Evaluation of Morphological Hierarchies for Supervised Segmentation

Perret, Benjamin; Cousty, Jean; Ura, Jean Carlo Rivera; Guimarães, Silvio Jamil Ferzoli

doi:10.1007/978-3-319-18720-4_4

Cited by 19 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One should note that such segmentations are not hierarchical, and as such, we can not truly assess the bene t of a hierarchical organisation. A considerable amount of work is nowadays devoted to the construction of a sound evaluation framework [1,[29][30][31]. Although the question of the evaluation of hierarchies is an even more complex question, we are deeply convinced that the computer-vision community at large would bene t if hierarchical ground truths were available.…”

Section: Discussionmentioning

confidence: 99%

Hierarchizing graph-based image segmentation algorithms relying on region dissimilarity

Guimarães

Kenmochi

Cousty

et al. 2017

Mathematical Morphology - Theory and Applications

Self Cite

View full text Add to dashboard Cite

This article is a rst attempt towards a general theory for hierarchizing non-hierarchical image segmentation method depending on a region-dissimilarity parameter which controls the desired level of simpli cation: each level of the hierarchy is "as close as possible" to the result that one would obtain with the non-hierarchical method using the corresponding scale as simpli cation parameter. The introduction of this hierarchization problem in the form of an optimization problem, as well as the proposed tools to tackle it, is an important contribution of the present article. Indeed, with the hierarchized version of a segmentation method, the user can just select the level in the hierarchy, controlling the desired number of regions or can leverage on any of the tools introduced in hierarchical analysis. The main example investigated in this study is the criterion proposed by Felzenszwalb and Huttenlocher for which we show that the results of the hierarchized version of the segmentation method are better than those of the original one with the added property that it satis es the strong causality and location principles from scale-sets image analysis. An interesting perspective of this work, considering the current trend in computer vision, is obviously, on a speci c application, to use learning techniques and train a criterion to choose the correct region.

show abstract

Section: Discussionmentioning

confidence: 99%

Hierarchizing graph-based image segmentation algorithms relying on region dissimilarity

Guimarães

Kenmochi

Cousty

et al. 2017

Mathematical Morphology - Theory and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

“…This method makes use of the Kruskal algorithm for propagating tags between sets hierarchically, since a minimum spanning tree establishes a hierarchical partition of a set [10].…”

Section: Hierarchical Strategy (Mst)mentioning

confidence: 99%

Tag Propagation Approaches within Speaking Face Graphs for Multimodal Person Discovery

Fonseca

Freire

Patrocínio

et al. 2017

Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing

Self Cite

View full text Add to dashboard Cite

The indexing of broadcast TV archives is a current problem in multimedia research. As the size of these databases grows continuously, meaningful features are needed to describe and connect their elements efficiently, such as the identification of speaking faces. In this context, this paper focuses on two approaches for unsupervised person discovery. Initial tagging of speaking faces is provided by an OCR-based method, and these tags propagate through a graph model based on audiovisual relations between speaking faces. Two propagation methods are proposed, one based on random walks and the other based on a hierarchical approach. To better evaluate their performances, these methods were compared with two graph clustering baselines. We also study the impact of different modality fusions on the graph-based tag propagation scenario. From a quantitative analysis, we observed that the graph propagation techniques always outperform the baselines. Among all compared strategies, the methods based on hierarchical propagation with late fusion and random walk with score-fusion obtained the highest MAP values. Finally, even though these two methods produce highly equivalent results according to Kappa coefficient, the random walk method performs better according to a paired t-test, and the computing time for the hierarchical propagation is more than 4 times lower than the one for the random walk propagation.

show abstract

“…In order to have a more complete evaluation, we have performed a comparison with a state-of-the-art method [14], called Multiscale Combinatorial Grouping (MCG), and an well-know technique [1], named Ultrametric Contour Map (UCM), including different assessment measures: Precision-Recall (PR) for boundaries [1] and the Marked Segmentation [13] ( Figure 6).…”

Section: Comparison With Other Techniquesmentioning

confidence: 99%

Evaluation of Combinations of Watershed Hierarchies

Maia

Araújo

Cousty

et al. 2017

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

The main goal of this paper is to evaluate the potential of some combinations of watershed hierarchies. We also propose a new combination based on merging level sets of hierarchies. Experiments were performed on natural image datasets and were based on evaluating the segmentations extracted from level sets of each hierarchy against the image ground truths. Our experiments show that most of combinations studied here are superior to their individual counterparts, which opens a path for a deeper investigation on combination of hierarchies.

show abstract

Evaluation of Morphological Hierarchies for Supervised Segmentation

Cited by 19 publications

References 22 publications

Hierarchizing graph-based image segmentation algorithms relying on region dissimilarity

Hierarchizing graph-based image segmentation algorithms relying on region dissimilarity

Tag Propagation Approaches within Speaking Face Graphs for Multimodal Person Discovery

Evaluation of Combinations of Watershed Hierarchies

Contact Info

Product

Resources

About