Lip Image Segmentation Using Fuzzy Clustering Incorporating an Elliptic Shape Function

Leung, S.H.; Wang, Shilin; Lau, Wing Cheong

doi:10.1109/tip.2003.818116

Cited by 108 publications

(47 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another fuzzy clustering based lip segmentation method proposed in [30] obtains the spatial continuity constraints by using a dissimilarity index that allows spatial interactions between image voxels. Similarly, Leung et al [31] and Wang et al [12] deal with lip segmentation using fuzzy clustering with spatial restriction. Although these methods give promising results, their accuracy highly depends on the pre-defined number of segments, whose selection is often a nontrivial task in practice.…”

Section: A Review Of Related Workmentioning

confidence: 99%

Lip Segmentation under MAP-MRF Framework with Automatic Selection of Local Observation Scale and Number of Segments

Cheung

Cao

et al. 2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-This paper addresses the problem of segmenting lip region from frontal human face image. Supposing each pixel of the target image has an optimal local scale from the segmentation viewpoint, we treat the lip segmentation problem as a combination of observation scale selection and observed data classification. Accordingly, we propose a hierarchical multiscale Markov random field (MRF) model to represent the membership map of each input pixel to a specific segment and localscale map simultaneously. Subsequently, lip segmentation can be formulated as an optimal problem in the maximum a posteriori (MAP)-MRF framework. Then, we present a rival-penalized iterative algorithm to implement the segmentation, which is independent of the number of predefined segments. The proposed method mainly features two aspects: 1) its performance is independent of the predefined number of segments, and 2) it takes into account the local optimal observation scale for each pixel. Finally, we conduct the experiments on four benchmark databases, i.e. AR, CVL, GTAV, and VidTIMIT. Experimental results show that the proposed method is robust to the segment number that changes with a speaker's appearance, and can enhance the segmentation accuracy by taking advantage of the local optimal observation scale information.Index Terms-Lip segmentation, MAP-MRF framework, number of segments, local scale selection.

show abstract

Section: A Review Of Related Workmentioning

confidence: 99%

Lip Segmentation under MAP-MRF Framework with Automatic Selection of Local Observation Scale and Number of Segments

Cheung

Cao

et al. 2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…information is often used as an important cue to differentiate lip pixels from those of the skin. In order to achieve this, the state-of-the-art techniques use, for instance, Markov random fields [34], LDA [35], adaptive Gaussian mixture models [29] or fuzzy clustering methods as in [30], [32]. There are also a number of boundary-based techniques to represent and to extract the lip contour, such as splines, active shape models, snakes, and parametric models, that use color gradient and/or edge information.…”

Section: Extraction Of Contour-based Motion Features 1) Lip Contoumentioning

confidence: 99%

Discriminative Analysis of Lip Motion Features for Speaker Identification and Speech-Reading

Çetingül

Yemez

Erzin³

et al. 2006

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-There have been several studies that jointly use audio, lip intensity, and lip geometry information for speaker identification and speech-reading applications. This paper proposes using explicit lip motion information, instead of or in addition to lip intensity and/or geometry information, for speaker identification and speech-reading within a unified feature selection and discrimination analysis framework, and addresses two important issues: 1) Is using explicit lip motion information useful, and, 2) if so, what are the best lip motion features for these two applications? The best lip motion features for speaker identification are considered to be those that result in the highest discrimination of individual speakers in a population, whereas for speech-reading, the best features are those providing the highest phoneme/word/phrase recognition rate. Several lip motion feature candidates have been considered including dense motion features within a bounding box about the lip, lip contour motion features, and combination of these with lip shape features. Furthermore, a novel two-stage, spatial, and temporal discrimination analysis is introduced to select the best lip motion features for speaker identification and speech-reading applications. Experimental results using an hidden-Markov-modelbased recognition system indicate that using explicit lip motion information provides additional performance gains in both applications, and lip motion features prove more valuable in the case of speech-reading application.Index Terms-Bayesian discriminative feature selection, lip motion, speaker identification, speech recognition, temporal discriminative feature selection.

show abstract

“…A fascinating technique, proposed by [Leung et al (2004)], joins both shading uniqueness amongst lip and skin and a spatial separation from an oval approximating lip shape with a specific end goal to encourage lip division. The primary gathering uses gadgets mounted straightforwardly on the client's body.…”

Section: Introductionmentioning

confidence: 99%

Neural Network through Face Recognition

Gupta¹,

S.Gupta²

2018

IJSRCSE

View full text Add to dashboard Cite

Abstract:The aim is to utilise image processing to figure out lip movements and provide lice interaction with the system based on it. The multimodal HCI is displayed which enables a client to take a shot at a PC utilizing developments and motions made with the specific user's mouth. Calculations for lip development and lip signal acknowledgement are introduced in points of interest. Client confront pictures are caught with a standard webcam. Face identification depends on a course of helped classifiers. Mouth position is utilized to track lip developments that enables a client to control a screen cursor. Three lip signals which are mouth opening, standing out tongue, and framing puckered lips respectively are perceived. An acknowledgment of lip is performed by simulated neural system.

show abstract

Lip Image Segmentation Using Fuzzy Clustering Incorporating an Elliptic Shape Function

Cited by 108 publications

References 23 publications

Lip Segmentation under MAP-MRF Framework with Automatic Selection of Local Observation Scale and Number of Segments

Lip Segmentation under MAP-MRF Framework with Automatic Selection of Local Observation Scale and Number of Segments

Discriminative Analysis of Lip Motion Features for Speaker Identification and Speech-Reading

Neural Network through Face Recognition

Contact Info

Product

Resources

About