Showing papers in "Journal of Visual Communication and Image Representation in 2011"

TL;DR: A systematic, comprehensive and up-to-date review of perceptual visual quality metrics (PVQMs) to predict picture quality according to human perception.

TL;DR: By proving that the readjusting procedure works, a theoretical proof is given to justify the method succeeded in embedding and extracting, and the proposed method not only has an acceptable image quality but also provides a large embedding capacity.

TL;DR: A reversible data hiding method based on image interpolation and the detection of smooth and complex regions in the cover images that provides better image quality and embedding capacity compared with prior works.

TL;DR: Optical flows are first estimated and then used for a clue to cluster human crowds into groups in unsupervised manner using the proposed method of adjacency-matrix based clustering (AMC).

TL;DR: The experimental results show that the proposed semi-fragile watermarking scheme outperforms four peer schemes and is capable of identifying intentional tampering and incidental modification, and localizing tampered regions.

TL;DR: Two natural approaches for a rotationally invariant similarity measure that will be used as an alternative to, respectively a modification of the well-known block matching algorithm in nonlocal means denoising are analysed.

TL;DR: A visual surveillance scheme for cage aquaculture that automatically detects and tracks ships (intruders) and a fast 4-connected component labeling method to greatly reduce the computational cost associated with the conventional method is presented.

TL;DR: An image authentication scheme which detects illegal modifications for image vector quantization (VQ) by using the pseudo random sequence and achieves acceptable image quality of the embedded image while keeping good detecting accuracy.

TL;DR: An improved reversible data hiding scheme that can recover original VQ indices after data extraction is presented and experimental results confirm that the hiding capacity of the proposed scheme is around 1.36 bpi in most digital images.

TL;DR: Experimental results show that the proposed hybrid camera system producing multi-view video sequences with more accurate depth maps, especially along the boundary of objects, is suitable for generating more natural 3-D views for3-D TV than previous works.

TL;DR: This work presents an automated and integrated framework that robustly tracks multiple targets for video-based event detection applications and demonstrates event detection by classifying the trajectories of the tracked objects from both traffic monitoring and human surveillance applications.

TL;DR: The algorithm of segment-based stereo matching using graph cuts is developed for extracting depth information from the stereo image pairs by employing the mean-shift algorithm and the use of Adaptive Support Weighted Self-Adaptation dissimilarity algorithm for the estimation of initial disparity.

TL;DR: An efficient video coding method using audio-visual focus of attention, which is based on the observation that sound-emitting regions in an audio- visual sequence draw viewers' attention, is proposed and can yield considerable coding gains over the constant quantization mode of H.264/AVC.

TL;DR: The test campaign described in this paper is by far the most extensive in the history of video coding standardization and shows high consistency and support an accurate comparison of the performance of the different coding technologies.

TL;DR: This paper proposes a new algorithm implementing morphological dilation and erosion of functions, which opens the way to such time-critical applications where the complexity and memory requirements of serial morphological operators represented a bottleneck limiting their usability.

TL;DR: The impact of image enhancement, specifically that of the multi-scale retinex with color restoration (msrcr) on image compression, and vice versa is addressed and an inversion process for the msrcr is developed.

TL;DR: This work proposes a non-blind image deconvolution method which preserves image details, while suppressing ringing and noise artifacts by controlling regularization strength according to local characteristics of the image.

TL;DR: An MPEG-like descriptor is proposed that contains conventional contour and region shape features with a wide applicability from any arbitrary shape to document retrieval through word spotting that is kept to minimum without limiting its discriminating ability.

TL;DR: A cross-layer optimization scheme, which includes packet prioritization and QoS mapping, for the delivery of SVC over the IEEE 802.11e wireless networks, is proposed, and a novel and efficient solution is proposed to reduce the computational complexity of the joint optimization problem.

TL;DR: It has been demonstrated that the new algorithm has almost no overhead with low level encryption and acceptable overhead for high level encryption that leads to totally unperceivable video.

TL;DR: In this paper, a least squares approach that is self-adaptive to the visual quality of the input sequence is proposed that outperforms the others significantly both objectively and subjectively.

TL;DR: A novel hybrid variational model for deconvolving Poissonian images by describing the original image as two parts - a cartoon part characterized by total variation, and a detailed part which has sparse representation over the wavelet basis is proposed.

TL;DR: This paper focuses on improving coding efficiency while preventing drift error in privacy protected H.264/AVC video scrambling, and proposes a restricted video coding scheme, which involves three parts of Mode Restricted Intra Prediction, Search Window Restricted Motion Estimation and Boundary Strength Restricted Deblocking Filtering.

TL;DR: This paper shows it is possible to extract reliable motion trajectories directly from compressed H.264 video streams and proposes to include the information from the compressed domain prediction residuals to make the tracking more robust.

TL;DR: The DNLK filter is extended to form the Overcomplete Dual Non-local Kuan's (OCDNLK) filter by applying to the overcomplete DCT coefficients, which shows the effectiveness of the two methods.

TL;DR: No-reference analysis and processing of DCT (Discrete Cosine Transform) coded images based on estimation of selected MPEG parameters from the decoded video to assess MPEG video quality and perform post-processing without access to neither the original stream nor the code stream.

TL;DR: The experimental results show that compared to the state of the art scalable predictive coder, up to 30% bitrate reductions can be achieved with the combination of proposed prediction schemes depending on the content and quantization level.

TL;DR: Experimental results demonstrate that, compared with the original KTA with new intra coding tool enabled, up to 0.53dB of average coding gain is achieved by the proposed method, while applicable computational complexity is retained for practical video codecs.

TL;DR: The proposed method exploits the advantages of non-linear morphological filters, using a spectrogram to obtain an adequate marker for the morphological processing of the Wigner-Ville transform, and provides cross-term attenuations while preserving time-frequency resolutions.

TL;DR: This paper proposes to use Chambolle’s dual methods to solve Total Variation (TV) inpainting model and (weighted) TV colorization model by adding new variables and proves that the algorithms are quite efficient.