A graph-based mathematical morphology reader

Najman, Laurent; Cousty, Jean

doi:10.1016/j.patrec.2014.05.007

Cited by 41 publications

(27 citation statements)

References 156 publications

(219 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…See [19] for a general overview of mathematical morphology and [20] for an overview of segmentation concepts and approaches. Developments and applications within remote sensing mirror the advancements of basic research within mathematical morphology.…”

Section: Graph-based Connected Component Segmentationmentioning

confidence: 99%

“…A flat zone defines a specific level in a hierarchical image partitioning based on grey-level intensities [20,23,24]. Various successful methods and applications have been presented based on this notion, e.g., [2,[25][26][27][28].…”

Section: Graph-based Connected Component Segmentationmentioning

confidence: 99%

“…Various successful methods and applications have been presented based on this notion, e.g., [2,[25][26][27][28]. This development was elaborated upon with the notion of a quasi-flat zone, which relaxes the restrictive definition of a flat zone by introducing a certain level of dissimilarity tolerance between pixels (parameter controlled) [8,9,20,29]. Quasi-flat zones form the basis of flexible segmentation algorithms, suited to remote sensing image analysis problems.…”

Section: Graph-based Connected Component Segmentationmentioning

confidence: 99%

See 2 more Smart Citations

On Attribute Thresholding and Data Mapping Functions in a Supervised Connected Component Segmentation Framework

Fourie¹

2015

Remote Sensing

View full text Add to dashboard Cite

Search-centric, sample supervised image segmentation has been demonstrated as a viable general approach applicable within the context of remote sensing image analysis. Such an approach casts the controlling parameters of image processing-generating segments-as a multidimensional search problem resolvable via efficient search methods. In this work, this general approach is analyzed in the context of connected component segmentation. A specific formulation of connected component labeling, based on quasi-flat zones, allows for the addition of arbitrary segment attributes to contribute to the nature of the output. This is in addition to core tunable parameters controlling the basic nature of connected components. Additional tunable constituents may also be introduced into such a framework, allowing flexibility in the definition of connected component connectivity, either directly via defining connectivity differently or via additional processes such as data mapping functions. The relative merits of these two additional constituents, namely the addition of tunable attributes and data mapping functions, are contrasted in a general remote sensing image analysis setting. Interestingly, tunable attributes in such a context, conjectured to be safely useful in general settings, were found detrimental under cross-validated conditions. This is in addition to this constituent's requiring substantially greater computing time. Casting connectivity definitions as a searchable component, here via the utilization of data mapping functions, proved more beneficial and robust in this context. The results suggest that further investigations into such a general framework could benefit more from focusing on the aspects of data mapping and modifiable connectivity as opposed to the utility of thresholding various geometric and spectral attributes.

show abstract

Section: Graph-based Connected Component Segmentationmentioning

confidence: 99%

Section: Graph-based Connected Component Segmentationmentioning

confidence: 99%

Section: Graph-based Connected Component Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

On Attribute Thresholding and Data Mapping Functions in a Supervised Connected Component Segmentation Framework

Fourie¹

2015

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…As the algorithms for computing the trees are graph-based ones, these ideas can be extended to work on any graph, and not only on 2D/3D images (e.g. Xu et al [19], [14]). …”

Section: Introductionmentioning

confidence: 99%

Scale-space for empty catheter segmentation in PCI fluoroscopic images

Bacchuwar

Cousty

Vaillant³

et al. 2017

Int J CARS

Self Cite

View full text Add to dashboard Cite

Purpose: In this article, we present a method for empty guiding catheter segmentation in fluoroscopic X-ray images. The guiding catheter, being a commonly visible landmark, its segmentation is an important and a difficult brick for Percutaneous Coronary Intervention (PCI) procedure modeling. Methods: In number of clinical situations, the catheter is empty and appears as a low contrasted structure with two parallel and partially disconnected edges. To segment it, we work on the level-set scale-space of image, the min tree, to extract curve blobs. We then propose a novel structural scale-space, a hierarchy built on these curve blobs. The deep connected component, i.e. the cluster of curve blobs on this hierarchy, that maximizes the likelihood to be an empty catheter is retained as final segmentation. Results: We evaluate the performance of the algorithm on a database of 1250 fluoroscopic images from 6 patients. As a result, we obtain very good qualitative and quantitative segmentation performance, with mean precision and recall of 80.48% and 63.04% respectively. Conclusions: We develop a novel structural scale-space to segment a structured object, the empty catheter, in challenging situations where the information content is very sparse in the images. Fully-automatic empty catheter segmentation in X-ray fluoroscopic images is an important and preliminary step in PCI procedure modeling, as it aids in tagging the arrival and removal location of other interventional tools.

show abstract

“…On the one hand, we note that in the literature, one can find some works about nonlinear filters on graphs and hypergraphs, particularly mathematical morphology operators in the algebraic sense [3,4,5,6,7,8,9], where the couple of nonlinear operator (dilation/erosion) are maps from two different lattices, i.e., they are maps "from nodes to edges" or "edges to nodes". On the other hand, some regularisation techniques and nonlinear operators have been introduced on function evaluated on graph via directional derivative [10] [11] [12] or discrete version of the p-Laplacian [13].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear Operators on Graphs via Stacks

Velasco-Forero

Angulo

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We consider a framework for nonlinear operators on functions evaluated on graphs via stacks of level sets. We investigate family of transformations which includes adaptive flat and non-flat erosions and dilations. Additionally, we note the connection to mean motion curvature on graphs. Proposed operators are illustrated in the cases of functions on graphs, textured meshes and graphs of images.

show abstract

A graph-based mathematical morphology reader

Cited by 41 publications

References 156 publications

On Attribute Thresholding and Data Mapping Functions in a Supervised Connected Component Segmentation Framework

On Attribute Thresholding and Data Mapping Functions in a Supervised Connected Component Segmentation Framework

Scale-space for empty catheter segmentation in PCI fluoroscopic images

Nonlinear Operators on Graphs via Stacks

Contact Info

Product

Resources

About