典型文献
Image copy-move forgery passive detection based on improved PCNN and self-selected sub-images
文献摘要：
Image forgery detection remains a challenging pro-blem.For the most common copy-move forgery detection,the robustness and accuracy of existing methods can still be further improved.To the best of our knowledge,we are the first to propose an image copy-move forgery passive detection method by combining the improved pulse coupled neural network(PCNN)and the self-selected sub-images.Our method has the following steps:First,contour detection is performed on the input color image,and bounding boxes are drawn to frame the contours to form suspected forgery sub-images.Second,by improving PCNN to perform feature extraction of sub-images,the feature invariance of rotation,scaling,noise adding,and so on can be achieved.Finally,the dual feature matching is used to match the features and locate the forgery regions.What's more,the self-selected sub-images can quickly obtain suspected forgery sub-images and lessen the workload of feature extraction,and the improved PCNN can extract image features with high robustnesss.Through experiments on the standard image forgery datasets CoMoFoD and CASIA,it is effectively verified that the robustnesss score and accuracy of proposed method are much higher than the current best method,which is a more efficient image copy-move forgery passive detection method.
文献关键词：
中图分类号：
作者姓名：
Guoshuai ZHOU;Xiuxia TIAN;Aoying ZHOU
作者机构：
School of Computer Science and Technology,Shanghai University of Electric Power,Shanghai 200090,China;School of Data Science and Engineering,East China Normal University,Shanghai 200062,China
文献出处：
引用格式：
[1]Guoshuai ZHOU;Xiuxia TIAN;Aoying ZHOU-.Image copy-move forgery passive detection based on improved PCNN and self-selected sub-images)[J].计算机科学前沿,2022(04):126-141
A类：
blem,robustnesss,CoMoFoD
B类：
Image,copy,move,forgery,passive,detection,improved,PCNN,self,selected,sub,images,remains,challenging,For,most,common,accuracy,existing,methods,can,still,further,To,best,knowledge,we,are,first,by,combining,pulse,coupled,neural,network,Our,has,following,steps,First,performed,input,color,bounding,boxes,drawn,frame,contours,suspected,Second,improving,extraction,invariance,rotation,scaling,noise,adding,so,achieved,Finally,dual,matching,used,features,locate,regions,What,more,quickly,obtain,lessen,workload,Through,experiments,standard,datasets,CASIA,effectively,verified,that,score,proposed,much,higher,than,current,which,efficient
AB值：
0.426809
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
