Image segmentation using pulse coupled neural networks

Panos Liatsis, Bo Li, Tomislav Kos, Ida Srdic

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This manuscript deals with the application of Seeded Region Growing (SRG) and Pulse Coupled Neural Networks (PCNN) in image segmentation. SRG selects the initial seed points for the initialisation of the algorithm. During this process, the neighbours of the seed pixels are compared to certain similarity criteria and are appropriately merged to regions. PCNN have recently become popular in image processing applications. They have a dedicated architecture consisting of feeding/linking fields and spike generator and do not require training. The performance of the two techniques will be thoroughly investigated with applications to cDNA microarray images.

Original languageBritish English
Title of host publicationIWSSIP 2005 - Proceedings of 12th International Workshop on Systems, Signals and Image Processing (SSIP-SPI, 2005)
EditorsD.A. Karras, S. Voliotis, M. Rangoussi, A. Kokkosis
Pages127-131
Number of pages5
StatePublished - 2005
EventIWSSIP 2005 - 12th International Workshop on Systems, Signals and Image Processing(SSIP-SPI, 2005) - Chalkida, Greece
Duration: 22 Sep 200524 Sep 2005

Publication series

NameIWSSIP 2005 - Proceedings of 12th International Workshop on Systems, Signals and Image Processing

Conference

ConferenceIWSSIP 2005 - 12th International Workshop on Systems, Signals and Image Processing(SSIP-SPI, 2005)
Country/TerritoryGreece
CityChalkida
Period22/09/0524/09/05

Keywords

  • Image segmentation
  • Pulse coupled neural networks
  • Seeded region growing

Fingerprint

Dive into the research topics of 'Image segmentation using pulse coupled neural networks'. Together they form a unique fingerprint.

Cite this