首页 | 本学科首页   官方微博 | 高级检索  
     

基于无限光源模式的数字图像盲鉴别技术
引用本文:陈海鹏,申铉京,吕颖达,金玉善. 基于无限光源模式的数字图像盲鉴别技术[J]. 吉林大学学报(工学版), 2010, 40(1): 195-0200
作者姓名:陈海鹏  申铉京  吕颖达  金玉善
作者单位:吉林大学,计算机科学与技术学院,长春,130012
基金项目:吉林省科技发展计划项目(20050503)
摘    要:图像篡改通常会破坏自然图像的光照一致性,根据这一特点将光源方向的不一致性作为检测图像篡改的依据。针对在无限光源照射下生成的图像,根据图像的测量强度与计算强度间的误差函数和无限光源模式的约束条件函数,用Hestenes-Powell乘子法计算图像中不同对象和背景的光源方向,并以此判断图像是否被篡改。实验结果表明:本文算法能够有效地计算出无限光源模式下图像中不同对象和背景的光源方向,其正检率已经达到了82.3%。

关 键 词:计算机应用  图像篡改  无限光源  光源方向  盲鉴别  图像真实性
收稿时间:2008-04-20

Blind identification technology for digital images based on infinite light source model
CHEN Hai-peng,SHEN Xuan-jing,LU Ying-da,JIN Yu-shan. Blind identification technology for digital images based on infinite light source model[J]. Journal of Jilin University:Eng and Technol Ed, 2010, 40(1): 195-0200
Authors:CHEN Hai-peng  SHEN Xuan-jing  LU Ying-da  JIN Yu-shan
Affiliation:College of Computer Science and Technology, Jilin University, Changchun 130012, China
Abstract:Inconsistency in light source direction is taken as the basis for the detection of image tampering. Focusing on the images generated under the irradiation of infinite light source,the Hestenes-Powell multiplier method is used to calculate the light source direction of different objects and backgrounds in an image and to determine whether the image has been tampered with. The calculation is in accordance with the error function between the measured intensity and calculated intensity,and the constraint functi...
Keywords:computer application  image tampering  infinite light source  light source direction  blind identification  image authenticity
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《吉林大学学报(工学版)》浏览原始摘要信息
点击此处可从《吉林大学学报(工学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号