基于MB-LBP和SIFT特征匹配的图像复制粘贴检测  

Image Copy-move Detection Based on MB-LBP and SIFT Feature Matching

作　　者：韩丽娜 梁建娟 刘洪 刘本永 HAN Lina;LIANG Jianjuan;LIU Hong;LIU Benyong(College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China)

机构地区：[1]贵州大学大数据与信息工程学院,贵阳550025

出　　处：《智能计算机与应用》2020年第12期12-15,共4页Intelligent Computer and Applications

基　　金：国家自然科学基金(60862003);贵州省基金(黔科合基础[2019]1063号);贵州大学引进人才科研项目(贵大人基合同字(2017)13号、14号)。

摘　　要：复制粘贴篡改是最常见的图像篡改方式之一,常用检测算法中,SIFT算法是基于点特征的检测方法,对小的篡改区域检测性能较差。针对这一问题,本文探讨通过增加MB-LBP纹理特征提取更多的特征匹配对和提升检测定位能力的算法。实验结果表明,小区域的篡改检测定位是可行的。Copy-move tampering is one of the most commonly used methods of digital image tampering.Among the most related detection methods,the algorithm using SIFT features is usually point-based,and thus it has poor performance when the tampered area is small.To tackle the problem,in this paper we propose to add MB-LBP texture features to obtain more matching pairs and to improve the detection and location capability.The experimental results show that the proposed method is feasible for small area tamper detection and localization.

关 键 词：复制粘贴篡改 SIFT算法 MB-LBP纹理特征 篡改检测定位 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]