Home > Research > Publications & Outputs > Multimodal Biometric Human Recognition for Perc...

Links

Text available via DOI:

View graph of relations

Multimodal Biometric Human Recognition for Perceptual Human-Computer Interaction

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Multimodal Biometric Human Recognition for Perceptual Human-Computer Interaction. / Jiang, Richard M.; Sadka, Abdul H.; Crookes, Danny.
In: IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, Vol. 40, No. 6, 11.2010, p. 676-681.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Jiang, RM, Sadka, AH & Crookes, D 2010, 'Multimodal Biometric Human Recognition for Perceptual Human-Computer Interaction', IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol. 40, no. 6, pp. 676-681. https://doi.org/10.1109/TSMCC.2010.2050476

APA

Jiang, R. M., Sadka, A. H., & Crookes, D. (2010). Multimodal Biometric Human Recognition for Perceptual Human-Computer Interaction. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 40(6), 676-681. https://doi.org/10.1109/TSMCC.2010.2050476

Vancouver

Jiang RM, Sadka AH, Crookes D. Multimodal Biometric Human Recognition for Perceptual Human-Computer Interaction. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews. 2010 Nov;40(6):676-681. doi: 10.1109/TSMCC.2010.2050476

Author

Jiang, Richard M. ; Sadka, Abdul H. ; Crookes, Danny. / Multimodal Biometric Human Recognition for Perceptual Human-Computer Interaction. In: IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews. 2010 ; Vol. 40, No. 6. pp. 676-681.

Bibtex

@article{7f0bde0bfe8f480981aab5c63c58687b,
title = "Multimodal Biometric Human Recognition for Perceptual Human-Computer Interaction",
abstract = "In this paper, a novel video-based multimodal biometric verification scheme using the subspace-based low-level feature fusion of face and speech is developed for specific speaker recognition for perceptual human-computer interaction (HCI). In the proposed scheme, human face is tracked and face pose is estimated to weight the detected facelike regions in successive frames, where ill-posed faces and false-positive detections are assigned with lower credit to enhance the accuracy. In the audio modality, mel-frequency cepstral coefficients are extracted for voice-based biometric verification. In the fusion step, features from both modalities are projected into nonlinear Laplacian Eigenmap subspace for multimodal speaker recognition and combined at low level. The proposed approach is tested on the video database of ten human subjects, and the results show that the proposed scheme can attain better accuracy in comparison with the conventional multimodal fusion using latent semantic analysis as well as the single-modality verifications. The experiment on MATLAB shows the potential of the proposed scheme to attain the real-time performance for perceptual HCI applications.",
keywords = "Laplacian Eigenmap, low-level feature fusion, multimodal biometrics, perceptual human-computer interaction (HCI), speaker recognition",
author = "Jiang, {Richard M.} and Sadka, {Abdul H.} and Danny Crookes",
year = "2010",
month = nov,
doi = "10.1109/TSMCC.2010.2050476",
language = "English",
volume = "40",
pages = "676--681",
journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews",
issn = "1094-6977",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

RIS

TY - JOUR

T1 - Multimodal Biometric Human Recognition for Perceptual Human-Computer Interaction

AU - Jiang, Richard M.

AU - Sadka, Abdul H.

AU - Crookes, Danny

PY - 2010/11

Y1 - 2010/11

N2 - In this paper, a novel video-based multimodal biometric verification scheme using the subspace-based low-level feature fusion of face and speech is developed for specific speaker recognition for perceptual human-computer interaction (HCI). In the proposed scheme, human face is tracked and face pose is estimated to weight the detected facelike regions in successive frames, where ill-posed faces and false-positive detections are assigned with lower credit to enhance the accuracy. In the audio modality, mel-frequency cepstral coefficients are extracted for voice-based biometric verification. In the fusion step, features from both modalities are projected into nonlinear Laplacian Eigenmap subspace for multimodal speaker recognition and combined at low level. The proposed approach is tested on the video database of ten human subjects, and the results show that the proposed scheme can attain better accuracy in comparison with the conventional multimodal fusion using latent semantic analysis as well as the single-modality verifications. The experiment on MATLAB shows the potential of the proposed scheme to attain the real-time performance for perceptual HCI applications.

AB - In this paper, a novel video-based multimodal biometric verification scheme using the subspace-based low-level feature fusion of face and speech is developed for specific speaker recognition for perceptual human-computer interaction (HCI). In the proposed scheme, human face is tracked and face pose is estimated to weight the detected facelike regions in successive frames, where ill-posed faces and false-positive detections are assigned with lower credit to enhance the accuracy. In the audio modality, mel-frequency cepstral coefficients are extracted for voice-based biometric verification. In the fusion step, features from both modalities are projected into nonlinear Laplacian Eigenmap subspace for multimodal speaker recognition and combined at low level. The proposed approach is tested on the video database of ten human subjects, and the results show that the proposed scheme can attain better accuracy in comparison with the conventional multimodal fusion using latent semantic analysis as well as the single-modality verifications. The experiment on MATLAB shows the potential of the proposed scheme to attain the real-time performance for perceptual HCI applications.

KW - Laplacian Eigenmap

KW - low-level feature fusion

KW - multimodal biometrics

KW - perceptual human-computer interaction (HCI)

KW - speaker recognition

U2 - 10.1109/TSMCC.2010.2050476

DO - 10.1109/TSMCC.2010.2050476

M3 - Journal article

VL - 40

SP - 676

EP - 681

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

SN - 1094-6977

IS - 6

ER -