Please use this identifier to cite or link to this item:
Title: Face recognition by applying wavelet subband representation and kernel associative memory
Authors: Zhang, B.-L.
Zhang, H.
Ge, S.S. 
Keywords: Associative memory
Face recognition
Kernel methods
Wavelet transform
Issue Date: Jan-2004
Citation: Zhang, B.-L., Zhang, H., Ge, S.S. (2004-01). Face recognition by applying wavelet subband representation and kernel associative memory. IEEE Transactions on Neural Networks 15 (1) : 166-177. ScholarBank@NUS Repository.
Abstract: In this paper, we propose an efficient face recognition scheme which has two features: 1) representation of face images by two-dimensional (2-D) wavelet subband coefficients and 2) recognition by a modular, personalised classification method based on kernel associative memory models. Compared to PCA projections and low resolution "thumb-nail" image representations, wavelet subband coefficients can efficiently capture substantial facial features while keeping computational complexity low. As there are usually very limited samples, we constructed an associative memory (AM) model for each person and proposed to improve the performance of AM models by kernel methods. Specifically, we first applied kernel transforms to each possible training pair of faces sample and then mapped the high-dimensional feature space back to input space. Our scheme using modular autoassociative memory for face recognition is inspired by the same motivation as using autoencoders for optical character recognition (OCR), for which the advantages has been proven. By associative memory, all the prototypical faces of one particular person are used to reconstruct themselves and the reconstruction error for a probe face image is used to decide if the probe face is from the corresponding person. We carried out extensive experiments on three standard face recognition datasets, the FERET data, the XM2VTS data, and the ORL data. Detailed comparisons with earlier published results are provided and our proposed scheme offers better recognition accuracy on all of the face datasets.
Source Title: IEEE Transactions on Neural Networks
ISSN: 10459227
DOI: 10.1109/TNN.2003.820673
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Oct 20, 2018


checked on Oct 3, 2018

Page view(s)

checked on Sep 29, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.