人脸边缘自适应搜索算法及仿真研究  

Adaptive searching Algorithm of Facial Edge and Simulation Research

作　　者：李茹[1] 闫俊斌[1] 邓嵩[2] 

机构地区：[1]山西大学计算机与信息技术学院,山西太原030006 [2]山西财经大学,山西太原030006

出　　处：《计算机仿真》2006年第5期87-90,共4页Computer Simulation

摘　　要：人脸轮廓线提取是人脸识别中极为重要的内容,一种可靠、精确的人脸边缘提取算法对于身份鉴定技术等方面具有重要的应用价值。该文基于传统的边缘提取算法提出了一种自适应搜索轮廓线算法,首先基于人脸检测结果确定内外轮廓及搜索路径,然后对于每一条搜索路径提取出真正的轮廓点,最后利用人脸轮廓的平滑性通过曲线拟合完成轮廓线提取。该文以彩色人脸图像库数据为例,快速、准确地得到人脸轮廓线。仿真试验结果表明,该算法能在保持边缘检测精度的情况下,克服了噪声对轮廓特征提取的影响,并且对于姿势变化有一定的鲁棒性,具有一定的应用价值。The facial contour is one of the most important fields in face recognition. So a reliable method for locating the face edge precisely in an image is vital to many practical applications. A novel edge extraction algorithm of adaptive searching based on traditional edge extraction algorithm is proposed in this paper. Firstly, based on the result of face detoction, a search range and searching paths are determined. Secondly, for each searching path, adaptive searching schemes are designed to extract the true contour point. Finally, since the face contour is smooth, by curve fitting, facial contour can be extracted accurately. And then facial contour is gained accurately used the color facial image database in the paper. The simulation result shows that the algorithm overcomes the influence of noise for edge extraction, and has certain robust for the change of posture. The algorithm has further application value for face recognition.

关 键 词：边缘提取 自适应搜索算法 曲线拟合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]