Observatorio de I+D+i UPM

Memorias de investigación
Communications at congresses:
Feature extraction using coordinate logic filters and Artificial Neural Networks
Year:2009
Research Areas
  • Processing and signal analysis
Information
Abstract
Abstract: This paper presents a novel feature extraction method using the combination of the Coordinate Logic Filters (CLF) and Artificial Neural Networks (ANN) applied to 2D signals (Images). The method consists of image enhancement by histogram adaptive equalization technique, features extraction by modifying gray levels applying a nonlinear adaptive transformation function and edge detection by Coordinate Logic Filters (CLF), generation, clustering and labelling of suboptimal features vectors by Self Organizing Map (SOM) Neural Network. For the detection we applied Back Propagation Neural Network (BPNN). This method is tested to detect Microcalcifications (MCs) in Regions of Interest (ROI) from mammograms. The experiment results show that the proposed method can locate MCs in an efficient way, moreover the method promise interesting advances in Medical Industry.
International
Si
Congress
Industrial Informatics, 2009. INDIN 2009. 7th IEEE International Conference on
960
Place
Cardiff, UK
Reviewers
Si
ISBN/ISSN
1935-4576
10.1109/INDIN.2009.5195878
Start Date
23/06/2009
End Date
26/06/2009
From page
644
To page
649
Porc. of Industrial Informatics, 2009. INDIN 2009. 7th IEEE International Conference on
Participants
  • Autor: Moisés González-Romo (UG)
  • Autor: Diego Andina De la Fuente (UPM)
  • Autor: Antonio Vega-Corona (UG)
  • Autor: Joel Quintanilla Dominguez (UPM)
Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Grupo de Automatización en Señal y Comunicaciones (GASC)
  • Departamento: Señales, Sistemas y Radiocomunicaciones
S2i 2019 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)