Structurally noise resistant classifier for multi-modal person verification

Sanderson, Conrad and Paliwal, Kuldip K. (2003) Structurally noise resistant classifier for multi-modal person verification. Pattern Recognition Letters, 24 16: 3089-3099. doi:10.1016/S0167-8655(03)00168-5


Author Sanderson, Conrad
Paliwal, Kuldip K.
Title Structurally noise resistant classifier for multi-modal person verification
Journal name Pattern Recognition Letters   Check publisher's open access policy
ISSN 0167-8655
Publication date 2003-12-01
Sub-type Article (original research)
DOI 10.1016/S0167-8655(03)00168-5
Open Access Status Not Open Access
Volume 24
Issue 16
Start page 3089
End page 3099
Total pages 11
Place of publication Amsterdam
Publisher North-Holland.
Language eng
Subject 080106 Image Processing
010401 Applied Statistics
090609 Signal Processing
080109 Pattern Recognition and Data Mining
Abstract n this letter we propose a piece-wise linear (PL) classifier for use as the decision stage in a two-modal verification system, comprised of a face and a speech expert. The classifier utilizes a fixed decision boundary that has been specifically designed to account for the effects of noisy audio conditions. Experimental results on the VidTIMIT database show that in clean conditions, the proposed classifier is outperformed by a traditional weighted summation decision stage (using both fixed and adaptive weights). Using white Gaussian noise to corrupt the audio data resulted in the PL classifier obtaining better performance than the fixed approach and similar performance to the adaptive approach. Using a more realistic noise type, namely “operations room” noise from the NOISEX-92 corpus, resulted in the PL classifier obtaining better performance than both the fixed and adaptive approaches. The better results in this case stem from the PL classifier not making a direct assumption about the type of noise that causes the mismatch between training and testing conditions (unlike the adaptive approach). Moreover, the PL classifier has the advantage of having a fixed (non-adaptive, thus simpler) structure.
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Unknown

Document type: Journal Article
Sub-type: Article (original research)
Collection: Excellence in Research Australia (ERA) - Collection
 
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: Mon, 30 Mar 2009, 23:43:47 EST by Maryanne Watson on behalf of School of Information Technol and Elec Engineering