多聚焦像素级数字图像信息融合  

A Survey of Color Facial Discriminating Feature Extraction

作　　者：刘永俊[1] 王剑[1] 

机构地区：[1]常熟理工学院计算机科学与工程学院,江苏常熟215500

出　　处：《常熟理工学院学报》2012年第4期100-104,共5页Journal of Changshu Institute of Technology

基　　金：常熟理工学院青年基金"基于多控制融合的人脸图像自动识别技术研究"(KY2008111);江苏省高校自然科学基金"基于投影分析理论与算法的图像特征抽取及分类技术研究"(05KJB520152)

摘　　要：根据图像的清晰恢复结合数字图像处理的基本理论算法,采用多聚焦图像融合技术,提出基于像素级的多聚焦数字图像的融合算法.用统计学的方法计算出不同聚焦图像上的聚焦点,并将其取出合成为一张清晰图像.根据以上算法设计了图像融合软件,并进行了实验验证.With the advent of information age, the way of human getting information has been widened. Images tlave been a necessary way to receive the information. The need of digital image processing technique arises day by day. This paper introduces the general situation that arithmetic figure picture handles. For some color images from the same scene, each of them has a different focus. A novel image fusion scheme for clear restoration of the image is presented in this paper. According to the clear recovery of the image, combined with digital image processing algorithm of the basic theory, and by means of multi-focus image fusion technology, this paper proposes the fusion algorithm of the multi-focus digital image based on the pixel level and calculates the focuses of different focus images with statistical methods and takes out their synthesis for a clear image. Besides, the paper designs the image fusion software based on the above algorithm and conducts a validation by means of the experiment.

关 键 词：图像表示方法 数字图像处理 图像融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]