Title :
Image forgery detection using feature based clustering in JPEG images
Author :
Bhartiya, Gunjan ; Jalal, Anand Singh
Author_Institution :
Dept. of Comput. Eng. & Applic., GLA Univ., Mathura, India
Abstract :
JPEG images are most commonly used in a wide variety of applications. JPEG compression properties can be used for forgery detection in digital images. While performing an intended forgery, the image has to be recompressed. Therefore identifying the traces of recompression can be good clue for detecting manipulation. In this paper, a method to detect forgery in JPEG image is presented and an algorithm is devised to classify the image blocks as forged or non-forged based on this classification. The method produces better results than the previous methods which use the probability based approach for detecting forgery.
Keywords :
data compression; image classification; image coding; probability; JPEG compression properties; JPEG image; digital images; feature-based clustering; image classification; image forgery detection; image recompressed; intended forgery; probability; Accuracy; Digital images; Feature extraction; Forgery; Histograms; Image coding; Transform coding; Image Forgery; JPEG compression; double compression;
Conference_Titel :
Industrial and Information Systems (ICIIS), 2014 9th International Conference on
Conference_Location :
Gwalior
Print_ISBN :
978-1-4799-6499-4
DOI :
10.1109/ICIINFS.2014.7036583
