Segmentation of Natural Images by Texture and Boundary Compression

@article{Mobahi2011SegmentationON,
  title={Segmentation of Natural Images by Texture and Boundary Compression},
  author={Hossein Mobahi and Shankar R. Rao and Allen Yuqing Yang and S. Shankar Sastry and Yi Ma},
  journal={International Journal of Computer Vision},
  year={2011},
  volume={95},
  pages={86-98}
}
We present a novel algorithm for segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations that a homogeneously textured region of a natural image can be well modeled by a Gaussian distribution and the region boundary can be effectively coded by an adaptive chain code. The optimal segmentation of an image is the one that gives the shortest coding length for encoding all textures and boundaries in the image, and is… 
View on Springer
arxiv.org
147 Citations
Highly Influential Citations
13
Background Citations
34
Methods Citations
48
Results Citations
3

147 Citations

Rival Penalized Image Segmentation

TLDR
This paper extracts local homogeneity, textures and color features from images and describes them with Gaussian Mixture Models to cast natural image segmentation into a problem of feature clustering.

Using contour information for image segmentation

TLDR
An improved weight function that incorporates contour feature into the dissimilarity measure of pixels and gives better result while other measures including Probabilistic Rand Index, Variation of Information, and Boundary Displacement Error are close to the best result given by state-of-the-art algorithms.

Fusion of visual cues of intensity and texture in Markov random fields image segmentation

TLDR
Experimental results confirm the hypothesis that the integration of edge information increases the precision of the segmentation by ensuring the conservation of the homogeneous objects contours during the region growing process.

Segmentation of Visual Images by Sequential Extracting Homogeneous Texture Areas

TLDR
The research results in development of the segmentation algorithm realized as a computer program tested in a series of experiments that demonstrate its efficiency on grayscale natural scenes.

Model-Based Learning of Local Image Features for Unsupervised Texture Segmentation

TLDR
A two-stage algorithm which first learns suitable convolutional features and then performs segmentation, which achieves a competitive rank in the Prague texture segmentation benchmark, and it is effective for segmenting histological images.

Unsupervised Texture Segmentation of Natural Scene Images Using Region-based Markov Random Field

TLDR
This work proposes a novel unsupervised texture segmentation method by using the Region-based Markov Random Field (RMRF) model which enforces the spatial coherence between neighbor regions and introduces the concept of pivot regions which plays a decisive role to incorporate local data interaction.

Co-Sparse Textural Similarity for Image Segmentation

TLDR
An algorithm for segmenting natural images based on texture and color information, which leverages the co-sparse analysis model for image segmentation within a convex multilabel optimization framework is proposed, which outperforms state-of-the-art interactive segmentation methods on the Graz Benchmark.

Extraction of homogeneous fine-grained texture segments in visual images

TLDR
A series of experiments demonstrates efficiency of the algorithm in extraction of homogeneous fine-grained texture segments and the segmentation looks reasonable “from a human point of view”.

A regularization-based approach for unsupervised image segmentation

TLDR
The algorithm was tested on a standard evaluation data set, where it performs on par with state-of-the-art algorithms in terms of precision and greatly outperforms the state of the art by reducing the oversegmentation of the object of interest.

Hierarchical image segmentation via recursive superpixel with adaptive regularity

TLDR
An energy optimization algorithm that allows a pixel to be shared by multiple regions to improve the accuracy and appropriate the number of segments and overtakes the other algorithms in terms of balance between accuracy and computational time.
...

References

SHOWING 1-10 OF 42 REFERENCES

Natural Image Segmentation with Adaptive Texture and Boundary Encoding

We present a novel algorithm for unsupervised segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations that a homogeneously…

Contour and Texture Analysis for Image Segmentation

TLDR
This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture, and introduces a gating operator based on the texturedness of the neighborhood at a pixel to facilitate cue combination.

Boundary Extraction in Natural Images Using Ultrametric Contour Maps

  • Pablo Arbeláez
  • Computer Science
    2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06)
  • 2006
TLDR
This paper presents a low-level system for boundary extraction and segmentation of natural images and the evaluation of its performance proves that this system outperforms significantly two widely used hierarchical segmentation techniques, as well as the state of the art in local edge detection.

Unsupervised Segmentation of Color-Texture Regions in Images and Video

TLDR
The focus of this work is on spatial segmentation, where a criterion for "good" segmentation using the class-map is proposed and applying the criterion to local windows in theclass-map results in the "J-image," in which high and low values correspond to possible boundaries and interiors of color-texture regions.

A nonparametric statistical method for image segmentation using information theory and curve evolution

TLDR
This paper solves the information-theoretic optimization problem by deriving the associated gradient flows and applying curve evolution techniques and uses level-set methods to implement the resulting evolution.

Saliency driven total variation segmentation

This paper introduces an unsupervised color segmentation method. The underlying idea is to segment the input image several times, each time focussing on a different salient part of the image and to…

Combining region splitting and edge detection through guided Delaunay image subdivision

  • T. GeversA. Smeulders
  • Computer Science
    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
TLDR
Experiments on a real image indicate that the adaptive split-and-merge segmentation method yields good segmentation results even when there is a quadratic sloping of intensities particularly suited for segmenting natural scenes of man-made objects.

Yet Another Survey on Image Segmentation: Region and Boundary Information Integration

TLDR
This paper reviews different segmentation proposals which integrate edge and region information and highlights 7 different strategies and methods to fuse such information.

Spectral segmentation with multiscale graph decomposition

TLDR
The segmentation algorithm works simultaneously across the graph scales, with an inter-scale constraint to ensure communication and consistency between the segmentations at each scale, and incorporates long-range connections with linear-time complexity, providing high-quality segmentations efficiently.

Learning Probabilistic Models for Contour Completion in Natural Images

TLDR
This work develops a scale-invariant representation of images from the bottom up, using a piecewise linear approximation of contours and constrained Delaunay triangulation to complete gaps and model curvilinear grouping on top of this graphical/geometric structure.