Using contours to detect and localize junctions in natural images

@article{Maire2008UsingCT,
  title={Using contours to detect and localize junctions in natural images},
  author={Michael Maire and Pablo Andr{\'e}s Arbel{\'a}ez and Charless C. Fowlkes and Jitendra Malik},
  journal={2008 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2008},
  pages={1-8}
}
Contours and junctions are important cues for perceptual organization and shape recognition. Detecting junctions locally has proved problematic because the image intensity surface is confusing in the neighborhood of a junction. Edge detectors also do not perform well near junctions. Current leading approaches to junction detection, such as the Harris operator, are based on 2D variation in the intensity signal. However, a drawback of this strategy is that it confuses textured regions with… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 361 CITATIONS, ESTIMATED 25% COVERAGE

1 Structured Prediction for Object Boundary Detection in Images

VIEW 24 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Efficient image contour detection using edge prior

  • 2013 IEEE International Conference on Multimedia and Expo (ICME)
  • 2013
VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

When should you calibrate your camera ?

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Contour detection and image segmentation

VIEW 12 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Enhancing low-level features with mid-level cues

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Detecting 3D geometric boundaries of indoor scenes under varying lighting

  • IEEE Winter Conference on Applications of Computer Vision
  • 2014
VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Accurate Junction Detection and Characterization in Natural Images

  • International Journal of Computer Vision
  • 2013
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Image Segmentation Using a Sparse Coding Model of Cortical Area V 1

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Image Segmentation Using a Sparse Coding Model of Cortical Area V1

  • IEEE Transactions on Image Processing
  • 2013
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2008
2019

CITATION STATISTICS

  • 47 Highly Influenced Citations

  • Averaged 20 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES

Untangling Cycles for Contour Grouping

  • 2007 IEEE 11th International Conference on Computer Vision
  • 2007
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

A Min-Cover Approach for Finding Salient Curves

  • 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06)
  • 2006
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Supervised Learning of Edges and Object Boundaries

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Scale-invariant contour completion using conditional random fields

  • Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
  • 2005
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Segmentation induced by scale invariance

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Learning to detect natural image boundaries using local brightness, color, and texture cues

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2003
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

A computational approach to edge detection

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

A Combined Corner and Edge Detector

  • Alvey Vision Conference
  • 1988
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Graph Partitioning by Spectral Rounding: Applications in Image Segmentation and Clustering

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…