Stochastic image segmentation by typical cuts

Gdalyahu, Yoram; Weinshall, Daphna; Werman, Michael

doi:10.1109/cvpr.1999.784979

Cited by 28 publications

(20 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main research directions for this include mode-seeking [1], [2], deterministic annealing [3], stochastic clustering [4], [5], mixture model [6] [7], rate distortion [8], graph-based model [9], [10], [11], contourbased model [12], [13], and other variational methods [14], [15]. In most researches, the image segmentation problem is described as assigning a label to every pixel in a specific globalization framework.…”

Section: Introductionmentioning

confidence: 99%

Learning full pairwise affinities for spectral segmentation

Kim

Lee

2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

107

View full text Add to dashboard Cite

Abstract-Segmenting a single image into multiple coherent groups remains a challenging task in the field of computer vision. Particularly, spectral segmentation which uses the global information embedded in the spectrum of a given image's affinity matrix is a major trend in image segmentation. This paper focuses on the problem of efficiently learning a full range of pairwise affinities gained by integrating local grouping cues for spectral segmentation. We first construct a sparse multilayer graph whose nodes are both the pixels and the oversegmented regions obtained by an unsupervised segmentation algorithm. By applying the semi-supervised learning strategy to this graph, the intra and interlayer affinities between all pairs of nodes can be estimated without iteration. These pairwise affinities are then applied into the spectral segmentation algorithms. In this paper, two types of spectral segmentation algorithms are introduced: K-way segmentation and hierarchical segmentation. Our algorithms provide high-quality segmentations which preserve object details by directly incorporating the full-range connections. Moreover, since our full affinity matrix is defined by the inverse of a sparse matrix, its eigendecomposition can be efficiently computed. The experimental results on the BSDS and MSRC image databases demonstrate the superiority of our segmentation algorithms in terms of relevance and accuracy compared with existing popular methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Learning full pairwise affinities for spectral segmentation

Kim

Lee

2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

107

View full text Add to dashboard Cite

show abstract

“…Different graph-theoretic methods employ different algorithms to optimize different cost functions. These include Minimum Cut [66], Ratio Regions [13], Normalized Cut [54], Average Cut [49], the methods of Jermyn and Ishikawa [29], Ratio Cut [61], and many more recent methods (e.g., [40], [19], [51], [59], [52], [56], [5], [18]). Some of these methods attempt to solve NP-hard problems using approximate algorithms.…”

Section: Introductionmentioning

confidence: 99%

Salient closed boundary extraction with ratio contour

Wang

Kubota

Siskind

et al. 2005

IEEE Trans. Pattern Anal. Machine Intell.

155

175

View full text Add to dashboard Cite

Abstract-We present ratio contour, a novel graph-based method for extracting salient closed boundaries from noisy images. This method operates on a set of boundary fragments that are produced by edge detection. Boundary extraction identifies a subset of these fragments and connects them sequentially to form a closed boundary with the largest saliency. We encode the Gestalt laws of proximity and continuity in a novel boundary-saliency measure based on the relative gap length and average curvature when connecting fragments to form a closed boundary. This new measure attempts to remove a possible bias toward short boundaries. We present a polynomial-time algorithm for finding the most-salient closed boundary. We also present supplementary preprocessing steps that facilitate the application of ratio contour to real images. We compare ratio contour to two closely related methods for extracting closed boundaries: Elder and Zucker's method based on the shortest-path algorithm and Williams and Thornber's method based on spectral analysis and a strongly-connected-components algorithm. This comparison involves both theoretic analysis and experimental evaluation on both synthesized data and real images.

show abstract

“…The important factor in choosing the edge weights is to make sure they decrease rapidly enough with the decrease in similarity. A common choice (used in [10], [8], [3]) is …”

Section: Resultsmentioning

confidence: 99%

“…An interesting approach not based on bipartitioning is by Y. Gdalyahu, D. Weinshall and M. Werman [3]. They propose a stochastic segmentation algorithm which is based on -way cuts, which is a generalization of the two way cut defined before.…”

Section: Segmentation By Cutsmentioning

confidence: 99%

Image segmentation by nested cuts

Veksler

Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)

View full text Add to dashboard Cite

show abstract

Stochastic image segmentation by typical cuts

Cited by 28 publications

References 4 publications

Learning full pairwise affinities for spectral segmentation

Learning full pairwise affinities for spectral segmentation

Salient closed boundary extraction with ratio contour

Image segmentation by nested cuts

Contact Info

Product

Resources

About