Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.484863
Title: Theoretical and practical study of audio-visual person identification
Author: Hu, Haoji
Awarding Body: University of Southampton
Current Institution: University of Southampton
Date of Award: 2007
Availability of Full Text:
Full text unavailable from EThOS. Please contact the current institution’s library for further details.
Abstract:
There is an increasing interest in biometric identification but, unfortunately, identification based on only one classifier is unlikely to achieve acceptable performance for practical deployment. A potential way to overcome this is to combine results from more than one classifier. This thesis is concerned with combining the audio biometric (voice) and the visual biometric (face) for person identification. To achieve this goal, a speaker identification classifier and a face identification classifier are built and tested on the XM2VTS database. In this thesis, we provide both theoretical and practical research work on combining these two classifiers for the purpose of achieving better identification results. Experiments indicate that our approach achieves very high identification rate on the XM2VTS database. The main contributions ofthis thesis lie in three parts: first, we have proposed a new algorithm to adjust weighting parameter(s) for combining independent audio and visual signals; second, we have theoretically proved that there is no 'perfect' fusion algorithm suitable for all situations (the 'no panacea' theorem); third, we have built an audio-visual person identification system and achieved good performance on the XM2VTS database. There are several directions for our future research work, which includes: (1) developing combination algorithms which are robust to noise and unpredictable situations; (2) combining visual features with the audio-visual classifier; (3) research work on face recognition; (4) generalising the method offinding optimal weighting parameter to the person verification cases; (5) theoretical study on multiple classifier combination; (6) building a real-time audio-visual person recognition system.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.484863  DOI: Not available
Share: