Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/87999
Title: | Feature fusion with covariance matrix regularization in face recognition | Authors: | Lu, Ze Jiang, Xudong Kot, Alex Chichung |
Keywords: | Feature Fusion CNN |
Issue Date: | 2017 | Source: | Lu, Z., Jiang, X., & Kot, A. (2018). Feature fusion with covariance matrix regularization in face recognition. Signal Processing, 144, 296-305. | Series/Report no.: | Signal Processing | Abstract: | The fusion of multiple features is important for achieving state-of-the-art face recognition results. This has been proven in both traditional and deep learning approaches. Existing feature fusion methods either reduce the dimensionality of each feature first and then concatenate all low-dimensional feature vectors, named as DR-Cat, or the vice versa, named as Cat-DR. However, DR-Cat ignores the correlation information between different features which is useful for classification. In Cat-DR, on the other hand, the correlation information estimated from the training data may not be reliable especially when the number of training samples is limited. We propose a covariance matrix regularization (CMR) technique to solve problems of DR-Cat and Cat-DR. It works by assigning weights to cross-feature covariances in the covariance matrix of training data. Thus the feature correlation estimated from training data is regularized before being used to train the feature fusion model. The proposed CMR is applied to 4 feature fusion schemes: fusion of pixel values from 3 color channels, fusion of LBP features from 3 color channels, fusion of pixel values and LBP features from a single color channel, and fusion of CNN features extracted by 2 deep models. Extensive experiments of face recognition and verification are conducted on databases including MultiPIE, Georgia Tech, AR and LFW. Results show that the proposed CMR technique significantly and consistently outperforms the best single feature, DR-Cat and Cat-DR. | URI: | https://hdl.handle.net/10356/87999 http://hdl.handle.net/10220/44512 |
ISSN: | 0165-1684 | DOI: | 10.1016/j.sigpro.2017.10.024 | Schools: | School of Electrical and Electronic Engineering | Research Centres: | Rapid-Rich Object Search Lab | Rights: | © 2017 Elsevier B.V. This is the author created version of a work that has been peer reviewed and accepted for publication by Signal Processing, Elsevier B.V. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at:[http://dx.doi.org/10.1016/j.sigpro.2017.10.024]. | Fulltext Permission: | open | Fulltext Availability: | With Fulltext |
Appears in Collections: | EEE Journal Articles |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Feature Fusion with Covariance Matrix Regularization in.pdf | 1.23 MB | Adobe PDF | View/Open |
SCOPUSTM
Citations
20
23
Updated on Mar 22, 2024
Web of ScienceTM
Citations
20
20
Updated on Oct 25, 2023
Page view(s) 50
450
Updated on Mar 27, 2024
Download(s) 10
336
Updated on Mar 27, 2024
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.