Title :
Image copy-move forgery detection based on “crossing shadow” division
Author :
Hou, Dongmei ; Bai, Zhengyao ; Liu, Shuchun
Author_Institution :
Sch. of Inf. Sci. & Eng., Yunnan Univ., Kunming, China
Abstract :
A new image division method is proposed to detect image copy-move forgery. First, discrete wavelet transform (DWT) is applied to the input image to yield a reduced dimension representation. Then divide the reduced dimension representation into nine sub-images by using "crossing shadow" division. Next, calculate phase correlation and pulse to obtain spatial offset between the copied and the pasted part. With that, the copy-move regions can be easily located by virtue of pixel matching. Finally, the mathematical morphological operations were used to improve the detection. Experimental results show that this method can be implemented more conveniently and it has a wide application.
Keywords :
discrete wavelet transforms; image matching; image representation; mathematical morphology; reproduction (copying); security of data; crossing shadow; discrete wavelet transform; forgery detection; image copy move; image division method; image representation; mathematical morphology; phase correlation; pixel matching; Computational complexity; Correlation; Discrete wavelet transforms; Forgery; Fourier transforms; Pixel; copy-move forgery; crossing shadow; phase correlation; pulse;
Conference_Titel :
Electric Information and Control Engineering (ICEICE), 2011 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-8036-4
DOI :
10.1109/ICEICE.2011.5778232
