Textons, contours and regions: cue integration in image segmentation

Malik, Jitendra; Belongie, Serge; Shi, Jianfeng; Leung, Thomas

doi:10.1109/iccv.1999.790346

Cited by 221 publications

(157 citation statements)

References 16 publications

Supporting

Mentioning

155

Contrasting

Order By: Relevance

“…affine transformations yielding a procrustean density on feature constellations (see [21] and references therein). At the opposite end are "bags of features" that retain only feature labels regardless of their mutual position (see [22][23][24] and references therein). Viewpoint changes induce transformations more general than affine, but far less general than an arbitrary scrambling of feature positions.…”

Section: State Of the Artmentioning

confidence: 99%

Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions

Vedaldi

Soatto

2006

Computer Vision – ECCV 2006

View full text Add to dashboard Cite

Abstract. We study the set of domain deformations induced on images of three-dimensional scenes by changes of the vantage point. We parametrize such deformations and derive empirical statistics on the parameters, that show a kurtotic behavior similar to that of natural image and range statistics. Such a behavior would suggest that most deformations are locally smooth, and therefore could be captured by simple parametric maps, such as affine ones. However, we show that deformations induced by singularities and occluding boundaries, although rare, are highly salient, thus warranting the development of dedicated descriptors. We therefore illustrate the development of viewpoint invariant descriptors for singularities, as well as for occluding boundaries. We test their performance on scenes where the current state of the art based on affine-invariant region descriptors fail to establish correspondence, highlighting the features and shortcomings of our approach.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions

Vedaldi

Soatto

2006

Computer Vision – ECCV 2006

View full text Add to dashboard Cite

show abstract

“…First, the features of interest were windowed histograms of intensity. Second, we create a set of features consisting of windowed histograms of textons [3], position and intensity. Although we performed this segmentation work in 2D, it is important to clarify that both, Ncut and the Nyström approximation method can be applied in 3D.…”

Section: Segmentation Of Vertebral Bodiesmentioning

confidence: 99%

“…the matrix containing the similarity weights between the different pixel features) through the Nyström approximation method, the χ 2 test, a simple and effective measurement of histogram similarity [3], is performed based on the previous selection of 15 random histograms. Now we are ready to solve the eigenvalue problem of the Ncut technique through the Nyström approximation method [2].…”

Section: -I) Windowed Histograms Of Intensitymentioning

confidence: 99%

Normalized cuts for spinal MRI segmentation

Carballido‐Gamio

Belongie

Majumdar

2002

CARS 2002 Computer Assisted Radiology and Surgery

View full text Add to dashboard Cite

Segmentation of bony structures plays an important role in image guided surgery of the spine. In this paper, we discuss a novel approach to the segmentation of vertebral bodies from 2D sagittal magnetic resonance images of the spine. We have applied Normalized Cuts with the Nyström approximation method to MR sagittal images of the spine taking windowed histograms of intensity or textons as the most promising features. Both, Normalized cuts and the Nyström approximation method have shown to be a powerful segmentation technique in different fields, but its usefulness in the medical imaging environment has not been shown yet. Results in T1 high-resolution images of the spine have been encouraging to pursue further research in this difficult task.

show abstract

“…The diversity in segment types has led to a wide range of approaches for image segmentation: Algorithms for extracting uniformly colored regions (e.g., [1,2]), algorithms for extracting textured regions (e.g., [3,4]), algorithm for extracting regions with a distinct empirical color distribution (e.g., [5,6,7]). Some algorithms employ symmetry cues for image segmentation (e.g., [8]), while others use high-level semantic cues provided by object classes (i.e., class-based segmentation, see [9,10,11]).…”

Section: Introductionmentioning

confidence: 99%

What Is a Good Image Segment? A Unified Approach to Segment Extraction

Bagon

Boiman

Irani

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. There is a huge diversity of definitions of "visually meaningful" image segments, ranging from simple uniformly colored segments, textured segments, through symmetric patterns, and up to complex semantically meaningful objects. This diversity has led to a wide range of different approaches for image segmentation. In this paper we present a single unified framework for addressing this problem -"Segmentation by Composition". We define a good image segment as one which can be easily composed using its own pieces, but is difficult to compose using pieces from other parts of the image. This non-parametric approach captures a large diversity of segment types, yet requires no pre-definition or modelling of segment types, nor prior training. Based on this definition, we develop a segment extraction algorithm -i.e., given a single point-ofinterest, provide the "best" image segment containing that point. This induces a figure-ground image segmentation, which applies to a range of different segmentation tasks: single image segmentation, simultaneous co-segmentation of several images, and class-based segmentations.

show abstract

Textons, contours and regions: cue integration in image segmentation

Abstract: Abstract

Cited by 221 publications

References 16 publications

Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions

Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions

Normalized cuts for spinal MRI segmentation

What Is a Good Image Segment? A Unified Approach to Segment Extraction

Contact Info

Product

Resources

About