Recognition of Partially Occluded and Rotated Images With a Network of Spiking Neurons

ArticleinIEEE Transactions on Neural Networks 21(11):1697-709 · November 2010with12 Reads
DOI: 10.1109/TNN.2010.2050600 · Source: PubMed
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.
    • "This evaluation of residual action potential to differentiate the spike trains has been effectively used previously [33]. There is also previous work in [34] that suggested the information was carried by either the firing rate or the firing time of the individual spike response. "
    [Show abstract] [Hide abstract] ABSTRACT: Gabor Wavelets (GW) have been extensively used for facial feature representation due to its inherent multi-resolution and multi-orientation characteristics. In this work we extend the work on Local Gabor Feature Vector (LGFV) and propose a new face recognition method called LGFV//LN//SNP, which employs local normalization filter in pre-processing stage. We propose a novel Spiking Neuron Patterns (SNP) as a dimensionality reduction method to reduce the dimensions of local Gabor features. SNP is acquired from projection of LGFV//LN features using Spike Response Model (SRM), a neuron model describing the spike behavior of a biological neuron. Results on AR, FERET, Yale B and FRGC 2.0 face datasets showed that SNP implementation delivered significant improvement in accuracy. Comparisons with several previously published results also suggested that LGFV//LN//SNP achieved better results in some tests. Additionally, LGFV//LN//SNP requires relatively smaller number of GW than LGFV//LN to produce optimal results.
    Full-text · Article · May 2016
    • "The architecture of their network consists of three layers including the input layer that comprises excitatory neurons, the extraction layer that comprises both excitatory and inhibitory neurons, and finally the matching layer that comprises excitatory neurons. In their experiments, Shin et al. [2010] demonstrated that raising the number of neurons in the recognition layer to a particular level will notably improve the recognition rate [Shin et al. 2010]. "
    [Show abstract] [Hide abstract] ABSTRACT: An increased number of bio-inspired face recognition systems have emerged in recent decades owing to their intelligent problem-solving ability, flexibility, scalability, and adaptive nature. Hence, this survey aims to present a detailed overview of bio-inspired approaches pertaining to the advancement of face recognition. Based on a well-classified taxonomy, relevant bio-inspired techniques and their merits and demerits in countering potential problems vital to face recognition are analyzed. A synthesis of various approaches in terms of key governing principles and their associated performance analysis are systematically portrayed. Finally, some intuitive future directions are suggested on how bio-inspired approaches can contribute to the advancement of face biometrics in the years to come.. 2015. The impact of bio-inspired approaches towards the advancement of face recognition.
    Article · Sep 2015
    • "Many spiking models are now proposed to achieve different vision tasks. For instance, a vision system achieving image recognition using spiking neurons [55] has been shown to be robust to rotation and occlusion. "
    Full-text · Chapter · Sep 2012 · ACM Computing Surveys
Show more