[Show abstract][Hide abstract] ABSTRACT: In recent works, a new notion of component-graph was introduced. It extends the classical notion of componenttree initially proposed in mathematical morphology to model the structure of grey-level images. Component-graphs can indeed model the structure of any - grey-level or multivalued - images. We now extend the antiextensive filtering scheme based on component-trees, in order to make it tractable in the framework of component-graphs. More precisely, we provide solutions for building a component-graph; reducing it based on selection criteria; and reconstructing a filtered image from a reduced component-graph. In this article, we first consider the cases where component-graphs still have a tree structure; they are then called multivalued component-trees. The relevance and usefulness of such multivalued component-trees are illustrated by applicative examples on hierarchically classified remote sensing images.
IEEE Transactions on Image Processing 10/2014; · 3.11 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: In the continuous domain, rigid transformations are topology-preserving operations. Due to digitization, this is not the case when considering digital images, i.e., images defined on Z^n. In this article, we begin to investigate this problem by studying conditions for digital images to preserve their topological properties under all rigid transformations on Z^2. Based on (i) the recently introduced notion of DRT graph, and (ii) the notion of simple point, we propose an algorithm for evaluating digital images topological invariance.
Journal of Mathematical Imaging and Vision 06/2014; 49(2):418-433. · 2.33 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Component-trees model the structure of grey-level images by considering their binary level-sets obtained from successive thresholdings. They also enable to define anti-extensive filtering procedures for such images. In order to extend this image processing approach to any (grey-level or multivalued) images, both the notion of component-tree, and its associated filtering framework, have to be generalised. In this article we deal with the generalisation of the component-tree structure. We define a new data structure, the component-graph, which extends the notion of component-tree to images taking their values in any (partially or totally) ordered set. The component-graphs are declined in three variants, of increasing richness and size, whose structural properties are studied.
Journal of Mathematical Imaging and Vision 05/2014; · 2.33 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: We provide conditions under which 2D digital images preserve their topological properties under rigid transformations. We consider the two most common digital topology models, namely dual adjacency and well-composedness. This paper leads to the proposal of optimal preprocessing strategies that ensure the topological invariance of images under arbitrary rigid transformations. These results and methods are proved to be valid for various kinds of images (binary, gray-level, label), thus providing generic and efficient tools, which can be used in particular in the context of image registration and warping.
[Show abstract][Hide abstract] ABSTRACT: The automated detection and mapping of landslides from Very High Resolution (VHR) images present several challenges related to the heterogeneity of landslide sizes, shapes and soil surface characteristics. However, a common geomorphological characteristic of landslides is to be organized with a series of embedded and scaled features. These properties motivated the use of a multiresolution image analysis approach for their detection. In this work, we propose a hybrid segmentation/classification region-based method, devoted to this specific issue. The method, which uses images of the same area at various spatial resolutions (Medium to Very High Resolution), relies on a recently introduced top-down hierarchical framework. In the specific context of landslide analysis, two main novelties are introduced to enrich this framework. The first novelty consists of using non-spectral information, obtained from Digital Terrain Model (DTM), as a priori knowledge for the guidance of the segmentation/classification process. The second novelty consists of using a new domain adaptation strategy, that allows to reduce the expert’s interaction when handling large image datasets. Experiments performed on satellite images acquired over terrains affected by landslides demonstrate the efficiency of the proposed method with different hierarchical levels of detail addressing various operational needs.
ISPRS Journal of Photogrammetry and Remote Sensing 01/2014; 87:122-136. · 2.90 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: We study the conditions under which the topological properties of a 2D well-composed binary image are preserved under arbitrary rigid transformations. This work initiates a more global study of digital image topological properties under such transformations, which is a crucial but under-considered problem in the context of image processing, e.g., for image registration and warping.
2013 20th IEEE International Conference on Image Processing (ICIP); 09/2013
[Show abstract][Hide abstract] ABSTRACT: Rigid transformations are involved in a wide range of digital image processing applications. When applied on discrete images, rigid transformations are usually performed in their associated continuous space, requiring a subsequent digitization of the result. In this article, we propose to study rigid transformations of digital images as fully discrete processes. In particular, we investigate a combinatorial structure modelling the whole space of digital rigid transformations on arbitrary subset of Z2Z2 of size N × N. We describe this combinatorial structure, which presents a space complexity O(N9)O(N9) and we propose an algorithm enabling to construct it in linear time with respect to its space complexity. This algorithm, which handles real (i.e., non-rational) values related to the continuous transformations associated to the discrete ones, is however defined in a fully discrete form, leading to exact computation.
[Show abstract][Hide abstract] ABSTRACT: In ℝ2, rigid transformations are topology-preserving operations. However, this property is generally no longer true when considering digital images instead of continuous ones, due to digitization effects. In this article, we investigate this issue by studying discrete rigid transformations (DRTs) on ℤ2. More precisely, we define conditions under which digital images preserve their topological properties under any arbitrary DRTs. Based on the recently introduced notion of DRT graph and the classical notion of simple point, we first identify a family of local patterns that authorize topological invariance under DRTs. These patterns are then involved in a local analysis process that guarantees topological invariance of whole digital images in linear time.
Proceedings of the 17th IAPR international conference on Discrete Geometry for Computer Imagery; 03/2013
[Show abstract][Hide abstract] ABSTRACT: Connected filters, and in particular those relying on component trees, can be involved in vessel filtering and segmentation tasks. We propose a new component tree-based segmentation method that enables to easily obtain vascular volumes from 3D data, by simply providing 2D markers from MIP visualisations. This approach gathers the advantages of component trees (low algorithmic cost) and the user-friendly (fuzzy) handling of 3D images via 2D representations, leading to an ergonomic and fast tool. It has been successfully used for segmenting a large dataset of MRAs and CTAs visualizing Willis polygons, in the clinical context of stenosis detection.
Biomedical Imaging (ISBI), 2013 IEEE 10th International Symposium on; 01/2013
[Show abstract][Hide abstract] ABSTRACT: We propose a new distance called Hierarchical Semantic-Based Distance (HSBD), devoted to the comparison of nominal histograms equipped with a dissimilarity matrix providing the semantic correlations between the bins. The computation of this distance is based on a hierarchical strategy, progressively merging the considered instances (and their bins) according to their semantic proximity. For each level of this hierarchy, a standard bin-to-bin distance is computed between the corresponding pair of histograms. In order to obtain the proposed distance, these bin-to-bin distances are then fused by taking into account the semantic coherency of their associated level. From this modus operandi, the proposed distance can handle histograms which are generally compared thanks to cross-bin distances. It preserves the advantages of such cross-bin distances (namely robustness to histogram translation and histogram bin size issues), while inheriting the low computational cost of bin-to-bin distances. Validations in the context of geographical data classification emphasize the relevance and usefulness of the proposed distance.
Data & Knowledge Engineering. 01/2013; 87:206–225.
[Show abstract][Hide abstract] ABSTRACT: Cerebrovascular atlases can be used to improve medical tasks requiring the analysis of 3D angiographic data. The generation of such atlases remains however a complex and infrequently considered issue. The existing approaches rely on information exclusively related to the vessels. We alternatively investigate a new way, consisting of using both vascular and morphological information (i.e., cerebral structures) to improve the accuracy and relevance of the obtained vascular atlases. Experiments emphasize improvements in the main steps of the atlas generation process impacted by the use of morphological information. An example of cerebrovascular atlas obtained from a dataset of 56 MRAs acquired from different acquisition devices is finally provided.
Biomedical Imaging (ISBI), 2013 IEEE 10th International Symposium on; 01/2013
[Show abstract][Hide abstract] ABSTRACT: In the last 20years, 3D angiographic imaging has proven its usefulness in the context of various clinical applications. However, angiographic images are generally difficult to analyse due to their size and the complexity of the data that they represent, as well as the fact that useful information is easily corrupted by noise and artifacts. Therefore, there is an ongoing necessity to provide tools facilitating their visualisation and analysis, while vessel segmentation from such images remains a challenging task. This article presents new vessel segmentation and filtering techniques, relying on recent advances in mathematical morphology. In particular, methodological results related to spatially variant mathematical morphology and connected filtering are stated, and included in an angiographic data processing framework. These filtering and segmentation methods are evaluated on real and synthetic 3D angiographic data.
Medical image analysis 09/2012; · 3.09 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: In digital imaging, after several decades devoted to the study of
topological properties of binary images, there is an increasing need
of new methods enabling to take into (topological) consideration
n-ary images (also called label images). Indeed, while binary images
enable to handle one object of interest, label images authorise to
simultaneously deal with a plurality of objects, which is a frequent
requirement in several application fields. In this context, one of
the main purposes is to propose topology-preserving transformation
procedures for such label images, thus extending the ones (e.g.,
growing, reduction, skeletonisation) existing for binary images.
In this article, we propose, for a wide range of digital images,
a new approach that permits to locally modify a label image, while
preserving not only the topology of each label set, but also the
topology of any arrangement of the labels understood as the topology
of any union of label sets. This approach enables in particular to
unify and extend some previous attempts devoted to the same purpose.
Journal of Mathematical Imaging and Vision 08/2012; · 1.77 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: The extraction of urban patterns from very high spatial resolution (VHSR) optical images presents several challenges related to the size, the accuracy and the complexity of the considered data. Based on the availability of several optical images of a same scene at various resolutions (medium, high, and very high spatial resolution), a hierarchical approach is proposed to progressively extract segments of interest from the lowest to the highest resolution data, and then finally determine urban patterns from VHSR images. This approach, inspired by the principle of photo-interpretation, has for purpose to use as much as possible the user's skills while minimising his/her interaction. In order to do so, at each resolution, an interactive segmentation of one sample region is required for each semantic class of the image. Then, the user's behaviour is automatically reproduced in the remainder of the image. This process is mainly based on tree-cuts in binary partition trees. Since it strongly relies on user-defined segmentation examples, it can involve only low level—spatial and radiometric—criteria, then enabling fast computation of comprehensive results. Experiments performed on urban images datasets provide satisfactory results which may be further used for classification purpose.
[Show abstract][Hide abstract] ABSTRACT: Component-trees associate to a discrete grey-level image a descriptive data structure induced by the inclusion relation between the binary components obtained at successive level-sets. This article presents an original interactive segmentation methodology based on component-trees. It consists of the extraction of a subset of the image component-tree, enabling the generation of a binary object which fits at best (with respect to the grey-level structure of the image) a given binary target selected beforehand in the image. A proof of the algorithmic efficiency of this methodological scheme is proposed. Concrete application examples on magnetic resonance imaging (MRI) data emphasise its actual computational efficiency and its usefulness for interactive segmentation of real images.
[Show abstract][Hide abstract] ABSTRACT: The Fuzzy C-Means (FCM) algorithm is a widely used and flexible approach to automated image segmentation, especially in the field of brain tissue segmentation from 3D MRI, where it addresses the problem of partial volume effects. In order to improve its robustness to classical image deterioration, namely noise and bias field artifacts, which arise in the MRI acquisition process, we propose to integrate into the FCM segmentation methodology concepts inspired by the non-local (NL) framework, initially defined and considered in the context of image restoration. The key algorithmic contributions of this article are the definition of an NL data term and an NL regularisation term to efficiently handle intensity inhomogeneities and noise in the data. The resulting new energy formulation is then built into an NL-FCM brain tissue segmentation algorithm. Experiments performed on both synthetic and real MRI data, leading to the classification of brain tissues into grey matter, white matter and cerebrospinal fluid, indicate a significant improvement in performance in the case of higher noise levels, when compared to a range of standard algorithms.
[Show abstract][Hide abstract] ABSTRACT: In the last 20 years, progress in 3D medical imaging (such as MRI and CT) has led to the development of modalities devoted
to visualise vascular structures. These angiographic images progressively proved their usefulness in the context of various
clinical applications. However, such data are generally complex to analyse due to their size and low amount of relevant (vascular)
information versus noise, artifacts and other anatomical structures. Therefore, there is an ongoing necessity to provide tools facilitating
image visualisation and analysis. In this chapter, we first focus on vascular image analysis. In particular, we present a
survey on both standard and recent vessel segmentation methodologies. We then discuss the existing ways to model anatomical
knowledge via the computation of vascular atlases. Such atlases can notably be embedded in computer-aided radiology tools.
[Show abstract][Hide abstract] ABSTRACT: The extraction of urban patterns from very high spatial resolution optical images presents challenges related to the size,
the accuracy and the complexity of the data. In order to efficiently carry out this task, a multiresolution hierarchical approach
is proposed. It enables to progressively segment several images (of increasing resolutions) of a same scene, based on low
level criteria. The process, based on binary partition trees, is partially performed in an interactive fashion, and then automatically
completed. Experiments on urban images datasets provide encouraging results which may be further used for detection and classification
KeywordsHierarchical segmentation–multisource images–multiresolution–interactive/automated segmentation–partition-trees–remote sensing–urban analysis