基于广义判决分析的图像拼接检测最优类色度通道设计方法  

Optimal Chroma-like Channel Design for Image Splicing Detection Based on Generalized Discriminant Analysis

作　　者：赵旭东[1] 李生红[1] 王士林[2] 李建华[1] 

机构地区：[1]上海交通大学电子信息与电气工程学院,上海200240 [2]上海交通大学信息安全工程学院,上海200240

出　　处：《电子与信息学报》2014年第9期2033-2040,共8页Journal of Electronics & Information Technology

基　　金：国家973计划项目(2010CB731403;2010CB731406);国家自然科学基金(61271316;61071152);国家"十二五"科技支撑计划重点项目(2012BAH38B04);信息内容分析技术国家工程实验室资助课题

摘　　要：针对图像拼接检测问题,该文提出一种基于广义判决分析(GDA)的最优类色度通道设计方法。将最优类色度通道的设计建模为一个以GDA识别力为目标函数,以类色度通道参数范围为约束条件的最优化问题,通过网格搜索和梯度上升法求解最优类色度通道参数。在哥伦比亚图像拼接检测评估库中的实验结果显示,目前4种主流的图像拼接检测方法在最优类色度通道上的识别率均高于已有的颜色通道,验证了该方法的通用性和有效性。A Generalized Discriminant Analysis （GDA） based method is proposed to find the optimal chroma-like channel for image splicing detection. The channel design scheme is modeled as an optimization problem in which the objective function is the discriminative power of GDA with constraint of coefficients of the chroma-like channel. The optimization problem is resolved by grid searching combined with the gradient ascent algorithm. The results obtained from the experiment in the Columbia Image Splicing Detection Evaluation Dataset show that the detection performance of four current methods in the mainstream with regard to the rate of identification in the most optimal color designed channel is better than that in the existing color channels, which verify the versatility and effectiveness of the Drooosed method.

关 键 词：图像拼接检测 类色度通道 广义判决分析 网格搜索 梯度上升法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]