Abstract
In Chap. 1, we introduced the concept of feature coding as well as its role in the Bag-of-Features model. In this chapter, we will discuss the taxonomy of feature coding. First intuitively describe several classic feature coding algorithms, and then categorize them in two ways, namely Taxonomy I according to their final representations and Taxonomy II according to their original motivations. Taxonomy I involves the number of codewords for describing a feature and the dimensions for the coding response on a codeword. This way is easy for readers to quickly know about the algorithms, especially their main steps. The second way is for an in-depth understanding of feature coding. According to their motivations, most feature coding algorithms belong to one of the five main categories: (1) Voting based coding; (2) Fisher coding; (3) Reconstruction based coding; (4) Local tangent based coding; and (5) Saliency based coding. This chapter is closely related to the content in the following chapters, e.g. the formulation, motivations and relationships of various feature coding algorithms, as well as how they evolve.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
G. Csurka, C. Bray, C. Dance, L. Fan, Visual categorization with bags of keypoints, in European Conference on Computer Vision (2004)
Y. Huang, K. Huang, Y. Yu, T. Tan, Salient coding for image classification, in IEEE Conference on Computer Vision and Pattern Recognition (2011)
J. Gemert, J. Geusebroek, C. Veenman, A. Smeulders, Kernel codebooks for scene categorization, in European Conference on Computer Vision (2008)
J. Yang, K. Yu, Y. Gong, T. Huang, Linear spatial pyramid matching using sparse coding for image classification, in IEEE Conference on Computer Vision and Pattern Recognition (2009)
K. Yu, T. Wang, Y. Gong, Nonlinear learning using local coordinate coding. Advances in Neural Information Processing Systems (2009)
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)
Z. Wu, Y. Huang, L. Wang, T. Tan, Group encoding of local features in image classification, in International Conference on Pattern Recognition (2012)
Xi. Zhou, K. Yu, T. Zhang, T. Huang, Image classification using super-vector coding of local image descriptors, in European Conference on Computer Vision (2010)
K. Yu, T. Zhang, Improved local coordinate coding using local tangents, in International Conference on Machine Learning (2010)
F. Perronnin, C. Dance, Fisher Kernels on visual vocabularies for image categorization, in IEEE Conference on Computer Vision and Pattern Recognition (2007)
Y. Huang, Z. Wu, L. Wang, T. Tan, Feature coding in image classification: a comprehensive study. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 493–506 (2014)
F. Perronnin, J. Sanchez, T. Mensink, Improving the Fisher Kernel for large-scale image classification, in European Conference on Computer Vision (2010)
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). Taxonomy. 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_2
Download citation
DOI: https://doi.org/10.1007/978-3-662-45000-0_2
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)