Abstract
At any given moment, humans eye captures a large amount of information simultaneously. Among these information, human visual system is able to select specific information in which human is interested. In recent years, there have been trials for (system) experimental, computational and theoretical studies on imitating human visual system, which are commonly referred as sparse coding. When any visual stimuli are given, human visual system makes a minimal number of neurons activated efficiently. It increases the storage capacity in associative memories. A set of activated neurons and deactivated neurons are called sparse code and the process to make sparse code is called sparse coding. In this paper, the effectiveness of the proposed method is demonstrated for Graz-02 dataset. And visual words were visualized that were relevant to activated neurons as patch-level images and sparse coding. By displaying active neurons that are represented by visual words, sparse coding could be a solution to top-down visual object detection.
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
Preview
Unable to display preview. Download preview PDF.
References
Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: CVPR 2005 (2005)
Olshausen, B., Field, D.: Sparse coding of sensory Inputs. Current Opinion in Neurobiology 14(4), 481–487 (2004)
Yang, J., Yang, M.-H.: Top-down visual saliency via Joint CRF andDictionary Learning. In: CVPR (2012)
Laffety, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence. ACM (2001)
Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)
Szummer, M., Kohli, P., Hoiem, D.: Learning cRFs using graph cuts. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 582–595. Springer, Heidelberg (2008)
Yang, J., Yu, K., Huang, T.: Supervised translation-invariant sparse coding. In: CVPR (2010)
Tosic, I., Frossard, P.: Dictionary Learning. IEEE Signal Processing Magazine (2011)
Jolliffe, I.: Principal Component Analysis. Springer, New York (1986)
Information-maximization approach to blind separation and blind deconvolution. Neural Comput. 7(6), 1129–1159 (1995)
Barlow, H.B.: Possible principles underlying the transformations of sensory messages. In: Rosenblith, W. (ed.) Sensory Communication, ch. 13, pp. 217–234. MIT Press, Cambridge (1961)
Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: NIPS (2006)
Joachims, T., Finley, T., Yu, C.-N.: Cutting-plane training of structural svms. Machine Learning 77(1), 27–59 (2009)
Yang, J., Yu, K., Huang, T.: Supervised translation-invariant sparse coding. In: CVPR (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Yoo, Y.H., Kim, J.H. (2014). Target-Driven Visual Words Representation via Conditional Random Field and Sparse Coding. In: Kim, JH., Matson, E., Myung, H., Xu, P., Karray, F. (eds) Robot Intelligence Technology and Applications 2. Advances in Intelligent Systems and Computing, vol 274. Springer, Cham. https://doi.org/10.1007/978-3-319-05582-4_60
Download citation
DOI: https://doi.org/10.1007/978-3-319-05582-4_60
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-05581-7
Online ISBN: 978-3-319-05582-4
eBook Packages: EngineeringEngineering (R0)