ICA-Based Lip Feature Representation for Speaker Authentication

Wang, S.L.; Liew, Alan Wee‐Chung

doi:10.1109/sitis.2007.37

Cited by 8 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kaynak et al [9] have conducted a comprehensive investigation about such features for lip motion analysis. For the appearance-based features, as the teeth and tongue are always appearing during the speaking process, the transforming coefficients such as Principal Component Analysis (PCA), Independent Components Analysis (ICA) and two dimensional Discrete Cosine Transform (2D-DCT) have shown their effectiveness [14], [30], [31]. Differing from the above-mentioned features that are extracted from a single frame level, the motion based features are able to reveal the temporal characteristics of lip movements [7], [13].…”

Section: A Visual Feature Extractionmentioning

confidence: 99%

Learning Multi-Boosted HMMs for Lip-Password Based Speaker Verification

Liu

Cheung

2014

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Abstract-This paper proposes a concept of lip motion password (simply called lip-password hereinafter), which is composed of a password embedded in the lip movement and the underlying characteristic of lip motion. It provides a double security to a visual speaker verification system, where the speaker is verified by both of the private password information and the underlying behavioral biometrics of lip motions simultaneously. Accordingly, the target speaker saying the wrong password or an impostor who knows the correct password will be detected and rejected. To this end, we shall present a multi-boosted Hidden Markov model (HMM) learning approach to such a system. Initially, we extract a group of representative visual features to characterize each lip frame. Then, an effective lip motion segmentation algorithm is addressed to segment the lip-password sequence into a small set of distinguishable subunits. Subsequently, we integrate HMMs with boosting learning framework associated with a random subspace method and data sharing scheme to formulate a precise decision boundary for these subunits verification, featuring on high discrimination power. Finally, the lip-password, whether spoken by the target speaker with the pre-registered password or not, is identified based on all the subunit verification results learned from multi-boosted HMMs. The experimental results show that the proposed approach performs favorably compared with the state-of-the-art methods.Index Terms-Lip-password, lip motion segmentation, multi-boosted HMMs, random subspace method, data sharing scheme.

show abstract

Section: A Visual Feature Extractionmentioning

confidence: 99%

Learning Multi-Boosted HMMs for Lip-Password Based Speaker Verification

Liu

Cheung

2014

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…In the past several years, biometric features, such as fingerprint, iris and human face, have been widely used for human identity identification and authentication. Recent study [1][2][3][4][5][6][7][8][9] have shown that visual information about the lip region and its movement contain abundant speaker identity related information and can be regarded as a new biometric feature in many multi-modal person verification systems.…”

Section: Introductionmentioning

confidence: 99%

“…Many researches have proposed various lip feature representations for speaker authentication and identification [3][4][5][6][7]. For the physiological part, Luettin et al [3] employ the Active Shape Model (ASM) to describe the outer lip contour and both the lip shape and intensity profile along the contour points have been adopted to describe the static human lip.…”

Section: Introductionmentioning

confidence: 99%

“…Matthews et al [5] have proposed the Active Appearance Model for lip modeling and both the lip shape and the intensity variation inside the outer lip contour (referred to as the lip texture) have been adopted to represent the lip region. In our previous work [6], we have demonstrated that the ICA-based presentation of the lip features (both shape and texture) can be a better choice compared with the traditional PCA-based representations in [5]. Recently, Goswami et al proposed a new local texture descriptor (LOCP) to describe the lip texture and achieved a satisfactory performance for speaker identification [7].…”

Section: Introductionmentioning

confidence: 99%

“…Recently, Goswami et al proposed a new local texture descriptor (LOCP) to describe the lip texture and achieved a satisfactory performance for speaker identification [7]. For the behavioral part, the first order derivatives of the static features have been widely used to infer the dynamic information [3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sparse coding based lip texture representation for visual speaker identification

Lai

Wang

Shi

et al. 2014

2014 19th International Conference on Digital Signal Processing

View full text Add to dashboard Cite

Recent research has shown that the speaker's lip shape and movement contain rich identity-related information and can be adopted for speaker identification and authentication. Among all the static lip features, the lip texture (intensity variation inside the outer lip contour) is of high discriminative power to differentiate various speakers. However, the existing lip texture feature representations cannot describe the texture information adequately and provide unsatisfactory identification results. In this paper, a sparse representation of the lip texture is proposed and a corresponding visual speaker identification scheme is presented. In the training stage, a sparse dictionary is built based on the texture samples for each speaker. In the testing stage, for any lip image investigated, the lip texture information is extracted and the reconstruction errors using all the dictionaries for every speaker are calculated. The lip image is identified to the speaker with the minimum reconstruction error. The experimental results show that the proposed sparse coding based scheme can achieve much better identification accuracy (91.37% for isolate image and 98.21% for image sequence) compared with several state-of-the-art methods when considering the lip texture information only.

show abstract