Universidad Complutense de Madrid
E-Prints Complutense

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



Downloads per month over past year

Shin, Joo-Heon and Smith, David and Swiercz, Waldemar and Staley, Kevin and Rickard, JTerry and Montero, Javier and Kurgan, Lukasz A and 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

[thumbnail of Montero143.pdf] PDF
Restringido a Repository staff only


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


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.

Item Type:Article
Uncontrolled Keywords:Image recognition; Partially occluded and rotated images; Spiking neurons; Synaptic plasticity rule
Subjects:Sciences > Mathematics > Operations research
ID Code:28875
Deposited On:02 Mar 2015 15:45
Last Modified:21 Apr 2016 13:34

Origin of downloads

Repository Staff Only: item control page