人脸跟踪技术在智能家庭服务系统中的应用

Face Tracking for Use in Intelligent Home Service Interface

提出了一个用于可感知人—机界面系统的快速且鲁棒性强的人脸提取和跟踪算法。算法分两步:首先利用皮肤颜色过滤法和背景去除技术提取出类似皮肤的区域;再利用区域填充和图像分析技术将人的面部分割出来。实验结果证明了此算法的可行性和实时性。

As a first step towards a perceptual human computer interface,an effective and robust face tracking algorithm has been proposed to locate and track the user's face in video sequence.The algorithm relies on a two- step process in which skin- like regions are first segmented by using skin color filter together with the background removal technique.Then the face detection is performed on the segmented binary image by utilizing region filling processing and image analysis technique.The experiment results have demonstrated the feasibility and near real- time performance of the proposed algorithm.