[1]张震,苏白娜,喻宙..一种新的图像拷贝篡改检测方法[J].郑州大学学报(工学版),2012,33(06):15-18.[doi:10.3969/j.issn.1671-6833.2012.06.004]
　ZHANG Zhen,SU Baina,YU Zhou.A New Approach for Detecting Copy-Forged Images[J].Journal of Zhengzhou University (Engineering Science),2012,33(06):15-18.[doi:10.3969/j.issn.1671-6833.2012.06.004]
点击复制

一种新的图像拷贝篡改检测方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
33卷
期数:
2012年06期
页码:
15-18
栏目:
出版日期:
2012-11-10

文章信息/Info

Title:
A New Approach for Detecting Copy-Forged Images
作者:
张震; 苏白娜; 喻宙.
郑州大学 电气工程学院,河南郑州,450001, 郑州大学 电气工程学院,河南郑州,450001, 郑州大学 电气工程学院,河南郑州,450001
Author(s):
ZHANG Zhen; SU Baina; YU Zhou
School of Electrical Engineering,Zhengzhou University.Zhengzhou 450001，China
关键词:
图像篡改检测;  拷贝篡改定位;  保局投影;  尺度不变特征变换
Keywords:
image forgery detection;  copy forgery location;  LPP;  SIFT
分类号:
TP391
DOI:
10.3969/j.issn.1671-6833.2012.06.004
摘要:
针对图像的区域拷贝篡改提出了一种新的检测方法,即基于LPP-SIFT(Locality Preserving Projection-Scale Invariant Feature Transform)的检测算法.该算法利用SIFT提取图像的特征点,结合LPP特征映射,生成低维特征点描述子,然后依据向量角度比率得到匹配点对,匹配点对聚集的区域即为拷贝篡改区域.实验表明该算法能够有效地检测定位区域拷贝篡改图像,且对于拷贝区域的旋转、缩放以及图像的JPEG压缩、噪声添加等操作具有较强的鲁棒性.
Abstract:
This paper proposes a novel method based on LPP-SIFT ( Locality Preserving Projection-Scale Invariant F’eature ’Transform ) for image copy-forgery detection, First, some steps of SF’T algorithm are used toextract key points; second, LPP is used to obtain low-dimensional feature descriptors, and then key points canbe matched by the ratio of vector angel, If mass matching key points exist in a region, the region can bejudged to have undergone copy-forged operation, Experiments demonstrate that the method can effectively de.tect forged images and locate the forged area, and this method is robust to rotation, scaling, jPEG compressionand noise addition.
更新日期/Last Update: 1900-01-01