Recognition of partially occluded and rotated images with a network of spiking neurons

Joo Heon Shin, David Smith, Waldemar Swiercz, Kevin Staley, J. Terry Rickard, Javier Montero, Lukasz A. Kurgan, Krzysztof J. Cios

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we introduce a novel system for recognition of partially occluded and rotated images. The system is based on a hierarchical network of integrate-and-fire spiking neurons with random synaptic connections and a novel organization process. The network generates integrated output sequences that are used for image classification. The proposed network is shown to provide satisfactory predictive performance given that the number of the recognition neurons and synaptic connections are adjusted to the size of the input image. Comparison of synaptic plasticity activity rule (SAPR) and spike timing dependant plasticity rules, which are used to learn connections between the spiking neurons, indicates that the former gives better results and thus the SAPR rule is used. Test results show that the proposed network performs better than a recognition system based on support vector machines.

Original languageEnglish (US)
Article number5617367
Pages (from-to)1697-1709
Number of pages13
JournalIEEE Transactions on Neural Networks
Volume21
Issue number11
DOIs
StatePublished - Nov 2010
Externally publishedYes

Keywords

  • Image recognition
  • partially occluded and rotated images
  • spiking neurons
  • synaptic plasticity rule

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Recognition of partially occluded and rotated images with a network of spiking neurons'. Together they form a unique fingerprint.

Cite this