Paper Info
Title
Camera Response Functions for Image Forensics: An Automatic Algorithm for Splicing Detection
Abstract
We present a fully automatic method to detect doctored digital images. Our method is based on a rigorous consistency checking principle of physical characteristics among different arbitrarily shaped image regions. In this paper, we specifically study the camera response function (CRF), a fundamental property in cameras mapping input irradiance to output image intensity. A test image is first automatically segmented into distinct arbitrarily shaped regions. One CRF is estimated from each region using geometric invariants from locally planar irradiance points (LPIPs). To classify a boundary segment between two regions as authentic or spliced, CRF-based cross fitting and local image features are computed and fed to statistical classifiers. Such segment level scores are further fused to infer the image level authenticity. Tests on two data sets reach performance levels of 70% precision and 70% recall, showing promising potential for real-world applications. Moreover, we examine individual features and discover the key factor in splicing detection. Our experiments show that the anomaly introduced around splicing boundaries plays the major role in detecting splicing. Such finding is important for designing effective and efficient solutions to image splicing detection.
Year
DOI
Venue
2010
10.1109/TIFS.2010.2077628
IEEE Transactions on Information Forensics and Security
Keywords
Field
DocType
tampering detection,camera response function,shaped image region,automatic algorithm,image coding,statistical analysis,geometric invariants,boundary segment,image segmentation,test image,locally planar irradiance points,splicing boundary,cameras mapping input irradiance,computer forensics,automatic method,crf-based cross fitting,image classification,image splicing detection,local image feature,cameras,splicing detection,camera response functions,digital image,camera response function (crf),image forensics,output image intensity,statistical classifiers,image level authenticity,doctored digital image detection,image features,splicing,brightness,estimation
Computer vision,Data set,Pattern recognition,Feature (computer vision),Computer science,Image segmentation,Digital image,Artificial intelligence,RNA splicing,Invariant (mathematics),Contextual image classification,Standard test image
Journal
Volume
Issue
ISSN
5
4
1556-6013
Citations 
PageRank 
References 
25
0.95
20
Authors
2
Name
Order
Citations
PageRank
Yu-Feng Hsu125817.15
Shih-Fu Chang2130151101.53