.
H. Altendorf, D. Jeulin (2010): Random Walk Based Stochastic Modeling of 3D Fiber Systems. Physical Review E : Statistical, Nonlinear, and Soft Matter Physics 83(4) 10 p., 041804.
For the simulation of fiber systems, there exist several stochastic models: systems of straight nonoverlapping fibers, systems of overlapping bending fibers or fiber systems created by sedimentation. However, there is a lack of models providing dense, nonoverlapping fiber systems with a given random orientation distribution and a controllable level of bending. We introduce a new stochastic model in this paper, that generalizes the forcebiased packing approach to fibers represented as chains of balls. The starting configuration is modeled using random walks, where two parameters in the...
C. Peyrega (2010): Prédiction des propriétés acoustiques de matériaux fibreux hétérogènes à partir de leur microstructure 3D.
This PhD thesis is carried out in the framework of the Silent Wall research program whose main objective consists of designing an acoustic and thermal insulating system for buildings, from fibrous materials. Since the acoustic insulation is the main issue of this work, several fields of research are prospected within the study of the microstructural properties of these media. The Thermisorel material, made of wooden fibres, is a reference fibrous medium for the Silent Wall project thanks to its good acoustic and thermal insulating properties. Volumic 3D XRay microtomographic images of this...
V. Guipont, M. Jeandin, G. Rolland, D. Jeulin, C. Peyrega, W. Ludwig (2010): Microstructures of cold sprayed coatings investigated by Xray microtomography. Thermal Spray Bulletin 140—147.
F. Meyer (2010): Scheduling trains with delayed departures.
A number of image transformations may be expressed as shortes paths algorithms in various algebras We introduce a general framework where a graph is considered as a railway network on which the trains follow shortest paths. Given a fixed traveling time on each edge and an arbitrary distribution of departure times, one searches the first arrival time of a train at each node. This formulation leads to interesting filters and image decomposition in the (min,+) algebra and sheds new light on flooding and razing algorithms in the algebras (min,max) and (max,min).
M. Zaslavskiy (2010): L'alignement de graphes : applications en bioinformatique et vision par ordinateur.
The graph matching problem is among the most important challenges of graph processing, and plays a central role in various fields of pattern recognition. We propose an approximate method for labeled weighted graph matching, based on a convexconcave programming approach which can be applied to the matching of large sized graphs. This method allows to easily integrate information on graph label similarities into the optimization problem, and therefore to perform labeled weighted graph matching. One of the interesting applications of the graph matching problem is the alignment of...
List of all publications from the CMM, recorded on the HAL depository under the tag
ENSMP_CMM
.
See also: