article

Learning spatial relations in object recognition

Authors:

Arnold W. M. SmeuldersAuthors Info & Claims

Pattern Recognition Letters, Volume 27, Issue 14

Pages 1673 - 1684

https://doi.org/10.1016/j.patrec.2006.03.016

Published: 15 October 2006 Publication History

Abstract

This paper studies two types of spatial relationships that can be learned from training examples for object recognition. The first one employs deformable relationships between object parts with a Gaussian model, while the second one describes pairwise relationships between pixel intensity values using Bayesian networks. We perform experiments on a human face dataset and a horse dataset, imposing the same amount of annotation of training data, which can be seen as sending knowledge to the learning algorithms. The result indicates that the Bayesian network method compares favorably to the deformable model, as it can capture long-distance stable relations in the object appearance. We also conclude that both methods are superior to strictly spatial matching by template and strictly non-spatial classifiers.

References

[1]

Graph matching for visual object recognition. Spatial Vision. v13. 335-340.]]

[2]

Burl, M., Perona, P. 1996. Recognition of planar object classes. In: Proc. CVPR'96, pp. 223-230.]]

[3]

Colmenarez, A., Huang, T., 1997. Face detection with information-based maximum discrimination. In: Proc. CVPR'97, pp. 782-787.]]

[4]

Support vector networks. Machine Learn. v20. 273-297.]]

[5]

Deselaers, T., Keysers, D., Ney, H. 2005. Discriminative training for object recognition using image patches. In: Proc. CVPR'05, vol. II, pp. 157-162.]]

[6]

Query processing in spatial-query-by-sketch. J. Visual Lang. Comput. v8 i4. 403-424.]]

[7]

Felzenszwalb, P., Huttenlocher, D. 2000. Efficient matching of pictorial structures. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 66-75.]]

[8]

Fergus, R., Perona, P., Zisserman, A., 2003. Object class recognition by unsupervised scale-invariant learning. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, vol. 2, pp. 264-271.]]

[9]

The representation and matching of pictorial structure. IEEE Trans. Comput. v22 i1. 67-92.]]

[10]

Fussenegger, M., Opelt, A., Pinz, A., Auer, P. 2004. Object recognition using segmentation for feature detection. In: Proc. ICPR'04, vol. III, pp. 41-48.]]

[11]

Gao, D., Vasconcelos, N., 2005. Discriminant saliency for visual recognition from cluttered scenes. In: Advances in Neural Information Processing Systems, vol. 17, pp. 481-488.]]

[12]

. In: Jordan, M.I. (Ed.), Learn. Graph. Models, MIT Press.]]

[13]

Gradient-based learning applied to document recognition. Proc. IEEE. v86 i11. 2278-2324.]]

[14]

Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufman.]]

[15]

Pham, T.V., Smeulders, A.W.M., 2004. Statistical strategy for object class recognition using part detectors. In: Leonardis, A., Bischof, H. (Eds.), Proc. Statistical Learning in Computer Vision, pp. 33-48.]]

[16]

Face detection by aggregated Bayesian network classifiers. Pattern Recognition Lett. v23 i4. 451-461.]]

[17]

Digital Image Processing. second ed. Wiley.]]

[18]

A shape analysis model with applications to a character recognition system. IEEE Trans. Pattern Anal. Machine Intell. v16 i4. 393-404.]]

[19]

Schneiderman, H., Kanade, K. 2000. A statistical method for 3D object detection applied to faces and cars. In: Proc. CVPR 2000, pp. 746-751.]]

[20]

Recognition of shapes by editing their shock graphs. IEEE Trans. Pattern Anal. Machine Intell. v26 i5. 550-571.]]

[21]

Shock graphs and shape matching. Internat. J. Comput. Vision. v30. 1-24.]]

[22]

An Introduction to Multivariate Statistics. North Holland.]]

[23]

Example-based learning for view-based human face detection. IEEE PAMI. v20 i1. 39-51.]]

[24]

Arrangement: A spatial relation between parts for evaluating similarity of tomographic section. IEEE Trans. Pattern Anal. Machine Intell. v17 i9. 880-893.]]

[25]

Finding optimum branchings. Networks. v7. 25-35.]]

[26]

Weber, M., Welling, M., Perona, P., 2000. Unsupervised learning of models for recognition. In: Proc. ECCV, pp. 18-32.]]

Cited By

Ghosh PMitchell MTanyi JHung A(2016)Incorporating priors for medical image segmentation using a genetic algorithmNeurocomputing10.1016/j.neucom.2015.09.123195:C(181-194)Online publication date: 26-Jun-2016
https://dl.acm.org/doi/10.1016/j.neucom.2015.09.123
Santosh KLamiroy BWendling L(2014)Integrating vocabulary clustering with spatial relations for symbol recognitionInternational Journal on Document Analysis and Recognition10.1007/s10032-013-0205-417:1(61-78)Online publication date: 1-Mar-2014
https://dl.acm.org/doi/10.1007/s10032-013-0205-4
Pham TMulhem PMaisonnasse LGaussier ELim J(2012)Visual graph modeling for scene recognition and mobile robot localizationMultimedia Tools and Applications10.1007/s11042-010-0598-860:2(419-441)Online publication date: 1-Sep-2012
https://dl.acm.org/doi/10.1007/s11042-010-0598-8
Show More Cited By

Index Terms

Learning spatial relations in object recognition
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Object recognition
  2. Machine learning
2. Mathematics of computing
  1. Probability and statistics
    1. Probabilistic algorithms
    2. Probabilistic reasoning algorithms
      1. Markov-chain Monte Carlo methods
      2. Sequential Monte Carlo methods

Recommendations

Multi-label learning by exploiting label dependency
KDD '10: Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining

In multi-label learning, each training example is associated with a set of labels and the task is to predict the proper label set for the unseen example. Due to the tremendous (exponential) number of possible label sets, the task of learning from multi-...
Expression-assisted facial action unit recognition under incomplete AU annotation

Facial action unit (AU) recognition is an important task for facial expression analysis. Traditional AU recognition methods typically include a supervised training, where the AU annotated training images are needed. AU annotation is a time consuming, ...
Improving image categorization by using multiple instance learning with spatial relation
ICIAP'11: Proceedings of the 16th international conference on Image analysis and processing: Part I

Image categorization is a challenging problem when a label is provided for the entire training image only instead of the object region. To eliminate labeling ambiguity, image categorization and object localization should be performed simultaneously. ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Pattern Recognition Letters

Pattern Recognition Letters Volume 27, Issue 14

15 October 2006

175 pages

ISSN:0167-8655

Issue’s Table of Contents

Copyright © Elsevier B.V. © 2006.

Publisher

Elsevier Science Inc.

United States

Publication History

Published: 15 October 2006

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Ghosh PMitchell MTanyi JHung A(2016)Incorporating priors for medical image segmentation using a genetic algorithmNeurocomputing10.1016/j.neucom.2015.09.123195:C(181-194)Online publication date: 26-Jun-2016
https://dl.acm.org/doi/10.1016/j.neucom.2015.09.123
Santosh KLamiroy BWendling L(2014)Integrating vocabulary clustering with spatial relations for symbol recognitionInternational Journal on Document Analysis and Recognition10.1007/s10032-013-0205-417:1(61-78)Online publication date: 1-Mar-2014
https://dl.acm.org/doi/10.1007/s10032-013-0205-4
Pham TMulhem PMaisonnasse LGaussier ELim J(2012)Visual graph modeling for scene recognition and mobile robot localizationMultimedia Tools and Applications10.1007/s11042-010-0598-860:2(419-441)Online publication date: 1-Sep-2012
https://dl.acm.org/doi/10.1007/s11042-010-0598-8
Antúnez EMarfil RBandera A(2011)A new perception-based segmentation approach using combinatorial pyramidsProceedings of the 16th international conference on Image analysis and processing: Part I10.5555/2042620.2042662(327-336)Online publication date: 14-Sep-2011
https://dl.acm.org/doi/10.5555/2042620.2042662
Brombach BBruns EBimber OConati CBauer MOliver NWeld D(2009)Subobject detection through spatial relationships on mobile phonesProceedings of the 14th international conference on Intelligent user interfaces10.1145/1502650.1502688(267-276)Online publication date: 8-Feb-2009
https://dl.acm.org/doi/10.1145/1502650.1502688

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents