基于图像序列的模糊聚类嘴唇分割算法

Moving information guided FCM for lip segmentation of image sequences

嘴唇分割是唇读系统中很重要的一步。由于人们说话是一个连续的过程,所以最终需要处理的是连续的帧。但是,现有的大多数嘴唇分割算法都是针对于孤立的图片而不是连续的嘴唇序列,因此在嘴唇分割的过程中忽略了连续两帧之间的联系。文中提出了基于模糊聚类的图像序列嘴唇分割算法。该算法是在传统模糊聚类框架中融入了运动信息和参考颜色信息。文中首先利用已有的算法来处理图像序列,发现实验结果并不稳定。通过分析发现:当像素点在连续两帧间运动较小或静止时,人们希望它们的分类和上一帧保持连续性;对于同一个人的嘴唇序列,其嘴唇聚类中心不会发生较大的偏移。基于以上两点,提出了基于运动信息的模糊聚类图像序列嘴唇分割算法。

Lip segmentation is an important step in lip reading. Since human speech is continuous in natural,lip sequences rather than isolated lip images need to be processed. However,most ol the current lip segmentation algorithms utilize isolated images and neglect the underlying connections between consecutive frames. In this paper, a fuzzy clustering based algorithm called moving information guided luzzy C-means algorithm is proposed to exploit the above connection and to extract the lip region Irom lip image sequences.