Feature-level data fusion for bimodal person recognition

Chibelushi, C.C., Mason, J.S.D. and Deravi, F. (1997) Feature-level data fusion for bimodal person recognition. In: Sixth IEE Int. Conf. on Image Processing and its Applications, 14 - 17July 1997, Dublin, Ireland.

Full text not available from this repository.

Abstract or description

Consistently high person recognition accuracy is difficult to attain using a single recognition modality. This paper assesses the fusion of voice and outer lip-margin features for person identification. Feature fusion is investigated in the form of audio-visual feature vector concatenation, principal component analysis, and linear discriminant analysis. The paper shows that, under mismatched test and training conditions, audio-visual feature fusion is equivalent to an effective increase in the signal-to-noise ratio of the audio signal. Audio-visual feature vector concatenation is shown to be an efective method for feature combination, and linear discriminant analysis is shown to possess the capability of packing discriminating audio-visual information into fewer coefficients than principal component analysis. The paper reveals a high sensitivity of bimodal person identification to a mismatch between LDA or PCA feature-fusion module and speaker model training noise-conditions. Such a mismatch leads to worse identification accuracy than unimodal identification.

Item Type:	Conference or Workshop Item (Paper)
Faculty:	Previous Faculty of Computing, Engineering and Sciences > Computing
Event Title:	Sixth IEE Int. Conf. on Image Processing and its Applications
Event Location:	Dublin, Ireland
Event Dates:	14 - 17July 1997
Depositing User:	Claude CHIBELUSHI
Date Deposited:	12 May 2013 20:36
Last Modified:	24 Feb 2023 13:38
URI:	https://eprints.staffs.ac.uk/id/eprint/1116

Actions (login required)

View Item