DMCA
A unified SWSI-KAMs framework and performance evaluation on face recognition
| Venue: | Neurocomputing |
| Citations: | 1 - 0 self |
BibTeX
@ARTICLE{Chen_aunified,
author = {Songcan Chen and Lei Chen Zhi-hua Zhou},
title = {A unified SWSI-KAMs framework and performance evaluation on face recognition},
journal = {Neurocomputing},
year = {},
volume = {2005}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract: Kernel method is an effective and popular trick in machine learning. In this paper, by introducing it into conventional auto-associative memory models (AMs), we construct a unified framework of kernel auto-associative memory models (KAMs),which makes the existing exponential and polynomial AMs become its special cases. Further, in order to reduce KAM’s connect complexity, inspired by “small-world network ” recently described by Watts and Strogatz, we propose another unified framework of small-world structure (SWS) inspired kernel auto-associative memory models (SWSI-KAMs), which, in principle, makes KAMs implemented easier in structure. Simulation results on FERET face database show that, the SWSI-KAMs adopting such kernels as Exponential and Hyperbolic tangent kernels have advantages of configuration simplicity while their recognition performance is almost as well as, even better than, corresponding KAMs with full connectivity. In the end, the SWSI-KAM adopting Exponential kernel with different connectivities was emphatically investigated for robustness based on those face images which are added random noises and/or partially occluded in a mosaic way, and the experiments demonstrate that the SWSI-KAM with Exponential kernel is more robust in all cases of network connectivity of 20%, 40 % and 60 % than
Keyphrases
unified swsi-kams framework performance evaluation face recognition kernel auto-associative memory model exponential kernel unified framework conventional auto-associative memory model popular trick recognition performance kernel method feret face database show special case configuration simplicity network connectivity hyperbolic tangent kernel face image different connectivity added random noise polynomial am swsi-kams adopting kernel full connectivity machine learning mosaic way kam connect complexity simulation result small-world network small-world structure
