Clustering and use of spatial and frequency information in a biologically inspired approach to image classification

Please use this identifier to cite or link to this item: https://doi.org/10.1109/IJCNN.2012.6252424

Title:	Clustering and use of spatial and frequency information in a biologically inspired approach to image classification
Authors:	Jalali, S. Lim, J.-H. Tham, J.Y. Ong, S.H.
Issue Date:	2012
Citation:	Jalali, S.,Lim, J.-H.,Tham, J.Y.,Ong, S.H. (2012). Clustering and use of spatial and frequency information in a biologically inspired approach to image classification. Proceedings of the International Joint Conference on Neural Networks : -. ScholarBank@NUS Repository. https://doi.org/10.1109/IJCNN.2012.6252424
Abstract:	In this paper, we explore the use of spatial and frequency information of features in the biologically inspired model of HMAX. We discuss and refine previous models which use a similar framework and build specialized features which are better tuned to image structures by using unsupervised methods of clustering and picking the most frequent features using the statistics of the occurrence of the features in different spatial zones. Our classification results on the Caltech 101 dataset show significant improvements of up to 6% compared to previous improvements of the biologically inspired model of HMAX. © 2012 IEEE.
Source Title:	Proceedings of the International Joint Conference on Neural Networks
URI:	http://scholarbank.nus.edu.sg/handle/10635/69616
ISBN:	9781467314909
DOI:	10.1109/IJCNN.2012.6252424
Appears in Collections:	Staff Publications

There are no files associated with this item.

Check