In this study, the authors propose an image authentication algorithm in the DCT domain based on neural networks. The watermark is constructed from the image to be watermarked. It consists of the average value of each 8 × 8 block of the image. Each average value of a block is inserted in another supporting block sufficiently distant from the protected block to prevent simultaneous deterioration of the image and the recovery data during local image tampering. Embedding is performed in the middle frequency coefficients of the DCT transform. In addition, a neural network is trained and used later to recover tampered regions of the image. Experimental results shows that the proposed method is robust to JPEG compression and can also not only localise alterations but also recover them.

A classification of correlation algorithms is provided. A method of S-preparation is discussed, which, due to the preliminary conveyor formation of correlated image convolution sums, is characterised by high noise immunity and adaptivity to uncertainty and variability of the signal clutter situation.

This study proposes a contour-based corner detector using the magnitude responses of the imaginary part of the Gabor filters on contours. Unlike the traditional contour-based methods that detect corners by analysing the shape of the edge contours and searching for local curvature maxima points on planar curves, the proposed corner detector combines the pixels of the edge contours and their corresponding grey-variation information. Firstly, edge contours are extracted from the original image using Canny edge detector. Secondly, the imaginary parts of the Gabor filters are used to smooth the pixels on the edge contours. At each edge pixel, the magnitude responses at each direction are normalised by their values and the sum of the normalised magnitude response at each direction is used to extract corners from edge contours. Thirdly, both the magnitude response threshold and the angle threshold are used to remove the weak or false corners. Finally, the proposed detector is compared with five state-of-the-art detectors on some grey-level images. The results from the experiment reveal that the proposed detector is more competitive with respect to detection accuracy, localisation accuracy, affine transforms and noise-robustness.

Data hiding is a technique that is embedding the secret message into the media. In 2010, Chen et al.’s proposed a scheme combined the ‘Canny’ edge detector and fuzzy edge detector to increase edge pixels, and embedded more secret data into the edge pixels than the non-edge pixels based on the least-significant-bit (LSB) substitution scheme. In this study, the authors use Kaur et al.’s fuzzy logic-based algorithm and extend the original design to block-based design. The experimental results show that the proposed method achieves higher payload with Kaur et al.'s fuzzy logic-based algorithm, and achieve minimal distortion by selecting the number of edge pixel's embedding length of each block which has minimum mean-squared error.

The authors propose a video fingerprinting method based on structural similarity and a graph model. Structural similarity-based fingerprint generation and double-layer matching are the two main contributions. The video is mapped to a graph with frames as its vertices, and structural similarity is proposed to compute the weights of the edges. Then, the fingerprint consisting of a match tag (a coarse fingerprint) and a fine fingerprint is generated by this graph. The match tag is generated by an independent set of this graph, and the fine fingerprint is generated by the weight matrix of the graph based on the two-block-dimensional discrete cosine transform. During the matching, the video can be matched at the first-layer using the match tag to obtain a candidate set, whereas the second-layer matching is performed in this candidate set using the fine fingerprint to find a final match. The proposed video fingerprinting method is shown to be resistant to geometric attacks on frames and impairment of transmission channels.

Nowadays, the lossless watermarking methods that can resist attacks have attracted more attention. Obtaining a robust lossless watermarking was at the cost of reducing the capacity and the watermarked image quality. This study presents a new robust lossless watermarking scheme in the transform domain where the Slantlet transform (SLT) has been applied to transform the host image and blocks of the SLT coefficients have been selected for the embedding process. The histograms of the selected blocks are modified according to a predefined threshold value to carry the watermark bits. The overflow/underflow of the pixel values have been avoided by using a pixel adjustment method as a post-processing step. In the proposed scheme, the original host image can be recovered without any distortion after the hidden watermark has been extracted and the watermark can withstand different kinds of attacks. In comparison with the previous methods, the proposed scheme has higher embedding capacity, better robustness against unintentional attacks and improved visual quality. The results of the experiments prove the efficiency of the proposed scheme.