Hierarchical Image Segmentation Based on Iterative Contraction and Merging

Syu, Jia-Hao; Wang, Sheng-Jyh; Wang, Lichun

doi:10.1109/tip.2017.2651395

Cited by 44 publications

(26 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the method is simpler than region merging. According to the result, it can be seen that AMR can help seeded segmentation algorithms to achieve a hierarchical segmentation [47], [48]. Hierarchical segmentation is a multilevel segmentation scheme, and it usually outputs a coarse-to-fine hierarchy of segments ordered by the level of details.…”

Section: B the Monotonic Increasingness Property Of Amrmentioning

confidence: 99%

Adaptive Morphological Reconstruction for Seeded Image Segmentation

Lei

Jia

Liu

et al. 2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Morphological reconstruction (MR) is often employed by seeded image segmentation algorithms such as watershed transform and power watershed as it is able to filter seeds (regional minima) to reduce over-segmentation. However, MR might mistakenly filter meaningful seeds that are required for generating accurate segmentation and it is also sensitive to the scale because a single-scale structuring element is employed. In this paper, a novel adaptive morphological reconstruction (AMR) operation is proposed that has three advantages. Firstly, AMR can adaptively filter useless seeds while preserving meaningful ones. Secondly, AMR is insensitive to the scale of structuring elements because multiscale structuring elements are employed. Finally, AMR has two attractive properties: monotonic increasingness and convergence that help seeded segmentation algorithms to achieve a hierarchical segmentation. Experiments clearly demonstrate that AMR is useful for improving algorithms of seeded image segmentation and seed-based spectral segmentation. Compared to several state-of-the-art algorithms, the proposed algorithms provide better segmentation results requiring less computing time. Source code is available at https://github.com/SUST-reynole/AMR.

show abstract

Section: B the Monotonic Increasingness Property Of Amrmentioning

confidence: 99%

Adaptive Morphological Reconstruction for Seeded Image Segmentation

Lei

Jia

Liu

et al. 2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Instead of human subjectively specifying the two crucial parameters for removing noisy regions, our approach provides soft‐segmented results based on the estimated appearance overlap, and then automatically set up the relevant parameters in the Dense CRF framework, finally, per‐pixel accurate segmentation results are obtained based on a mean‐field inference. We believe that is the most significant difference between our approach and the GSF‐based approach. (iv) Many other prominent segmentation methods: Such as segmentation based on level set method [40–42], segmentation combined the saliency [43–45], and method based on region merging [6, 46], and so on. In addition, there are some co‐segmentation techniques [47–49] that are used for segmenting common objects in multiple images.…”

Section: Related Workmentioning

confidence: 99%

Adaptive appearance separation for interactive image segmentation based on Dense CRF

Peng

2019

IET Image Processing

View full text Add to dashboard Cite

“…Mathematical morphology has been used in hierarchical image analysis with, e.g., hierarchical watersheds [3,4,5,6], binary partition trees [7,8,9], quasiflat zone hierarchies [10,11], and tree-based shape spaces [12]. Other methods for hierarchical image analysis consider regular and irregular pyramids [13], scale-set theory [14], multiscale combinatorial grouping [15], series of optimization problems [16], and generic image classification based on convolutional neural networks [17].…”

Section: Introductionmentioning

confidence: 99%

Hierarchical segmentation from a non-increasing edge observation attribute

Cayllahua-Cahuina

Cousty²,

Guimarães

et al. 2020

Pattern Recognition Letters

View full text Add to dashboard Cite

Hierarchical image segmentation provides region-oriented scale-spaces: sets of image segmentations at different detail levels in which the segmentations at finer levels are nested with respect to those at coarser levels. Guimarães et al. proposed a hierarchical graph-based image segmentation (HGB) method based on the Felzenszwalb-Huttenlocher dissimilarity. It computes, for each edge of a graph, the minimum scale in a hierarchy at which two regions linked by this edge should be merged according to the dissimilarity. We provide an explicit definition of the (edge-) observation attribute and Boolean criterion which are at the basis of this method and show that they are not increasing. Then, we propose an algorithm to compute all the scales for which the criterion holds true. Finally, we propose new methods to regularize the observation attribute and criterion and to set up the observation scale value of each edge of a graph, following the current trend in mathematical morphology to study criteria which are not increasing on a hierarchy. Assessments on Pascal VOC 2010 and 2012 show that these strategies lead to better segmentation results than the ones obtained with the original HGB method.

show abstract

Hierarchical Image Segmentation Based on Iterative Contraction and Merging

Cited by 44 publications

References 21 publications

Adaptive Morphological Reconstruction for Seeded Image Segmentation

Adaptive Morphological Reconstruction for Seeded Image Segmentation

Adaptive appearance separation for interactive image segmentation based on Dense CRF

Hierarchical segmentation from a non-increasing edge observation attribute

Contact Info

Product

Resources

About