Shape matching and object recognition using shape contexts

@article{Belongie2010ShapeMA,
  title={Shape matching and object recognition using shape contexts},
  author={Serge J. Belongie and Jitendra Malik and Jan Puzicha},
  journal={2010 3rd International Conference on Computer Science and Information Technology},
  year={2010},
  volume={9},
  pages={471-474}
}
This paper presents my work on computing shape models that are computationally fast and invariant basic transformations like translation, scaling and rotation. In this paper, I propose shape detection using a feature called shape context. Shape context describes all boundary points of a shape with respect to any single boundary point. Thus it is descriptive of the shape of the object. Object recognition can be achieved by matching this feature with a priori knowledge of the shape context of the… 

Figures from this paper

Shape matching and object recognition using shape contexts

TLDR
This paper presents work on computing shape models that are computationally fast and invariant basic transformations like translation, scaling and rotation, and proposes shape detection using a feature called shape context, which is descriptive of the shape of the object.

A Fast Shape Context Matching Using Indexing

TLDR
The proposed algorithm uses the mean distances and standard deviations of shape contexts as the index of shapes to reduce the search space of the previous work on shape matching with shape context descriptor.

Two-dimensional shape matching by shape distributions

  • H. WuXiang Liu
  • Computer Science
    2010 Sixth International Conference on Natural Computation
  • 2010
TLDR
A novel and distinctive shape descriptor based on shape distributions that is not only invariant to rotation, translation and scale but also insensitive to shape occlusion and deformation is presented.

Recognition of shape parts using shape geodesies

TLDR
A robust distance is defined based on geodesics in the shape space based on elastic shape matching to handle elastic deformations and compare shape parts locally and outperforms existing schemes for shape part recognition.

A Corner Potential Flow based Shape Descriptor for Object Recognition

TLDR
A novel shape signature for recognizing the objects in complex plane is proposed, applied on the contour shape representation, and then the description of representative shape features with the corner potential flow measure followed by the Fourier transformation.

Deformable HOG-Based Shape Descriptor

TLDR
A new deformable feature extraction method that adapts to the shape to be described, dealing in this way with the variability introduced in the handwriting domain, significantly outperform other descriptors in the literature for the task of hand-drawn shape recognition and handwritten word retrieval.

A Non-rigid Feature Extraction Method for Shape Recognition

TLDR
The proposed methodology consists in a novel feature extraction technique, which uses a non-rigid representation adaptable to the shape that adapts its representation to the given shape and encodes the pixel density distribution.

Contour Based Shape Matching for Object Recognition

TLDR
The experimental results validate that the proposed novel contour signature is robust to rotation, scaling, occlusion, intra-class variations and articulated variations, and the superior shape matching and retrieval accuracy on benchmark datasets verifies the effectiveness of the method.

Object Recognition Using Junctions

TLDR
An object detection/recognition algorithm based on a new set of shape-driven features and morphological operators that is robust to a certain degree of scale change and has advantages of recognizing object parts and dealing with occlusions.

Circle filling rate descriptor for object recognition

  • Yahya SirinM. F. Demirci
  • Computer Science
    2013 21st Signal Processing and Communications Applications Conference (SIU)
  • 2013
TLDR
This work presents a shape description technique, which is based on the local shape filling rate of object silhouettes, which calculates the ratio between pixels that lie within the shape and the total number of pixels in each circle.
...

References

SHOWING 1-10 OF 94 REFERENCES

Shape matching and object recognition using shape contexts

TLDR
This paper presents work on computing shape models that are computationally fast and invariant basic transformations like translation, scaling and rotation, and proposes shape detection using a feature called shape context, which is descriptive of the shape of the object.

A Shape Descriptor for Shapes with Boundary Noise and Texture

TLDR
A part-based shape descriptor that incorporates both the description of the general shape form of each subpart and its geometric relationship with other connected parts, and a saliency measure that weighs each part’s visual significance is incorporated into the shape matching process.

Affine invariant model-based object recognition

TLDR
An efficient matching algorithm, which assumes affine approximation to the prospective viewing transformation, is proposed and was successfully tested in recognition of industrial objects appearing in composite occluded scenes.

Shape context and chamfer matching in cluttered scenes

TLDR
It is shown that the robustness of shape matching can be increased by including a figural continuity constraint, and the combined shape and continuity cost is minimized using the Viterbi algorithm on features, resulting in improved localization and correspondence.

Deformable Templates for Face Recognition

  • A. Yuille
  • Computer Science
    Journal of Cognitive Neuroscience
  • 1991
We describe an approach for extracting facial features from images and for determining the spatial organization between these features using the concept of a deformable template. This is a

Recognizing objects by matching oriented points

  • A. JohnsonM. Hebert
  • Computer Science
    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
TLDR
This work presents an approach to recognition of complex objects in cluttered 3-D scenes that does not require feature extraction or segmentation, and demonstrates the effectiveness of the algorithm with results showing recognition of complexes in clutters scenes with occlusion.

Shape Discrimination Using Fourier Descriptors

  • E. PersoonK. Fu
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1986
TLDR
A critical review is given of two kinds of Fourier descriptors and a distance measure is proposed, in terms of FD's, that measures the difference between two boundarv curves.

Object recognition from local scale-invariant features

  • D. Lowe
  • Computer Science
    Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
TLDR
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.

Efficient and Robust Retrieval by Shape Content through Curvature Scale Space

We introduce a very fast and reliable method for shape similarity retrieval in large image databases which is robust with respect to noise, scale and orientation changes of the objects. The maxima of

Shape descriptors for non-rigid shapes with a single closed contour

TLDR
This paper reports on the MPEG-7 Core Experiment CE-Shape, which gave a unique opportunity to compare various shape descriptors for non-rigid shapes with a single closed contour and found that a more theoretical comparison of these descriptors seems to be extremely hard.
...