By Topic

Digital Home (ICDH), 2012 Fourth International Conference on

Date 23-25 Nov. 2012

Filter Results

Displaying Results 1 - 25 of 95
  • [Front cover]

    Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (793 KB)  
    Freely Available from IEEE
  • [Title page i]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (112 KB)  
    Freely Available from IEEE
  • [Title page iii]

    Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (151 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (129 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): v - x
    Save to Project icon | Request Permissions | PDF file iconPDF (159 KB)  
    Freely Available from IEEE
  • Welcome Message from the General Chairs of ICDH 2012

    Page(s): xi
    Save to Project icon | Request Permissions | PDF file iconPDF (98 KB)  
    Freely Available from IEEE
  • Conference Organization

    Page(s): xii
    Save to Project icon | Request Permissions | PDF file iconPDF (108 KB)  
    Freely Available from IEEE
  • Organizing Committee

    Page(s): xiii
    Save to Project icon | Request Permissions | PDF file iconPDF (87 KB)  
    Freely Available from IEEE
  • Organizing and Supporting Institutions

    Page(s): xiv
    Save to Project icon | Request Permissions | PDF file iconPDF (343 KB)  
    Freely Available from IEEE
  • A Cloth Simulation Method Based on Differential Geometric Energy

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (815 KB) |  | HTML iconHTML  

    According to the properties of bending and stretching in the cloth simulation, in order to achieve a superior cloth deformation effects, this paper proposes a new cloth simulation method based on the geometric deformation model that can preserve geometric features in the deformation better. Based on differential domain constraints condition, deformation energy function based on the different types of cloth materials is optimized. Nonlinear least squares deformation energy is the core of this differential framework. The cloth deformation is simulated interactively by increasing the related constraints and iteration methods. On the basis of design of geometric energy, transformation, and the corresponding nonlinear optimization numerical solution, the cloth deformation can be simulated more realistic. Especially, the geometric features about textile material effects can be simulated. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Joint Object Tracking Framework with Incremental and Multiple Instance Learning

    Page(s): 7 - 12
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (434 KB) |  | HTML iconHTML  

    When objects undergo large pose change, illumination variation or partial occlusion, most existed visual tracking algorithms tend to drift away from targets and even fail in tracking them. To address this issue, in this paper we propose an online algorithm by combining Incremental Learning (IL) and Multiple Instance Learning (MIL) based on local sparse representation for tracking an object in a video system. First, the target location is estimated using the online updated IL. Then, to decrease the visual drift due to the accumulation of errors while updating IL subspace with the first step results, a two-step object tracking method combining a static IL model with a dynamical MIL model is proposed. We utilize information of the static IL model involving the singular values, the Eigen template to avoid visual drift if there is no significant appearance change in the tracked objects. Otherwise, we use the dynamical MIL model to discriminate the target from the background when there is significant appearance change in the tracked objects. Experiments on some publicly available benchmarks of video sequences show that our proposed tracker is more robust and effective than others. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Algorithm of Geometric Fractal in Dynamic Geometry

    Page(s): 13 - 17
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (186 KB) |  | HTML iconHTML  

    Geometric Fractal is an important and interesting function of dynamic geometry, but it is a big system burden because geometric fractal has a significant negative impact on system performance. In this paper, we propose a new algorithm to improve the efficiency of geometric fractal in dynamic geometry system. The new algorithm treats lots of fractal graphics as a whole geometric object. This method can greatly reduce the computational load and complexity of generating and updating these fractal graphics runtime. It makes real-time calculation of geometric update possible and very rapid. The new algorithm was compared with Super Sketch Platform and The Geometer's Sketchpad, the most popular two dynamic geometry systems. The experimental results demonstrate the effectiveness of the proposed approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Intelligent Contour Tracking Algorithm in Binary Image

    Page(s): 18 - 22
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (169 KB) |  | HTML iconHTML  

    There are some problems in the traditional contour tracking algorithms based on direction to track boundary points. Such as low accuracy, low efficiency and easy to fall into the cycle of death. To solve these problems, this paper presents a new boundary contour tracking algorithm, it combines the boundary points' scanning direction and weights to determine the next boundary point, the algorithm can scan multiple connected region contours. Experiments show that our algorithm is not only very accurate, but also to get a complete and accurate target area outline. Especially for those contour feature points which distributed complicated area, it has better reflect superiority of the algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Method for Parsing Structures of Business Flow Diagram

    Page(s): 23 - 27
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (173 KB) |  | HTML iconHTML  

    In many business domain, flow diagrams play more and more important roles with which to represent commercial operation process. Many professional persons promote capability of decisions by means of this graphical descriptive tool. One of important issues is that given a diagram how to obtain the similar peer ones in repository or rank them according to designed algorithms. In this paper, we introduce a novel metric algorithm. Compared to previews methods, we focus not only on conventional semantic or syntactic similarity, but also on the nodes order in entire diagram hierarchical relationship. By precisely studying hundreds of diagrams, we conclude that node's layer order affect the similarity between two diagrams in some fields, such as business diagrams. We integrated layer order weight value and texts information embedded in the node into the flow diagram similarity measure system. Experimental results show that our algorithm is valid and efficient especially when considering layer orders. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Depth Map Generation Method Based on K-means Clustering

    Page(s): 28 - 32
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (255 KB) |  | HTML iconHTML  

    In this paper, we propose a novel depth map generation method. After a series of pre-treatment process, image quality capture and bilateral filtering, K-means clustering method has been used for classification of background and front objects. Then the depth map could be generated directly depend on the predeterminate model which is given a forehand, finally the correct depth map can be vividly created base on the layer Stratifying. The experiment result shows that the depth map directly represent the depth information and also earn good subjective evaluation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Distortion-free Data Hiding Scheme for High Dynamic Range Images

    Page(s): 33 - 38
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (226 KB) |  | HTML iconHTML  

    Information hiding has become an interesting topic that is arousing more and more attention. In 2011, Yu and Wu proposed a novel, distortion-free, information-hiding method based on the radiance format's diversity expression for high dynamic range (HDR) images. In this paper, we propose a segment-based method that makes it possible to use all different expressions of every pixel's radiance format to hide information, thereby further improving the performance of Yu and Wu's scheme. The experimental results indicated that the proposed scheme did, indeed, outperforms Yu and Wu's scheme in terms of hiding capacity and security for HDR images. In addition, the proposed scheme has more flexibility due to the flexibility of the segment size. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Non-linear Method of Automatic Video Scratch Removal

    Page(s): 39 - 45
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1418 KB) |  | HTML iconHTML  

    Video in painting is an important topic in digital image processing. Old age, repeat play and improper preservation always deteriorate the film, dust and mechanical operations produce artifacts like scratches and blotches. This paper presents an automatic scratch detection and removal approach. An accurate wavelet method is introduced to automatically detect the scraches and a new nonlinear continued fraction method dealing with both spatical and temporal information around the scratch is investigated in the restoration stage. In our experiment results, we show that our scheme not only obtains more accurate detection of scratches, but also gives better video quality. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Partial Differential Equation Method Based on Image Features and Its Applications in Denoising

    Page(s): 46 - 51
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (393 KB) |  | HTML iconHTML  

    In this paper a novel denoising algorithm based on partial differential equation variational approach is proposed. The proposed algorithm is obtained by weighted combinations of the an isotropic diffusion model and total variation model. Experimental results show that our new approach is more efficient in image denoising than both an isotropic diffusion and total variation in terms of preserving edges information and texture features. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Scene Division Method for Overlapping Splicing in Multi-channel Display

    Page(s): 52 - 56
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (269 KB) |  | HTML iconHTML  

    Multi-channel display technology is widely applied. However, there are still deformation and inconformity problems in displaying fusion areas between the adjacent channels. This paper proposes a new scene division method based on projection matrix, which makes the projection planes of each node staying on the same plane, ensuring the consistency of display. We do some experiments using our method and compare the results with the existing method-the scene division based on view matrix. The experiments show that our method is a more proper way to solve the problem of deformation in the fusion areas. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Abstraction for Static and Dynamic Images Based on Visual Saliency

    Page(s): 57 - 62
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1497 KB) |  | HTML iconHTML  

    Reliable estimation of visual perception reflects understanding of the meaningful structure in an image. The paper describes a complete abstraction framework for static and dynamic images that explicitly responds to this goal, stylizes the corresponding salient and non-salient part differently by an edge preserving filter at a time while keep harmonious transition between the two parts. First, this paper introduces an automatic salient object segmentation algorithm to distinguish salient regions, and it is a saliency computation based local spatial neighbors. Taking into account the actual needs, the paper provides an interactive technology, this can be convenient for specifying image salient structure information on purpose. Based on the generated salient information mask, the paper then uses single-scale an isotropic filter to process the salient part, and use multi-scale an isotropic filter to process the non-salient part so that can implement a strong abstraction effect. Proposed method generates a kind of image and video abstraction that it represents a preferable visual effect. Experiments show that our algorithm could get the desired effect for processing a certain number of images and videos. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Action Recognition with Trajectory and Scene

    Page(s): 63 - 68
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (644 KB) |  | HTML iconHTML  

    Trajectory features have recently shown promising results to action recognition in video. Typically, they are extracted by tracking feature points with the KLT tracker or matching SIFT descriptors between frames. However, trajectory can be due to the action of interest, but also be caused by background or the camera motion. To overcome the problem, human detection is applied to roughly estimate of the location of the human in the video and segment video into Foreground/Background regions. In many cases, human actions can be identified not only by observing human body in motion, but also properties of the surrounding scene. In our work, we addresse the problem and propose an approach that integrates multiple features from scene and people. We evaluate our video description with a bag of-features model. We also present experimental results on two datasets with an increasing degree of difficulty and demonstrate significant improvements. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive Facial Expression Recognition Based on a Weighted Component and Global Features

    Page(s): 69 - 73
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (260 KB) |  | HTML iconHTML  

    An adaptive facial expression recognition method based on component and global features is presented in this paper. The facial component features are highlighted for purpose of improving facial expression percent correct rate. Firstly, eyebrows, eyes, nose and mouth are divided from a facial expression image and then the component features would be gotten from these organ images which are processed by Gabor wavelets. The weighted adaptive algorithm would be used to calculate the component feature weights, the weighted component features fuse with the global feature to get a feature fusion matrix. Finally, Weighted Principal Component Analysis (WPCA) and Fisher Linear Discriminant (FLD) methods are used to reduce dimensions and classify facial expression. Experimental results show that the algorithm proposed in this paper has much more accurate recognition rate compared with the global Gabor wavelets, PCA and FLD integrated algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive Particle Size Setting and Normal Calculation Methods in Fluid Rendering

    Page(s): 74 - 79
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (667 KB) |  | HTML iconHTML  

    In this paper, we present an adaptive particle size setting method in Lagrangian-approach based screen space splatting algorithm in real-time fluid rendering. The particle radius will be adjusted according to its Weber number and local density in the rendering process so that a large radius of peaceful fluid particle can help to eliminate a bumpy surface artifact, and a small radius can prevent obviously spherical shapes of particles in splash. We also propose an adaptive normal calculation method to avoid the numerical calculation errors in normal computation process. An adaptive sampling interval is set in accordance with the viewing distance from camera to the fluid so that fuzzy edges or double image effect in a fixed sampling interval normal computation process could be prevented. Both of the two approaches introduced in this paper take only small amount of computing time and will have little impact on the time consuming property of a real-time fluid rendering application. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Algorithm of Image Reconstruction Based on Rational Interpolation with Rectangle-Hole Structure

    Page(s): 80 - 83
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (153 KB) |  | HTML iconHTML  

    Digital image reconstruction is an important problem in Digital image application, the credibility of near damaged points is very important to image reconstruction. This paper presents a method for digital image reconstruction, which is built up by the numerical values of the gray of nearer points. The method transfers image reconstruction problem with the damaged pixel holes of the rectangular grid to rational interpolation problem. Using the rational interpolation improved in the paper, the method can improve the credibility of near damaged points. Originally, When the line or the column has the damaged pixel points which need to reconstruction, the classical method of Newton-Thiele rational interpolation can't use the numerical values of the gray of the pixel points of the line or the column. The rational interpolation method improved in the paper can avoid this phenomenon. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Efficient Prediction-Based Power Saving Mechanism for Mobile Devices

    Page(s): 84 - 89
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (488 KB) |  | HTML iconHTML  

    In order to reduce the power consumption of a mobile station and the air interface resources utilization of serving base stations, IEEE802.16e introduced the sleep mode during which a mobile station stops its normal service. By predicting the next downlink inter-packet arrival time, a novel efficient power saving mechanism (PSCI-ED) is proposed in this paper to improve both energy efficiency and packet delay. Simulation results reveal that the proposed mechanism can achieve much better results on reducing the power consumption and the packet delay due to the consideration of the traffic characteristics and rate changes, compared with the sleep mode algorithm recommended by IEEE802.16e. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.