Efficient image classification using neural networks and multiresolution analysis

Tirakis, Andreas; Kollias, Stefanos

dc.contributor.author	Tirakis, Andreas	en
dc.contributor.author	Kollias, Stefanos	en
dc.date.accessioned	2014-03-01T02:40:58Z
dc.date.available	2014-03-01T02:40:58Z
dc.date.issued	1993	en
dc.identifier.issn	07367791	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30301
dc.subject	Image Classification	en
dc.subject	Is Success	en
dc.subject	multiresolution analysis	en
dc.subject	Feedforward Neural Network	en
dc.subject	Neural Network	en
dc.subject.other	Classification (of information)	en
dc.subject.other	Computer architecture	en
dc.subject.other	Learning systems	en
dc.subject.other	Neural networks	en
dc.subject.other	Feedforward neural networks	en
dc.subject.other	Image classification	en
dc.subject.other	Multiresolution analysis	en
dc.subject.other	Multiresolution classification	en
dc.subject.other	Image processing	en
dc.title	Efficient image classification using neural networks and multiresolution analysis	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICASSP.1993.319200	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICASSP.1993.319200	en
heal.publicationDate	1993	en
heal.abstract	In this paper, we investigate a new efficient image classification strategy. We propose a multiresolution analysis of the images to be classified and use of feedforward neural networks to classify the images at various lower resolutions. This approach results in a major reduction of the networks' interconnection weights as well as the required learning times. The proposed approach is applied first to the images of the lowest resolution; if the classification results are not acceptable, it is successively repeated to the next images of higher resolution. A neural network architecture which incorporates most of the interconnection weights already computed at the lower level (i.e., the knowledge already acquired by the network of the previous resolution level) is proposed for this purpose. Experimental results illustrate the efficiency of the proposed multiresolution classification procedure in a real life application.	en
heal.publisher	Publ by IEEE, Piscataway, NJ, United States	en
heal.journalName	Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing	en
dc.identifier.doi	10.1109/ICASSP.1993.319200	en
dc.identifier.volume	1	en
dc.identifier.spage	I	en
dc.identifier.epage	641-I-643	en