Image Classification Using Hybrid Neural Networks

Chih Fong Tsai, Ken McGarry, John Tait

Research output: Contribution to journalConference articlepeer-review

29 Scopus citations


Use of semantic content is one of the major issues which needs to be addressed for improving image retrieval effectiveness. We present a new approach to classify images based on the combination of image processing techniques and hybrid neural networks. Multiple keywords are assigned to an image to represent its main contents, i.e. semantic content. Images are divided into a number of regions and colour and texture features are extracted. The first classifier, a self-organising map (SOM) clusters similar images based on the extracted features. Then, regions of the representative images of these clusters were labeled and used to train the second classifier, composed of several support vector machines (SVMs). Initial experiments on the accuracy of keyword assignment for a small vocabulary are reported.

Original languageEnglish
Pages (from-to)431-432
Number of pages2
JournalSIGIR Forum (ACM Special Interest Group on Information Retrieval)
Issue numberSPEC. ISS.
StatePublished - 2003
EventProceedings of the Twenty-Sixth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2003 - Toronto, Ont., Canada
Duration: 28 Jul 20031 Aug 2003


  • Content-based image retrieval
  • Image indexing/classification
  • Neural networks


Dive into the research topics of 'Image Classification Using Hybrid Neural Networks'. Together they form a unique fingerprint.

Cite this