Il-Kyu Eom

Spliced Image Detection Using Characteristic Function Moments of Co-occurrence Matrix

This paper presents an improved feature extraction method to achieve a good performance in the detection of splicing forged images. Strong edges caused by the image splicing destroy the statistical dependencies between parent and child subbands in the wavelet domain. We analyze the co-occurrence probability matrix of parent and child subbands in the wavelet domain, and calculate the statistical moments from two-dimensional characteristic function of the co-occurrence matrix. The extracted features are used as the input of SVM classifier. Experimental results show that the proposed method obtains a good performance with a small number of features compared to the existing methods.

Spatially adaptive denoising based on mixture modeling and interscale dependencies of wavelet coefficients

In this paper, we propose a mixture modeling of wavelet coefficients for image denoising. A binary mask value is constructed using the parent-child relationship of wavelet domain. Using probabilities based on the significance map, probability weighted Wiener filter is proposed, and also we develop the method of selecting windows of different sizes around the coefficient. Experimental results show that our method outperforms other critically sampled wavelet denoising schemes.