Computing the 2-D image euler number by an Artificial Neural Network

Humberto Sossa, Ángel Carreón, Elizabeth Guevara, Raúl Santiago

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

4 Scopus citations

Abstract

We describe for the first time how the Euler number of a 2-D binary image can be obtained by means of Artificial Neural Network (ANN). Calculating the Euler image number is treated as a pattern classification problem. To arrive at the specialized ANN architecture, we perform a partial results analysis provided by a known formulation to compute the Euler image number. We use this analysis for designing the desired ANN architecture. Due to its good functioning characteristics, outcomes with the so-called Morphological Neural Perceptron with Dendritic Processing (MNPDP) are presented. Numerical as well as experimental results with realistic images to demonstrate the operation and applicability of the proposed approach are reported. Initial results concerning the GPU implementation of the proposed ANN to show that the processing time can be effectively reduced are also provided.

Original languageEnglish
Title of host publication2016 International Joint Conference on Neural Networks, IJCNN 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1609-1616
Number of pages8
ISBN (Electronic)9781509006199
DOIs
StatePublished - 31 Oct 2016
Event2016 International Joint Conference on Neural Networks, IJCNN 2016 - Vancouver, Canada
Duration: 24 Jul 201629 Jul 2016

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2016-October

Conference

Conference2016 International Joint Conference on Neural Networks, IJCNN 2016
Country/TerritoryCanada
CityVancouver
Period24/07/1629/07/16

Keywords

  • Artificial neural networks
  • Euler number computation
  • Morphological neural networks

Fingerprint

Dive into the research topics of 'Computing the 2-D image euler number by an Artificial Neural Network'. Together they form a unique fingerprint.

Cite this