Tampere University of Technology

TUTCRIS Research Portal

Feature synthesis for image classification and retrieval via one-against-all perceptrons

Research output: Contribution to journalArticleScientificpeer-review


Original languageEnglish
Pages (from-to)943–957
Number of pages15
JournalNeural Computing and Applications
Issue number4
Early online date29 Jul 2016
Publication statusPublished - Feb 2018
Publication typeA1 Journal article-refereed


Most 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.

ASJC Scopus subject areas


  • Content-based image retrieval and classification, Feature synthesis, Multi-dimensional particle swarm optimization, Multi-layer perceptrons

Publication forum classification

Field of science, Statistics Finland