Multi-Feature Bio-Inspired Model for Scene Classification

Article Preview

Abstract:

A multi-feature bio-inspired model for scene image classification (MFBIM) is presented in this work; it extends the hierarchical feedforward model of the visual cortex. Firstly, each of three paths of classification uses each image property (i.e. shape, edge or color based features) independently. Then, BPNN assigns the category of an image based on the previous outputs. Experiments show that the model boosts the classification accuracy over the shape based model. Meanwhile, the proposed approach achieves a high accuracy comparable to other reported methods on publicly available color image dataset.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

1569-1572

Citation:

Online since:

February 2013

Authors:

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] M. Pietikainen T. Maenpaa J. Viertola. Color Texture Classification with Color Histogram and Local Binary Patterns, Proc. 2nd International Workshop on Texture Analysis and Synthesis, June, (2002).

DOI: 10.1109/icpr.2002.1044840

Google Scholar

[2] L. Fei-Fei and P. Perona. A Bayesian Hierarchical Model for Learning Natural Scene Categories. IEEE Computer Vision and Pattern Recognition, 2: 524-531, (2005).

DOI: 10.1109/cvpr.2005.16

Google Scholar

[3] S. Lazebnik, C. Schmid and J. Ponce, Beyond bags features: spatial pyramid matching for recognizing natural scene categories, In IEEE Intl. Conf. on Computer Vision and Pattern Recognition, (2006).

DOI: 10.1109/cvpr.2006.68

Google Scholar

[4] T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber and T. Poggio. Robust object recognition with cortex-like mechanisms. IEEE Trans. Pattern Anal. Machine Intell., 29(3): 411–426, (2007).

DOI: 10.1109/tpami.2007.56

Google Scholar

[5] Dekun Hu, Simon X. Yang, Stefano Gregori, Jianping Li, Bo Fu. Image Segmentation Based on Trickle-Up and Trickle-Down Visual Pathway in Primate. Journal of Computational Information Systems, 2012, 8(9): 3757-3765.

Google Scholar

[6] Dekun Hu, Jianping Li, Simon X. Yang, Stefano Gregori. A Multiple Feature Fusion Model for Image Segmentation Based on Hierarchical visual pathway. International Journal on Advances in Information Sciences and Service Sciences, 2012, 4(8): 274-282.

DOI: 10.4156/aiss.vol4.issue8.33

Google Scholar

[7] CBCL, http: /cbcl. mit. edu/software-datasets/standard model /index. html.

Google Scholar