A Multi-Scale Lip Segmentation Method Based on Markov Random Field

DOI

10.2991/icaita-18.2018.35How to use a DOI?

Keywords

lip segmentation; MAP-MRF framework; multi-scale model; wavelet domain

Abstract

In order to perform lip segmentation in a lip-reading system, we propose a new method based on maximum a posterior and Markov random field (MAP-MRF) framework to statistically model observed images of different texture areas in this paper. First, we establish a multi-scale model to capture the characteristics of each sub-region in the image and use the tree structure in the wavelet domain to calculate the probability of tree nodes at different scales. Thus, the number of layer can be considered as one segment cluster. Then, we utilize MRF to translate the lip segmentation problem into labeling optimization issue. Finally, the Bayesian criteria and the extended expectation maximum (EM) algorithm are applied to estimate child node parameters. The experimental results of this method are more robust than the traditional iterative condition model (ICM).

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yuanyao Lu
AU  - Xiaoshan Zhu
AU  - Qingqing Liu
PY  - 2018/03
DA  - 2018/03
TI  - A Multi-Scale Lip Segmentation Method Based on Markov Random Field
BT  - Proceedings of the 2018 2nd International Conference on Artificial Intelligence: Technologies and Applications (ICAITA 2018)
PB  - Atlantis Press
SP  - 137
EP  - 140
SN  - 1951-6851
UR  - https://doi.org/10.2991/icaita-18.2018.35
DO  - 10.2991/icaita-18.2018.35
ID  - Lu2018/03
ER  -