Abstract

The wide use of high-performance image acquisition devices and powerful image-processing software has made it easy to tamper images for malicious purposes. Image splicing, which has constituted a menace to integrity and authenticity of images, is a very common and simple trick in image forgery. Therefore, image-splicing detection is one the significant issues involved in digital forensics. In this paper, an effective passive splicing image forgery detection scheme based on Improved Local Binary Pattern (LBP) and Discrete Cosine Transform (DCT) is proposed. First, the chrominance component of the input image is divided into non-overlapping blocks. Then, for each block, Improved LBP is calculated and transformed into frequency domain using 2D DCT. Standard deviations of frequency coefficients for all blocks are calculated and used as features K-Nearest Neighbors (KNN) algorithm is used for classification. Experimental results show the accuracy improvement for the proposed method in terms of the detection performance over CASIA1 and CASIA2 image splicing detection evaluation dataset.