提出一种基于混合肤色模型的实时人脸跟踪方法。
Th paper presents a new real-time face tracking method based on a mixed skin-color model.
由于室内存在多种物体，背景不断变化，且光照条件可能不断变化，提出采用人脸肤色的标准混合高斯模型与人眼特征相结合的人脸检测法，无需对原始图像进行尺度变换。
An effective and fast method of face detection for a service robot is proposed, which combines a mixture of Gaussian distribution model of skin tone color with eyes features.
利用人脸检测结果，结合混合高斯模型，以人脸肤色为样本在线建立了具有针对性的人体肤色模型。
Since a human face has the similar skin color distribution with the human body, we can use the skin pixels in a detected face to build the skin color model of human body dynamically by GMM.
应用推荐