According to the characteristics of the color filter array interpolation in a camera, an image splicing forgery detection algorithm based on bi-cubic interpolation and Gaussian mixture model is... Show More

According to the characteristics of the color filter array interpolation in a camera, an image splicing forgery detection algorithm based on bi-cubic interpolation and Gaussian mixture model is proposed. The authors make the assumption that the image is acquired using a color filter array, and that tampering removes the artifacts due to a demosaicing algorithm. This article extracts the image features based on the variance of the prediction error and create image feature likelihood map to detect and locate the image tampered areas. The experimental results show that the proposed method can detect and locate the splicing tampering areas precisely. Compared with bi-linear interpolation, this method can reduce the prediction error and improve the detection accuracy.

In this article, a blind and robust medical image watermarking technique based on Finite Ridgelet Transform (FRT) and Singular Value Decomposition (SVD) is proposed. A host medical image is first... Show More

In this article, a blind and robust medical image watermarking technique based on Finite Ridgelet Transform (FRT) and Singular Value Decomposition (SVD) is proposed. A host medical image is first transformed into 16 × 16 non-overlapping blocks and then ridgelet transform is applied on the individual blocks to obtain sets of ridgelet coefficients. SVD is then applied on these sets, to obtain the corresponding U, S and V matrix. The watermark information is embedded into the host medical image by modification of the value of the significant elements of U matrix. This proposed technique is tested on various types of medical images such as X-ray and CT scan. The simulation results revealed that this technique provides better imperceptibility, with an average PSNR being 42.95 dB for all test medical images. This technique also overcomes the limitation of the existing technique which is applicable on only the Region of Interest (ROI) of the medical image.

Delay tolerant networks (DTNs) represent a class of intermittently connected networks. In such networks, messages are hard to track since they are transmitted by opportunistic encounters between... Show More

Delay tolerant networks (DTNs) represent a class of intermittently connected networks. In such networks, messages are hard to track since they are transmitted by opportunistic encounters between mobile nodes. This feature makes DTN an appropriate masking channel for information hiding systems. However, the DTN often has poor communication quality, given that it suffers from frequent disruptions. In order to improve the communication quality of DTN and meet the needs of information hiding system, an efficient routing strategy is proposed in this article. On the other hand, in information hiding systems, a relatively long Time-To-Live (TTL) of messages will increase the risk of the message being exposed. To achieve a balance between delivery ratio and concealment, the sensitivity of message TTL is analyzed and a suitable value of lifetime is given. Finally, the simulation results show that the proposed algorithm can improve the effectiveness of message transmission, and the DTN can be used as masking channel to realize information hiding system.

Detecting digital audio forgeries is a significant research focus in the field of audio forensics. In this article, the authors focus on a special form of digital audio forgery—copy-move—and propose... Show More

Detecting digital audio forgeries is a significant research focus in the field of audio forensics. In this article, the authors focus on a special form of digital audio forgery—copy-move—and propose a fast and effective method to detect doctored audios. First, the article segments the input audio data into syllables by voice activity detection and syllable detection. Second, the authors select the points in the frequency domain as feature by applying discrete Fourier transform (DFT) to each audio segment. Furthermore, this article sorts every segment according to the features and gets a sorted list of audio segments. In the end, the article merely compares one segment with some adjacent segments in the sorted list so that the time complexity is decreased. After comparisons with other state of the art methods, the results show that the proposed method can identify the authentication of the input audio and locate the forged position fast and effectively.

In previous studies of synthetic speech detection (SSD), the most widely used features are based on a linear power spectrum. Different from conventional methods, this article proposes a new feature... Show More

In previous studies of synthetic speech detection (SSD), the most widely used features are based on a linear power spectrum. Different from conventional methods, this article proposes a new feature extraction method for SSD from octave power spectrum which is obtained from constant-Q transform (CQT). By combining CQT, block transform (BT) and discrete cosine transform (DCT), a new feature is obtained, namely, constant-Q block coefficients (CBC). In which, CQT is used to transform speech from the time domain into the frequency domain, BT is used to segment octave power spectrum into many blocks and DCT is used to extract principal information of every block. The experimental results on ASVspoof 2015 corpus shows that CBC is superior to other front-ends features that have been benchmarked on ASVspoof 2015 evaluation set in terms of equal error rate (EER).