Show simple item record

AuthorRaitoharju J.
AuthorKiranyaz S.
AuthorGabbouj M.
Available date2020-02-05T08:53:07Z
Publication Date2018
Publication NameNeural Computing and Applications
ResourceScopus
ISSN9410643
URIhttp://dx.doi.org/10.1007/s00521-016-2504-4
URIhttp://hdl.handle.net/10576/12715
AbstractMost existing content-based image retrieval and classification systems rely on low-level features which are automatically extracted from images. However, often these features lack the discrimination power needed for accurate description of the image content, and hence, they may lead to a poor retrieval or classification performance. We propose a novel technique to improve low-level features which uses parallel one-against-all perceptrons to synthesize new features with a higher discrimination power which in turn leads to improved classification and retrieval results. The proposed method can be applied on any database and low-level features as long as some ground-truth information is available. The main merits of the proposed technique are its simplicity and faster computation compared to existing feature synthesis methods. Extensive simulation results show a significant improvement in the features' discrimination power. 2016, The Natural Computing Applications Forum.
Languageen
PublisherSpringer London
SubjectContent-based image retrieval and classification
Feature synthesis
Multi-dimensional particle swarm optimization
Multi-layer perceptrons
TitleFeature synthesis for image classification and retrieval via one-against-all perceptrons
TypeArticle
Pagination943-957
Issue Number4
Volume Number29


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record