Abstract | ||
---|---|---|
We propose a new image forgery detection technique which fuses the outputs of two very diverse tools, based on machine learning and block-matching, respectively. The machine-learning tool builds upon some local descriptors recently proposed in the steganalysis field, which are selected and merged based on an ad hoc measure of reliability. The block-matching tool leverages on the patchmatch algorithm for fast search of candidate matchings. Both tools are fine-tuned so as to optimize their fusion which, in turn, exploits the respective strengths and weaknesses of each tool. The proposed technique ranked first in phase 1 of the first Image Forensics Challenge organized in 2013 by the IEEE Signal Processing Society. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICIP.2014.7026072 | Image Processing |
Keywords | Field | DocType |
image forensics,image fusion,image matching,learning (artificial intelligence),IEEE Signal Processing Society,Image Forensics Challenge,ad hoc reliability measure,block-matching tool,image forgery detection technique,local descriptors,machine learning,output fusion optimization,patchmatch algorithm,residual-based local descriptors,steganalysis field,Digital forensics,forgery detection,machine learning | Residual,Data mining,Signal processing,Pattern recognition,Digital forensics,Ranking,Computer science,Exploit,Artificial intelligence,Steganalysis,Fuse (electrical),Strengths and weaknesses | Conference |
ISSN | Citations | PageRank |
1522-4880 | 30 | 0.94 |
References | Authors | |
17 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Davide Cozzolino | 1 | 358 | 19.37 |
Diego Gragnaniello | 2 | 162 | 12.51 |
Luisa Verdoliva | 3 | 971 | 57.12 |