Digital spliced image forensics based on edge blur measurement

In this paper, a digital spliced image detection method based on edge blur measurement is proposed. The blur degree of edges in images is measured based on edge blur extension. The difference of blur degree between authentic images and spliced images is analyzed. The percentage of sharp edge is extracted as features, and used to classify the authentic images and spliced images. The experiments show that the proposed method is effective and the classification accuracy can reach 62% with only 1 kind of features.