Person Verification by Lip-Motion

Faraj, Maycel Isaac; Bigün, Josef

doi:10.1109/cvprw.2006.158

Cited by 17 publications

(30 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dealing with digit recognition only, parts of this work are reported [6] which is related to [7] [8]. The later is concerned with person authentication.…”

Section: Introductionmentioning

confidence: 99%

“…The reports [9][10] [11][12] [13] suggest visual features based on the shape and intensity of the lip region due to the changes in the mouth shape including the lips and tongue. The dynamic visual lip features carry significant phoneme-discrimination information embedded in motion information which can be modelled by moving-line patterns also known as normal image velocity [7][14], with no requirement of iterative process on detecting the mouth contour.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Lip Biometrics for Digit Recognition

Faraj

Bigün

2007

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

Abstract. This paper presents a speaker-independent audio-visual digit recognition system that utilizes speech and visual lip signals. The extracted visual features are based on line-motion estimation obtained from video sequences with low resolution (128 ×128 pixels) to increase the robustness of audio recognition. The core experiments investigate lip motion biometrics as stand-alone as well as merged modality in speech recognition system. It uses Support Vector Machines, showing favourable experimental results with digit recognition featuring 83% to 100% on the XM2VTS database depending on the amount of available visual information.

show abstract

“…Dealing with digit recognition only, parts of this work are reported [6] which is related to [7] [8]. The later is concerned with person authentication.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Lip Biometrics for Digit Recognition

Faraj

Bigün

2007

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

show abstract

“…Each person is described with Gaussian model parameters that are learned from a training set, that are the mean and variances of a number of Gaussian distributions, as well as their associated weights which are used to linearly combine the individual Normal components to finally yield a multidimensional distribution for the features. More details about the set-up can be found in [10].…”

Section: Gaussian Mixture Modelmentioning

confidence: 99%

“…The sampled waveform is converted into a sequence of acoustic parameter blocks, where the output sampling period is set to 10 ms and the window size is set to 25 ms, [10]. From each block we extract a 39 dimensional feature vector, consisting of 12 cepstral coefficients with normalized log-energy, 13 delta coefficients and delta-delta coefficients.…”

Section: Speech Featuresmentioning

confidence: 99%

“…Liveness detection is an anti-spoofing mechanism to protect biometric systems [5], [6], [7]. It is performed by, for example, face part detection and optical flow of lines to determine liveness score [8], analysis of fourier spectra of the face image [9], lip-motion to speech synchronization [10], body temperature, on the spot random queries such as pronouncing of random sequences of digits, iris size scanning under varying illumination etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Text Driven Face-Video Synthesis Using GMM and Spatial Correlation

View full text Add to dashboard Cite

Abstract. Liveness detection is increasingly planned to be incorporated into biometric systems to reduce the risk of spoofing and impersonation. Some of the techniques used include detection of motion of the head while posing/speaking, iris size in varying illumination, fingerprint sweat, textprompted speech, speech-to-lip motion synchronization etc. In this paper, we propose to build a biometric signal to test attack resilience of biometric systems by creating a text-driven video synthesis of faces. We synthesize new realistic looking video sequences from real image sequences representing utterance of digits. We determine the image sequences for each digit by using a GMM based speech recognizer. Then, depending on system prompt (sequence of digits) our method regenerates a video signal to test attack resilience of a biometric system that asks for random digit utterances to prevent play-back of pre-recorded data representing both audio and images. The discontinuities in the new image sequence, created at the connection of each digit, are removed by using a frame prediction algorithm that makes use of the well known block matching algorithm. Other uses of our results include web-based video communication for electronic commerce and frame interpolation for low frame rate video.

show abstract

Speaker and Digit Recognition by Audio-Visual Lip Biometrics

Faraj

Bigün

2007

Advances in Biometrics

View full text Add to dashboard Cite

Abstract. This paper proposes a new robust bi-modal audio visual digit and speaker recognition system by lip-motion and speech biometrics. To increase the robustness of digit and speaker recognition, we have proposed a method using speaker lip motion information extracted from video sequences with low resolution (128 ×128 pixels). In this paper we investigate a biometric system for digit recognition and speaker identification based using line-motion estimation with speech information and Support Vector Machines. The acoustic and visual features are fused at the feature level showing favourable results with digit recognition being 83% to 100% and speaker recognition 100% on the XM2VTS database.

show abstract

Person Verification by Lip-Motion

Abstract: This paper describes a new motion based feature extrac-

Cited by 17 publications

References 22 publications

Lip Biometrics for Digit Recognition

Lip Biometrics for Digit Recognition

Text Driven Face-Video Synthesis Using GMM and Spatial Correlation

Speaker and Digit Recognition by Audio-Visual Lip Biometrics

Contact Info

Product

Resources

About