Universidad Complutense de Madrid
E-Prints Complutense

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

Impacto

Descargas

Último año

Shin, Joo-Heon y Smith, David y Swiercz, Waldemar y Staley, Kevin y Rickard, JTerry y Montero, Javier y Kurgan, Lukasz A y Cios, Krzysztof J (2010) Recognition of partially occluded and rotated images with a network of spiking neurons. Neural Networks, IEEE Transactions on, 21 (11). pp. 1697-1709. ISSN 11636046

[img] PDF
Restringido a Sólo personal autorizado del repositorio

1MB

URL Oficial: http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5617367&abstractAccess=no&userType=inst


URLTipo de URL
http://ieeexplore.ieee.orgEditorial


Resumen

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.


Tipo de documento:Artículo
Palabras clave:Image recognition; Partially occluded and rotated images; Spiking neurons; Synaptic plasticity rule
Materias:Ciencias > Matemáticas > Investigación operativa
Código ID:28875
Depositado:02 Mar 2015 15:45
Última Modificación:21 Abr 2016 13:34

Descargas en el último año

Sólo personal del repositorio: página de control del artículo