• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Bio-Inspired Object Recognition Using Parameterized Metric Learning

Vol. 7, No. 4, April 29, 2013
10.3837/tiis.2013.04.012, Download Paper (Free):

Abstract

Computing global features based on local features using a bio-inspired framework has shown promising performance. However, for some tough applications with large intra-class variances, a single local feature is inadequate to represent all the attributes of the images. To integrate the complementary abilities of multiple local features, in this paper we have extended the efficacy of the bio-inspired framework, HMAX, to adapt heterogeneous features for global feature extraction. Given multiple global features, we propose an approach, designated as parameterized metric learning, for high dimensional feature fusion. The fusion parameters are solved by maximizing the canonical correlation with respect to the parameters. Experimental results show that our method achieves significant improvements over the benchmark bio-inspired framework, HMAX, and other related methods on the Caltech dataset, under varying numbers of training samples and feature elements.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
X. Li, B. Wang and Y. Liu, "Bio-Inspired Object Recognition Using Parameterized Metric Learning," KSII Transactions on Internet and Information Systems, vol. 7, no. 4, pp. 819-833, 2013. DOI: 10.3837/tiis.2013.04.012.

[ACM Style]
Xiong Li, Bin Wang, and Yuncai Liu. 2013. Bio-Inspired Object Recognition Using Parameterized Metric Learning. KSII Transactions on Internet and Information Systems, 7, 4, (2013), 819-833. DOI: 10.3837/tiis.2013.04.012.