Face identification with second-order pooling in single-layer networks

Shen, Fumin, Yang, Yang, Zhou, Xiang, Liu, Xianglong and Shao, Jie (2016) Face identification with second-order pooling in single-layer networks. Neurocomputing, 187 11-18. doi:10.1016/j.neucom.2015.07.133

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Shen, Fumin
Yang, Yang
Zhou, Xiang
Liu, Xianglong
Shao, Jie
Title Face identification with second-order pooling in single-layer networks
Journal name Neurocomputing   Check publisher's open access policy
ISSN 1872-8286
0925-2312
Publication date 2016-04-26
Year available 2015
Sub-type Article (original research)
DOI 10.1016/j.neucom.2015.07.133
Open Access Status File (Author Post-print)
Volume 187
Start page 11
End page 18
Total pages 8
Place of publication Amsterdam, Netherlands
Publisher Elsevier
Collection year 2016
Subject 1702 Cognitive Sciences
1706 Computer Science Applications
2805 Cognitive Neuroscience
Abstract Automatic face recognition has received significant performance improvement by developing specialized facial image representations. On the other hand, spatial pyramid pooling of features encoded by an over-complete dictionary has been the key component of many state-of-the-art generic objective classification systems. Inspired by its success, in this work we develop a new face image representation method under the framework of single-layer networks, where the key component is the second-order pooling layer. The proposed method differs from the previous methods in that, we encode the densely extracted local patches by a small-size dictionary; and the facial image signatures are obtained by pooling the second-order statistics of the encoded features. We show the importance of the encoding procedure, which is bypassed by the original second-order pooling method to avoid the high computational cost. Equipped with a simple linear classifier, the proposed method outperforms the state-of-the-art face identification performance by large margins. For example, on the LFW databases, the proposed method performs better than the previous best by around 13% accuracy.
Keyword Face recognition
Image classification
Second-order pooling
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Non-UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: Non HERDC
School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Wed, 11 May 2016, 14:30:10 EST by Anthony Yeates on behalf of Learning and Research Services (UQ Library)