Contour Detection and Hierarchical Image Segmentation

@article{Arbelez2011ContourDA,
  title={Contour Detection and Hierarchical Image Segmentation},
  author={Pablo Arbel{\'a}ez and Michael Maire and Charlotte Fowlkes and Julien Malik},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2011},
  volume={33},
  pages={898-916}
}
  • P. Arbeláez, M. Maire, J. Malik
  • Published 1 May 2011
  • Computer Science
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. [] Key Method Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation…
A NOVEL IMAGE SEGMENTATION AND CONTOUR DETECTION METHOD USING SUPER PIXEL AND MODULARITY
TLDR
An efficient algorithm based on modularity optimization and super pixel is proposed that produces extensive segmentation, preserves repetitive patterns with attractive time complexity, and achieves object-level segmentation to some extent.
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.
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.
Image Segmentation Using Hierarchical Merge Tree
TLDR
This paper uses a tree structure to represent the hierarchy of region merging to reduce the problem of segmenting image regions to finding a set of label assignment to tree nodes, and forms a constrained conditional model to associate region merging with likelihoods predicted using an ensemble boundary classifier.
Image Segmentation Using Hierarchical Merge Tree and Contour shape
TLDR
This paper forms the tree structure as a constrained conditional model to associate region merging with likelihoods predicted using an ensemble boundary classifier and presents an iterative training and testing algorithm that generates various tree structures and combines them to emphasize accurate boundaries by segmentation accumulation.
Consensus Region Merging for Image Segmentation
  • F. Nielsen, R. Nock
  • Computer Science
    2013 2nd IAPR Asian Conference on Pattern Recognition
  • 2013
TLDR
A novel segmentation algorithm that consists in combining many runs of a simple and fast randomized segmentation algorithms is proposed that yields a soft-edge closed contour detector and the theoretical probabilistic framework is described.
Hierarchical segmentation for color images
  • Qiang Chen
  • Computer Science
    2015 8th International Congress on Image and Signal Processing (CISP)
  • 2015
TLDR
This paper applies multiscale normalized cut to image pre-segmentation step to replace Voronoi algorithm or watershed transformation and an improved ultrametric measure method is introduced and employed to merger regions.
Contour detection based on gaussian filter
TLDR
Gaussian filter is used for detection of contour and segmentation of an image and it is shown that it gives proper curves present in the desired area while edge detection provides only edges and pixel points.
A Hierarchical Image Segmentation Algorithm Based on an Observation Scale
TLDR
This work proposes a hierarchical graph based image segmentation relying on a criterion popularized by Felzenszwalb and Huttenlocher, and quantitative and qualitative assessments of the method shows efficiency, ease of use and robustness of this method.
Consensus-Based Image Segmentation via Topological Persistence
  • Qian Ge, E. Lobaton
  • Computer Science, Mathematics
    2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2016
TLDR
A new approach to capture the consensus of information from a set of segmentations generated by varying parameters of different algorithms is proposed and a robust segmentation is obtained with the detection of certain segmentation curves guaranteed.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 89 REFERENCES
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.
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.
From contours to regions: An empirical evaluation
TLDR
This work provides extensive experimental evaluation to demonstrate that, when coupled to a high-performance contour detector, the OWT-UCM algorithm produces state-of-the-art image segmentations.
Contour Continuity in Region Based Image Segmentation
TLDR
A way of incorporating curvilinear grouping into region-based image segmentation through normalized cut approach and results on a large variety of images are shown.
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
Constrained image segmentation from hierarchical boundaries
TLDR
This paper considers an Ultrametric Contour Map, the representation of a hierarchy of segmentations as a real-valued boundary image, and proposes an algorithm for constructing Voronoi tessellations with respect to a distance defined by the UCM.
Efficient, high-quality image contour detection
TLDR
This work examines efficient parallel algorithms for performing image contour detection, with particular attention paid to local image analysis as well as the generalized eigensolver used in Normalized Cuts, and proposes a contour detector that provides uncompromised contour accuracy.
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
Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration
TLDR
A bottom-up aggregation approach to image segmentation that takes into account intensity and texture distributions in a local area around each region and incorporates priors based on the geometry of the regions, providing a complete hierarchical segmentation of the image.
A multiscale algorithm for image segmentation by variational method
TLDR
The authors prove that the most simple segmentation tool, the “region merging” algorithm, is enough to compute a local energy minimum belonging to a compact class and to achieve the job of most of the tools mentioned above.
...
1
2
3
4
5
...