摘要
人面是常见的复杂模式.在复杂景物图片中自动找出人面是一个困难但有重要意义的任务.这是自动人面识别系统的第一个重要步骤.作者提出了一个多层的基於知识的人面定位系统来在复杂背景中找出人面.在这个系统中高层是建立在镶嵌图上的.本文介绍了镶嵌图的一些性质和它们在人面定位中的应用.提出了在具有复杂背景图片中尺寸和数量未知的人面定位问题的解决方法.
The human face is a complex pattern. Finding human faces automatically in a scene is a difficult yet significant, problem. This is the first important step in a fully automatic human face recognition system. The authors have proposed a hierarchical knowledge-based face detection system to locate human faces in a complex background. In this system the higher levels are based on the mosaic images. In this paper the authors introduce several characteristics of the mosaic images and their application in the human face location. A mosaic image with certain size of cells may present the region features of a face. In this research the authors solved the problem of finding human faces in a picture with complex background when the size and number of faces are unknown.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
1996年第3期213-220,共8页
Pattern Recognition and Artificial Intelligence
关键词
人面定位
镶嵌图
模式识别
Human Face Location, Mosaic Image, Knowledge-based PR.