文章基本信息

标题：REPETITIVE FEATURE EXTRACTION WITH LOCALIZED DELAUNAY TRIANGULATION FOR COPY-MOVE-FORGERY-DETECTION
本地全文：下载
作者：Dhanya R ; R Kalaiselvi
期刊名称：Indian Journal of Computer Science and Engineering
印刷版ISSN：2231-3850
电子版ISSN：0976-5166
出版年度：2021
卷号：12
期号：5
页码：1179-1186
DOI：10.21817/indjcse/2021/v12i5/211205005
语种：English
出版社：Engg Journals Publications
摘要：The newly invented sophisticated softwares like Adobe Photoshop make the alteration of image very easy. Advanced tools are provided in these softwares that make the image look real which makes it inconvenient to be identified by the naked eye. Taking out features with key point based method using Scale Invariant Feature Transform (SIFT) is discussed in this paper. The extracted feature points are then modeled to with Delaunay Triangulation to get a group of triangles. Mean vertex descriptor of these triangles is matched. Outlier detection is done using Random Sample Consensus (RANSAC). Equivalent methods are outdone by the proposed approach in implementation.
关键词：Forensic Digital Image Processing;Delaunay Triangulation;Forgery Detection;RANSAC;SIFT