数字相片智能检测技术研究与实现  

Study and Implementation of Intelligent Inspection for ID Cards Digital Photo

作　　者：周广新[1] 赵龙[1] 肖全初 

机构地区：[1]国防科学技术大学计算机学院,湖南长沙410073 [2]湖南省司法警官学院,湖南长沙410131

出　　处：《计算机仿真》2006年第6期190-194,共5页Computer Simulation

摘　　要：该文针对第二代居民身份证制证用数字相片智能检测问题进行研究并简述主要的实现技术。文章分析An il K.Ja in等提出的光线补偿方法的不足和YCbC r颜色空间在应用中的优点。一种基于环境采样卡的图像校正方法和YCbC r颜色空间上经过非线性分段色彩变换到YCb C r空间的肤色模型。该文介绍了作者在肤色模型基础上眼睛标定的具体实现技术,提出一种基于像素统计的“密度”滤波处理方法来提高肤色判断的鲁棒性。介绍了优先眼睛标定的其它数字相片规格指标的综合智能检测实现技术。The paper aims at the problem of intelligent inspection for the ID cards digital photo and gives the methods for realization. The paper analyses the shortage of Lighting Compensation method advanced by Anil K. Jain and the advantage of YCbCr color space. It bring forward a method of color emendation baseol on Conditions Sampling Chart and a model of complexion based on YCb＇Cr＇ color space which changed from YCbCr by nonlinear color transformation. To improve the robust of complexion judgement, the paper gives a filtration method based on density of pixel. Based on the complexion model, the paper gives an integrated means by demarcating the eyes firstly.

关 键 词：居民身份证制证用数字相片 环境采样卡 非线性分段色彩变换 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论] TP391.41[自动化与计算机技术—计算机科学与技术]