By Topic

Computer Vision, Graphics & Image Processing, 2008. ICVGIP '08. Sixth Indian Conference on

Date 16-19 Dec. 2008

Filter Results

Displaying Results 1 - 25 of 111
  • [Front cover]

    Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (168 KB)  
    Freely Available from IEEE
  • [Title page i]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (15 KB)  
    Freely Available from IEEE
  • [Title page iii]

    Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (43 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (43 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): v - xii
    Save to Project icon | Request Permissions | PDF file iconPDF (176 KB)  
    Freely Available from IEEE
  • Message from the General Co-chairs

    Page(s): xiii
    Save to Project icon | Request Permissions | PDF file iconPDF (32 KB)  
    Freely Available from IEEE
  • Message from the Program Co-chairs

    Page(s): xiv - xv
    Save to Project icon | Request Permissions | PDF file iconPDF (36 KB)  
    Freely Available from IEEE
  • Committee Members

    Page(s): xvi
    Save to Project icon | Request Permissions | PDF file iconPDF (32 KB)  
    Freely Available from IEEE
  • Reviewers

    Page(s): xvii - xviii
    Save to Project icon | Request Permissions | PDF file iconPDF (114 KB)  
    Freely Available from IEEE
  • Technical Program Committee

    Page(s): xix
    Save to Project icon | Request Permissions | PDF file iconPDF (106 KB)  
    Freely Available from IEEE
  • Robust Watermarking Scheme Based on Multiresolution Fractional Fourier Transform

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1083 KB) |  | HTML iconHTML  

    In this paper, a new robust watermarking scheme is proposed in multiresolution fractional Fourier transform domain using singular value decomposition. The watermark is embedded in the high frequency sub-band of the host image at coarsest level. Although the schemes based on SVD are robust but fail under ambiguity attacks. In this attack, both the owner and attacker can extract their watermark from the watermarked image. To prevent ambiguity, the normalized mass matrix is formed and embedded in the host image. In extraction, normalized mass matrix is extracted first and compared with original one. If the similarity is found then the singular values are extracted to construct the watermark. Experimental evaluation demonstrates that the proposed scheme is able to withstand a variety of attacks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Adaptive Clustering Based Non-linear Filter for the Restoration of Impulse Corrupted Digital Images

    Page(s): 9 - 16
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (677 KB) |  | HTML iconHTML  

    The paper proposes a 2D impulse filtering algorithm for the restoration of salt & pepper impulse corrupted digital images. The algorithm incorporates a hard-C means clustering stage to facilitate pixel classification in the impulse detection phase and an efficient adaptive filtering scheme in the restoration phase. The impulse detection scheme of the algorithm avoids mis-classification of signals as impulses by clearly distinguishing the high frequency image details from impulse corrupted pixels. The adaptive restoration phase identifies the most suitable signal restorer from among the true signals of a reliable neighborhood. Experimental results in terms of subjective assessment and objective metrics favor the proposed algorithm at all impulse noise levels over many top-ranking filters. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Impulse Noise Removal from Color Images with Hopfield Neural Network and Improved Vector Median Filter

    Page(s): 17 - 24
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1034 KB) |  | HTML iconHTML  

    In this paper, a novel and effective method for impulse noise removal in corrupted color images is discussed. The new method consists of two phases. The first phase is a noise detection phase where a modified Hopfield neural network is used to detect impulse noise pixels. The second is a noise filtering phase where the disadvantage of taking vector median in a single color space is addressed and a new algorithm based on performing vector median first in RGB space and then in HSI space is presented. The results of simulations performed on a set of standard test images on a wide range of noise corruption show that the proposed method is capable of detecting all the impulse noise pixels with almost zero false positive rates and removes noise while retaining finer image details. It outperforms the standard procedures and is yet simple and suitable for real time applications. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image Denoising Using Matched Biorthogonal Wavelets

    Page(s): 25 - 32
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1415 KB) |  | HTML iconHTML  

    Current denoising techniques use the classical ortho normal wavelets for decomposition of an image corrupted with additive white Gaussian noise, upon which various thresholding strategies are built. The use of available biorthogonal wavelets in image denoising is less common because of their poor performance. In this paper, we present a method to design image-matched biorthogonal wavelet bases and report on their potential for denoising. We have conducted experiments on various image datasets namely Natural, Satellite and Medical with the designed wavelets using two existing thresholding strategies. Test results from comparing the performance of matched and fixed biorthogonal wavelets show an average improvement of 35% in MSE for low SNR values (0 to 18 db) in every dataset. This improvement was also seen in the PSNR and visual comparisons. This points to the importance of matching when using wavelet-based denoising. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Edge Detectors Based Anisotropic Diffusion for Enhancement of Digital Images

    Page(s): 33 - 38
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2744 KB) |  | HTML iconHTML  

    Using the edge detection techniques we propose a new enhancement scheme for noisy digital images. This uses inhomogeneous anisotropic diffusion scheme via the edge indicator provided by well known edge detection methods. Addition of a fidelity term facilitates the proposed scheme to remove the noise while preserving edges. This method is general in the sense that it can be incorporated into any of the nonlinear anisotropic diffusion methods. Numerical results show the promise of this hybrid technique on real and noisy images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Audio-Visual Person Authentication with Multiple Visualized-Speech Features and Multiple Face Profiles

    Page(s): 39 - 46
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1244 KB) |  | HTML iconHTML  

    We present an Audio-visual person authentication system which extracts several novel ldquovisualized-speech-featuresrdquo (VSF) from the spoken-password and multiple face profiles using a simple user-interface and combine these features to deliver high performance and resilience against imposter attacks. The spoken password is converted to a string of images formed by several visualized speech features. A compressed form of these VSFs preserves speaker identity in a compact manner. Simulation results on an in-house 210-user AV-user-ID database collected with wide variations of users in real-life office environments demonstrate separable distributions of client and imposter scores (0% EER), while offering low storage and computational complexities compared to conventional AV user-recognition methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visibility Cuts: A System for Rendering Dynamic Virtual Environments

    Page(s): 47 - 54
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (957 KB) |  | HTML iconHTML  

    The subject of occlusion culling of large 3D environments has received substantial contribution. However the major amount of research into the area has focussed on occlusion culling of static scenes using spatial partitioning. The primary aim of all these schemes is to minimize the load on the GPU by reducing the number of primitives to be rendered. We present an efficient algorithm for visibility culling that supports static and dynamic scenes with equal ease with significant performance improvements over existing schemes. For a given camera position the status of the object nodes in an object hierarchy can be seen as a visibility cut, the nodes of which are either outside the view frustum, or hidden or visible. We propose an efficient update scheme of this visibility cut while processing each frame, taking full advantage of the object hierarchy with spatial and temporal coherency. The whole scene walk through is modelled as a discrete event simulation where every change generates an event scheduled for that particular frame. For occlusion culling, we employ occlusion queries which helps the system to be output sensitive. The system supports transparency of entities without a major performance hit. We propose a scheme to select the level of detail of an object based on the results of occlusion queries. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-scale Method for Adaptive Mesh Editing Based on Rigidity Estimation

    Page(s): 55 - 62
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1114 KB) |  | HTML iconHTML  

    We present a multi-scale approach for direct manipulation of mesh models based on pre-estimated rigidity. Our method enhances space deformation by constructing a novel deformable structure with several layers of deformation graphs which have different densities of control nodes. An appropriate deformation graph is dynamically chosen according to the handle configuration. Such handle-aware strategy, together with special treatment for graph nodes, brings great improvement on both editing effect and performance. We demonstrate how to obtain a reduced deformable model by generating lattice structure and how to estimate the rigidity of mesh surface. Based on the rigidity analysis, we adjust the granularity of the computation which helps to speed the solving process. The experimental results show that our method preserves detailed features well and provides fast design of pleasing poses as the complexity of computing is confined within a limited range. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Explosion Simulation Using Compressible Fluids

    Page(s): 63 - 70
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1351 KB) |  | HTML iconHTML  

    We propose a novel physically based method to simulate explosions and other compressible fluid phenomena. The method uses compressible Navier Stokes equations for modeling the explosion with a Semi-Lagrangian integration method. The proposed integration method addresses the issues of stability and larger timesteps. This is achieved by modifying the Semi-Lagrangian method to reduce dissipation and increase accuracy, using improved interpolation and an error correction method. The proposed method allows the rendering of related phenomena like a fireball, dust and smoke clouds, and the simulation of solid interaction - like rigid fracture and rigid body simulation. Our method is flexible enough to afford substantial artistic control over the behavior of the explosion. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Algebraic Splats Representation for Point Based Models

    Page(s): 71 - 78
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2241 KB) |  | HTML iconHTML  

    The primitives of point-based representations are independent but are rendered using surfels, which approximate the immediate neighborhood of each point linearly. A large number of surfels are needed to convey the exact shape. Higher-order approximations of the local neighborhood have the potential to represent the shape using fewer primitives, simultaneously achieving higher rendering speeds. In this paper, we propose algebraic splats as a basic primitive of representation for point based models. An algebraic splat based representation can be computed using a moving least squares procedure. We specifically study low order polynomial splats in this paper. Quadratic and cubic splats provide good quality and high rendering speed using far fewer primitives on a wide range of models. They can also be rendered fast using ray tracing on modern GPUs. We also present an algorithm to construct a representation of a model with a user-specified number of primitives. Our method to generates a hole-free representation parametrized by a smoothing radius. The hole-free representation reduces the number of primitives needed by a factor 20 to 30 on most models and by a factor of over 100 on dense models like David with little or no drop in visual quality. We also present a two-pass GPU algorithm that ray-traces the algebraic splats and blends them using a Gaussian weighting scheme for smooth appearance. We are able to render models like David at upwards of 200 fps on a commodity GPU using algebraic splats. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Scalable Projective Bundle Adjustment Algorithm using the L infinity Norm

    Page(s): 79 - 86
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (407 KB) |  | HTML iconHTML  

    The traditional bundle adjustment algorithm for structure from motion problem has a computational complexity of O((m+n)3) per iteration and memory requirement of O(mn(m+n)), where m is the number of cameras and n is the number of structure points. The sparse version of bundle adjustment has a computational complexity of O(m3+mn) per iteration and memory requirement of O(mn). Here we propose an algorithm that has a computational complexity of O(mn(radicm+radicn)) per iteration and memory requirement of O(max(m,n)). The proposed algorithm is based on minimizing the Linfin norm of reprojection error. It alternately estimates the camera and structure parameters, thus reducing the potentially large scale optimization problem to many small scale subproblems each of which is a quasi-convex optimization problem and hence can be solved globally. Experiments using synthetic and real data show that the proposed algorithm gives good performance in terms of minimizing the reprojection error and also has a good convergence rate. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Frequency Domain Visual Servoing Using Planar Contours

    Page(s): 87 - 94
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (663 KB) |  | HTML iconHTML  

    Fourier domain methods have had a long association with geometric vision. In this paper, we introduce Fourier domain methods into the field of visual servoing for the first time. We show how different properties of Fourier transforms may be used to address specific issues in traditional visual servoing methods, giving rise to algorithms that are more flexible. Specifically, we demonstrate how Fourier analysis may be used to obtain straight camera paths in the Cartesian space, do path following and correspondence-less visual servoing. Most importantly, by introducing Fourier techniques, we set a framework into which robust Fourier-based geometry processing algorithms may be incorporated to address the various issues in servoing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Monocular Depth by Nonlinear Diffusion

    Page(s): 95 - 102
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (664 KB) |  | HTML iconHTML  

    Following the phenomenological approach of gestaltists, sparse monocular depth cues such as T- and X-junctions and the local convexity are crucial to identify the shape and depth relationships of depicted objects. According to Kanizsa, mechanisms called a modal and modal completion permit to transform these local relative depth cues into a global depth reconstruction. In this paper, we propose a mathematical and computational translation of gestalt depth perception theory, from the detection of local depth cues to their synthesis into a consistent global depth perception. The detection of local depth cues is built on the response of a line segment detector (LSD), which works in a linear time relative to the image size without any parameter tuning. The depth synthesis process is based on the use of a nonlinear iterative filter which is asymptotically equivalent to the Perona-Malik partial differential equation (PDE). Experimental results are shown on several real images and demonstrate that this simple approach can account a variety of phenomena such as visual completion, transparency and self-occlusion. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptation and Learning for Image Based Navigation

    Page(s): 103 - 110
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (768 KB) |  | HTML iconHTML  

    Image based methods are a new approach for solving problems in mobile robotics. Instead of building a metric (3D) model of the environment, these methods work directly in the sensor (image) space. The environment is represented as a topological graph in which each node contains an image taken at some pose in the workspace, and edges connect poses between which a simple path exists. This type of representation is highly scalable and is also well suited to handle the data association problems that effect metric model based methods. In this paper, we present an efficient, adaptive method for qualitative localization using content based image retrieval techniques. In addition, we demonstrate an algorithm which can convert this topological graph into a metric model of the environment by incorporating information about loop closures. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning Feature Trajectories Using Gabor Filter Bank for Human Activity Segmentation and Recognition

    Page(s): 111 - 118
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (497 KB) |  | HTML iconHTML  

    We describe a novel method for human activity segmentation and interpretation in surveillance applications based on Gabor filter-bank features. A complex human activity is modeled as a sequence of elementary human actions like walking, running, jogging, boxing, hand-waving etc. Since human silhouette can be modeled by a set of rectangles, the elementary human actions can be modeled as a sequence of a set of rectangles with different orientations and scales. The activity segmentation is based on Gabor filter-bank features and normalized spectral clustering. The feature trajectories of an action category are learnt from training example videos using dynamic time warping. The combined segmentation and the recognition processes are very efficient as both the algorithms share the same framework and Gabor features computed for the former can be used for the later. We have also proposed a simple shadow detection technique to extract good silhouette which is necessary for good accuracy of an action recognition technique. View full abstract»

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