Abstract
In Chap. 6, we discussed the role of features’ spatial information in enhancing feature coding.In this chapter, we will introduce another strategy for enhancement: modeling high order relationships among codewords [1]. In particular, we will discuss how to exploit the relationship of codewords and how to use it to obtain richer information in feature coding.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For an image patch with the size of \(16\times 16\), the possible number of gray SIFT descriptors is \(256^{16\times 16}\). But the number of codewords is usually less than a million.
- 2.
To describe a local feature, one or more codewords will be used. As a result, these codewords will generate responses on this local feature.
- 3.
The distance between a point and a domination region is defined by the distance from the point to the angular bisector of the domination angle.
- 4.
- 5.
- 6.
- 7.
References
Y. Huang, K. Huang, C. Wang, T. Tan, Exploring relations of visual words for image classification, in IEEE Conference on Computer Vision and Pattern Recognition (2011)
S.P. Lloyd, Least squares quantization in PCM. IEEE Trans. Inf. Theory 28(2), 129–137 (1982)
T. Joachims, Text categorization with support vector machines: learning with many relevant features, in ECML (1998)
G. Csurka, C. Bray, C. Dance, L. Fan, Visual categorization with bags of keypoints, in European Conference on Computer Vision (2004)
J. Wang, J. Yang, K. Yu, F. Lv, T. Huang, Y. Gong, Locality-constrained linear coding for image classification, in IEEE Conference on Computer Vision and Pattern Recognition (2010)
D.G. Lowe, Distinctive image features from scale-invariant key-points. Int. J. Comput. Vis. 2(60), 91–110 (2004)
S. Lazebnik, C. Schmid, J. Ponce, Beyond bags of features: spatial pyramid matching for recognizing natural scene categories, in IEEE Conference on Computer Vision and Pattern Recognition (2006)
Y. Boureau, N. Roux, F. Bach, J. Ponce, Y. LeCun, Ask the locals: multi-way local pooling for image recognition, in IEEE Conference on Computer Vision (2011)
G. Griffin, A. Holub, P. Perona, Caltech-256 object category dataset (2007)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2014 The Author(s)
About this chapter
Cite this chapter
Huang, Y., Tan, T. (2014). Enhancement via Integrating High Order Coding Information. In: Feature Coding for Image Representation and Recognition. SpringerBriefs in Computer Science. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45000-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-662-45000-0_7
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-44999-8
Online ISBN: 978-3-662-45000-0
eBook Packages: Computer ScienceComputer Science (R0)