An unconstrained method for lip detection in color images

Skodras, Evangelos; Fakotakis, Nikos

doi:10.1109/icassp.2011.5946578

Cited by 29 publications

(18 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, fuzzy C-means (FCM) and K-means clustering-based methods have been employed to perform lip segmentation [22]- [24]. Moreover, the works described in [25]- [27] utilize statistical models, e.g.…”

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

“…Several lip segmentation methods based on gray-scale image [3][4][5], other methods are based on color image. Some methods use color image directly [6,7], the other method use color conversion to other color space to enlarge the color different of lip and the background, for example YCbCr [8], NTSC [9], and CIE L*a*b* [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Lip segmentation and tracking based on Chan-Vese model

Nasuha

Sardjono

Purnomo

2013

2013 International Conference on Information Technology and Electrical Engineering (ICITEE)

View full text Add to dashboard Cite

Lip reading has wide spread application, e.g. audio-visual Automatic Speech Recognition (A V-ASR), silent speech interface and person identification. Lip segmentation is one of important step in lip reading, because it provides basic information to be processed in subsequent steps. Lip tracking is a process of locating lip to associate lip in consecutive video fr ames. Chan-Vese model is a region-based segmentation algorithm, which also can be used as tracking method. This algorithm can detect boundary of object which not defined by gradient, while classical active contour can't be applied. This method also can detect object by any initial curve in the image, not necessarily surround the obj ect. This paper investigates about lip segmentation and tracking based on Chan-Vese model, preceded by the color segmentation.

show abstract

“…This method needs prior knowledge of lips shape. Another technique is based on segmentation in color spaces [7,8].…”

Section: Introductionmentioning

confidence: 99%

Inner lips feature extraction based on CLNF with hybrid dynamic template for Cued Speech

Liu

Feng

Beautemps

2017

J Image Video Proc.

View full text Add to dashboard Cite

In previous French Cued Speech (CS) studies, one of the widely used methods is painting blue color on the speaker's lips to make lips feature extraction easier. In this paper, in order to get rid of this artifice, a novel automatic method to extract the inner lips contour of CS speakers is presented. This method is based on a recent facial contour extraction model developed in computer vision, called Constrained Local Neural Field (CLNF), which provides eight characteristic landmarks describing the inner lips contour. However, directly applied to our CS data, CLNF fails in about 41.4% of cases. Therefore, we propose two methods to correct the B parameter (aperture of inner lips) and A parameter (width of inner lips), respectively. For correcting the B parameter, a hybrid dynamic correlation template method (HD-CTM) using the first derivative of smoothed luminance variation is proposed. HD-CTM is first applied to detect the outer lower lips position. Then, the inner lower lips position is obtained by subtracting the validated lower lips thickness (VLLT). For correcting the A parameter, a periodical spline interpolation with a geometrical deformation of six CLNF inner lips landmarks is explored. Combined with an automatic round lips detector, this method is efficient to correct A parameter for round lips (the third vowel viseme made of French vowels with a small opening). HD-CTM is evaluated on 4800 images of three French speakers. It corrects about 95% CLNF errors of the B parameter, and total RMSE of one pixel (i.e., 0.05 cm on average) is achieved. The periodical spline interpolation method is tested on 927 round lips images. The total error of CLNF is reduced significantly, which is comparable to the state of the art. Moreover, the third viseme is properly distributed in the parameter A and B plane after using this method.

show abstract

An unconstrained method for lip detection in color images

Cited by 29 publications

References 10 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

Lip segmentation and tracking based on Chan-Vese model

Inner lips feature extraction based on CLNF with hybrid dynamic template for Cued Speech

Contact Info

Product

Resources

About