Copy-move forgery detection and localization by means of robust clustering with J-Linkage

作者：

Highlights：

• We present an effective and efficient approach for copy-move detection/localization.

• We improve previous works based on local visual features such as SIFT.

• We extend the J-Linkage clustering algorithm for the task of copy-move detection.

• By using J-Linkage we are able to compute a very precise tampering localization.

• Results on different datasets show that our method outperforms the state-of-the-art.

摘要

Highlights•We present an effective and efficient approach for copy-move detection/localization.•We improve previous works based on local visual features such as SIFT.•We extend the J-Linkage clustering algorithm for the task of copy-move detection.•By using J-Linkage we are able to compute a very precise tampering localization.•Results on different datasets show that our method outperforms the state-of-the-art.

论文关键词：Digital image forensics,Tampering detection,Copy-move detection,Copy-move localization

论文评审过程：Received 28 November 2012, Revised 19 March 2013, Accepted 19 March 2013, Available online 1 April 2013.

论文官网地址：https://doi.org/10.1016/j.image.2013.03.006