Showing papers in "Journal of Visual Communication and Image Representation in 2010"
••
TL;DR: This paper focuses on solving the restoration of blurred images corrupted by Poisson noise by minimizing an energy functional consisting of the I-divergence as similarity term and the TV regularization term by using alternating split Bregman techniques.
362 citations
••
TL;DR: A new rendering algorithm is explored that enables to compute a free-viewpoint between two reference views from existing cameras that performs forward warping for both texture and depth simultaneously.
136 citations
••
TL;DR: A new adaptive Haar wavelet transform, called Tetrolet Transform, is introduced, which shows the strong efficiency of the tetrolet transform for image approximation.
133 citations
••
TL;DR: The experimental results demonstrate that the ripplet transform can provide efficient representation of edges in images and holds great potential for image processing such as image restoration, image denoising and image compression.
99 citations
••
TL;DR: A novel approach named the scaling iterative closest point (SICP) algorithm which integrates a scale matrix with boundaries into the original ICP algorithm for scaling registration of m-D point sets is introduced.
89 citations
••
TL;DR: An iterative updating approach is developed in this paper by allowing the value of hyperparameter being simultaneously updated in each sample-generation iteration to improve the reconstructed high-resolution image quality, when the number of samples is insufficient.
72 citations
••
TL;DR: A 3D video display technique that allows multiple viewers to see 3D images from a 360-degree horizontal arc without wearing 3D glasses is proposed and improved by revolving the parallax barrier.
57 citations
••
TL;DR: The paper presents two main contributions, which have studied different alternatives to introduce the scalar part to obtain full colour quaternions, and several total lexicographic orderings forQuaternions have been defined, according to the various quaternion decompositions.
54 citations
••
TL;DR: A new reversible scheme based on locally adaptive coding for VQ-compressed images that has the best compression rate and the highest embedding capacity compared with other reversible VQ embedding methods is proposed.
51 citations
••
TL;DR: The proposed flip visual cryptography scheme is proved to have conditionally optimal contrast: its contrast is optimal if the double-secrets non-expanded FVC scheme is required to have perfect security.
50 citations
••
TL;DR: A new view synthesis method in multiview camera configurations of Free viewpoint TV (FTV) where potential depth errors are considered and the complementarity principle of the artifacts from left and right references is infers.
••
TL;DR: In this issue, a secure end-to-end touch-less fingerprint verification system is presented and Multiple Random Projections-Support Vector Machine (MRP-SVM) is proposed to secure fingerprint template while improving system performance.
••
TL;DR: A combinatorial algorithm is presented for varying grid sizes, which is free of any backtracking and can produce the isothetic cover of a connected component in a time linear in the length of the perimeter of the cover.
••
TL;DR: This paper addresses the image representation problem in visual sensor networks by using a piecewise autoregressive model to construct a prediction of the sparse component from the corresponding dense component and using projection onto convex set (POCS) to reconstruct the sparse components.
••
TL;DR: A novel rate-constrained edge detection algorithm, which integrates the idea of significance bitplanes into the Canny edge detector, which provides an efficient way to extract and encode edges.
••
TL;DR: Experimental results show that the proposed iteration-based algorithm can colour-correct the dense/sparse multicamera system, and out-performs the conventional method.
••
TL;DR: A novel method for unsupervised change detection in multi-temporal satellite images of the same scene using Gaussian mixture model (GMM) and genetic algorithm (GA) does not need any parameter tuning process, and is completely automatic.
••
TL;DR: A novel framework for video quality prediction of MPEG-based video services, considering the perceptual degradation that is introduced by the encoding process and the provision of the encoded signal over an error-prone wireless or wire-line network is proposed.
••
TL;DR: Experimental results show the success of the proposed cepstral approach for landmine detection from both acoustic and GPR images at low as well as high signal to noise ratios (SNRs).
••
TL;DR: A novel vision and a novel system for movies summarization by means of IM(S)^2, people generate on the fly customized video summaries responding to their preferences responding to the user's preferences.
••
TL;DR: A video copy detection framework that detects copy segments by fusing the results of three different techniques: facial shot matching, activity subsequence matching, and non-facial shot matching using low-level features is proposed.
••
TL;DR: This paper presents a general object boundary extraction model for piecewise smooth images, which incorporates local intensity distribution information into an edge-based implicit active contour, and proposes the local distribution fitting model for more accurate segmentation.
••
TL;DR: Experimental results demonstrate that the proposed method can achieve a significant end-to-end RD performance improvement over the selective streaming methods with simulcast coding or scalable multiview coding, and has better error-resilience performance to combat with packet-losses over the Internet protocol (IP) networks.
••
TL;DR: Experimental results show that compared with other methods, the proposed method can promote the correction speed greatly without noticeable quality degradation, and obtain higher coding performance.
••
TL;DR: An overall framework based on the complementary idea of acquiring sensor streams automatically in conjunction with video content is presented, augmented with the design and implementation ideas to illustrate the feasibility of managing geo-tagged video.
••
TL;DR: This paper takes advertising theory, psychology, and computational aesthetics into account to develop a novel virtual advertising mechanism, called virtual spotlighted advertising (ViSA), for tennis videos that utilizes the extraneous visual acuity of viewers while watching the attractive object, such that they are not much disturbed from the progress of the game.
••
TL;DR: This paper proposes a new approach, integrating TFRC with the application layer and the physical layer to form a holistic design for real-time video streaming over wireless multi-hop networks, which can achieve the best user-perceived video quality.
••
TL;DR: The experimental results show that for underwater color images the proposed method outperforms both WDR and SPIHT at very low bit rates in terms of compression ratio and reconstructed quality, while for natural images it has similar performance with WDRand SPIHT.
••
TL;DR: This paper analyzes Yahoo! Video, the 2nd largest U.S. video sharing site, and reveals key results regarding the impact of workload arrival distribution, Service Level Agreements (SLAs), and workload scheduling schemes on the design and operations of such large-scale video distribution systems.
••
TL;DR: An automatic algorithm to segment multiple objects from multi-view video based on the saliency model is presented, resulting in a more accurate Interested Objects (IOs) layer across all views of the frames.