Detecting logo-removal forgery by inconsistencies of blur

A new approach for detecting video logo-removal forgery is proposed by measuring inconsistencies of blur. Our approach is based on the assumption that if a digital video undergoes logo-removal forgery; the blurriness value of the forged region is expected to be different as compared to the non-tampered parts of the video. Blurriness is estimated by the regularity properties in the wavelet domain which involves measuring the decay of wavelet transform coefficients across scales. The distribution of blurriness value in a forged video is modeled as a GMM (Gauss Mixture Model). The EM (Expectation-Maximization) algorithm is employed to estimate the model parameters. Consequently, a Bayesian classifier is used to find the optimal threshold value. Experimental results show that our approach achieves promising accuracy in logo-removal forgery detection.