基于肤色信息和距离变换的快速人脸检测算法

Fast face detection based on skin color and distance transform

人脸识别技术是当今人工智能和模式识别领域的一项重要研究内容,快速稳定的人脸检测算法已成为新的研究热点。提出了一种基于肤色模型和距离变换的快速人脸检测算法,首先利用肤色在颜色空间的类聚特性对肤色加以判别,从而确定出人脸区域在图像中的基本位置,然后运用距离变换结合人脸的几何特征计算出长和宽,最终实现人脸的定位。实验结果表明:该算法简单,易实现,在执行时间和识别率上取得了较好的效果。

Nowadays the face recognition technology is a important research in the field of artificial intelligence and pattern recegnition,the fast and stable face detection algorithm becomes the new host research spot. A new fast face detection algorithm algorithm which based on skin color model and distance transform is proposed. First,skin pixels are distinguished from the non-skin pixels by using the clutter feature of skin color in the YCrCb color space and the essence position of face area in whole picture can be found. Then figure out the length and width using distance transform and the geometrical feature of human face, so the accurate face position can be located. The experimental results show the algorithm is simple and easy to implement, and is satisfactory in execution time and recognition.