Wen Chen, NJIT
Date:  July 17, 2008 (Thursday)
Time:  10:00am – 11:00am
Location:  ECEC 202, NJIT

Abstract:

The advancement of digital techniques makes it much easier than ever before to tamper with digital media such as digital image and video. The tampered image or video comes to appear so perceptually realistic that the trustworthiness of digital image or video cannot be taken for granted any more. Because it is not common in practice that the authentication data such as digital signature is embedded into a medium when the media is generated, the passive-blind techniques to authenticate the digital image or video are important for the applications such as criminal investigation, news reporting, intelligence analysis, and so on.

In this dissertation, the passive-blind techniques in the following three areas have been investigated: (1) image splicing detection; (2) computer graphics identification; and (3) double MPEG video compression detection. The proposed techniques have been implemented in the two-class pattern recognition framework.

Image splicing is the process of making a composite picture by cutting and joining one or multiple regions from the same or different photographs without further post-processing. To differentiate the authentic images from spliced images, the distinguishing image features are extracted by exploiting both magnitude and phase information of a given image. The first part of image features is the statistical moments of characteristic functions of a test image, its prediction-error image, and their wavelet subbands. Furthermore, the approximation (LL) subband at different levels is individually erased (i.e., wavelet coefficients forced to be zero), and inverse wavelet transform is applied in order to enhance high frequency components. From these reconstructed images with LL subbands erased, moments of wavelet characteristic functions form the second part of features. Finally, the statistics (mean, variance, skewness and kurtosis) of 2-D phase congruency array associated with the above-mentioned reconstructed images are the third part of features for splicing detection.

Due to the high photorealism achieved by computer rendering software, the computer graphics may be used as a fake photo picture. To identify computer graphics, the statistical moments of characteristic function of the image and wavelet subbands are used as the distinguishing features. In addition, the influence of different image color representations on the feature effectiveness is investigated. Furthermore, to reduce the redundancy of the features, the binary Genetic Algorithm is applied to seek the optimal feature set.

The video is often tampered in spatial domain by altering video content, dropping, inserting or reordering the frames. For MPEG video file, the tampered video often needs to be re-encoded and re-saved, in which double compression occurs. By identifying the double compression, the traces of possible tampering operation will be revealed. The problem of double MPEG compression detection is approached by analyzing the probability distribution of the first digits of the non-zero quantized MPEG AC coefficients. A decision rule using GOP as the detection unit is proposed.

Committee Members:

Dr. Yun Q. Shi, Professor, Department of ECE, NJIT (Advisor)
Dr. Nirwan Ansari, Professor, Department of ECE, NJIT
Dr. Roberto Rojas-Cessa, Associate Professor, Department of ECE, NJIT
Dr. Frank Y. Shih, Professor, Computer Science Department, NJIT
Dr. Edward K. Wong, Associate Professor, Department of Computer Science, Polytech University

Click here for seminar archive

Note: All ECE MS thesis and PhD dissertation (proposal) defenses are counted towards ECE791.