18th International Conference on Pattern Recognition (ICPR'06)

20-24 Aug. 2006

Go

Filter Results

Displaying Results 1 - 25 of 253
  • 18th International Conference on Pattern Recognition - Cover

    Publication Year: 2006, Page(s): c1
    Request permission for commercial reuse | |PDF file iconPDF (354 KB)
    Freely Available from IEEE
  • 18th International Conference on Pattern Recognition - Title

    Publication Year: 2006, Page(s):i - iii
    Request permission for commercial reuse | |PDF file iconPDF (107 KB)
    Freely Available from IEEE
  • 18th International Conference on Pattern Recognition - Copyright

    Publication Year: 2006, Page(s): iv
    Request permission for commercial reuse | |PDF file iconPDF (91 KB)
    Freely Available from IEEE
  • 18th International Conference on Pattern Recognition - Table of contents

    Publication Year: 2006, Page(s):v - xxiv
    Request permission for commercial reuse | |PDF file iconPDF (174 KB)
    Freely Available from IEEE
  • Message from the ICPR2006 General Co-Chairs

    Publication Year: 2006, Page(s): xxv
    Request permission for commercial reuse | |PDF file iconPDF (34 KB) | HTML iconHTML
    Freely Available from IEEE
  • Message from the President of IAPR

    Publication Year: 2006, Page(s): xxvi
    Request permission for commercial reuse | |PDF file iconPDF (29 KB) | HTML iconHTML
    Freely Available from IEEE
  • ICPR2006 Organizing Committee

    Publication Year: 2006, Page(s): xxvii
    Request permission for commercial reuse | |PDF file iconPDF (26 KB)
    Freely Available from IEEE
  • ICPR2006 Technical Chairs

    Publication Year: 2006, Page(s): xxviii
    Request permission for commercial reuse | |PDF file iconPDF (25 KB) | HTML iconHTML
    Freely Available from IEEE
  • ICPR2006 Program Committee

    Publication Year: 2006, Page(s): xxix
    Request permission for commercial reuse | |PDF file iconPDF (41 KB)
    Freely Available from IEEE
  • ICPR2006 Additional Reviewers

    Publication Year: 2006, Page(s): xxxv
    Request permission for commercial reuse | |PDF file iconPDF (45 KB)
    Freely Available from IEEE
  • IAPR Member Societies and Members of the Governing Board

    Publication Year: 2006, Page(s): xxxvi
    Request permission for commercial reuse | |PDF file iconPDF (31 KB) | HTML iconHTML
    Freely Available from IEEE
  • IAPR Standing Committees

    Publication Year: 2006, Page(s): xxxvii
    Request permission for commercial reuse | |PDF file iconPDF (31 KB)
    Freely Available from IEEE
  • IAPR Technical Committees

    Publication Year: 2006, Page(s): xxxviii
    Request permission for commercial reuse | |PDF file iconPDF (33 KB)
    Freely Available from IEEE
  • Accurate 3D Scanning of Swaying Human Body Parts by One Projection Based on OIMP Technique

    Publication Year: 2006, Page(s):1 - 4
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (343 KB) | HTML iconHTML

    Three-dimensional (3D) shape measurement based on spatial pattern projection (coded structured light projection) technique has been used in practical applications. However, multiple pattern projection is required for the measurement, and so application to a swaying human body part is difficult. A new technique for measuring the 3D topography of swaying human body parts or a human face using optima... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of Building Roof Facets by Merging Aerial Images and 3D Lidar Data in a Hierarchical Segmentation Framework

    Publication Year: 2006, Page(s):5 - 8
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (513 KB) | HTML iconHTML

    We investigate in this paper an original methodology for detecting roof facets through the fusion of aerial images and lidar data (3D point cloud). Based on a hierarchical segmentation of the image, we define a cost function that manages the merging order of regions. It depends on both radio-metric similarities of two neighbouring regions as well as on extracted information from lidar data. Consid... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multimodal Range Image Segmentation by Curve Grouping

    Publication Year: 2006, Page(s):9 - 12
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (410 KB) | HTML iconHTML

    A fast range image segmentation method for scenes comprising general faced objects is introduced. The range segmentation is based on a recursive adaptive probabilistic detection of step discontinuities which are present at object face borders in mutually registered range and intensity data. Detected face outlines guides the subsequent region growing step where the neighbouring face curves are grou... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discontinuity-Based Simplification of Free Form Surface From a Range Image

    Publication Year: 2006, Page(s):13 - 16
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (172 KB) | HTML iconHTML

    This paper improves an existing method for more accurate simplification of free form surface represented as dense points. The main improvement lies in two aspects: one is the introduction of a novel transformation of curvatures, the other is to propose sampling points using both curvature information and curvature variation information. The experimental results based on real images show that the o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Flag Guided Integration of Multiple Registered Range Images

    Publication Year: 2006, Page(s):17 - 20
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (789 KB) | HTML iconHTML

    Integration of multiple registered range images finds applications in numerous areas. While most existing integration algorithms detect corresponding points between neighbouring views based on interpoint distances, we define in this paper corresponding area for each point and then carry out geometrical, rigidity, and orientation tests for the same purpose, not only reflecting the scanning nature o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive Feature Integration for Segmentation of 3D Data by Unsupervised Density Estimation

    Publication Year: 2006, Page(s):21 - 24
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (3967 KB) | HTML iconHTML

    In this paper, a novel unsupervised approach for the segmentation of unorganized 3D points sets is proposed. The method derives by the mean shift clustering paradigm devoted to separate the modes of a multimodal density by using a kernel-based technique. Here, the attention is focused on the selection of the kernel bandwidth which typically strongly affects the level of accuracy of the segmentatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast Synthesis of Dynamic Colour Textures

    Publication Year: 2006, Page(s):25 - 28
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (435 KB) | HTML iconHTML

    Textural appearance of many real word materials is not static but shows progress in time. If such a progress is spatially and temporally homogeneous these materials can be represented by means of dynamic texture (DT). DT modelling is a challenging problem which can add new quality into computer graphics applications. We propose a novel hybrid method for colour DTs modelling. The method is based on... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiscale Blob Features for Gray Scale, Rotation and Spatial Scale Invariant Texture Classification

    Publication Year: 2006, Page(s):29 - 32
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (158 KB) | HTML iconHTML

    This paper proposes to apply a series of flexible threshold planes to the textured image and then use the topological and geometrical attributes of the blobs in the obtained binary images to describe image texture. The proposed multiscale blob features (MBF) is invariant to linear gray-level scaling and rotation, and is insensitive to uniform spatial scaling. The experiment results show that MBF o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D Texture Classification Using the Belief Net of a Segmentation Tree

    Publication Year: 2006, Page(s):33 - 36
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (309 KB) | HTML iconHTML

    This paper presents a statistical approach to 3D texture classification from a single image obtained under unknown viewpoint and illumination. Unlike in prior work, in which texture primitives (textons) are defined in a filter-response space, and texture classes modeled by frequency histograms of these textons, we seek to extract and model geometric and photometric properties of image regions defi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-Validated and Spatially Coherent Clustering with Net-Structured MRF and Graph Cuts

    Publication Year: 2006, Page(s):37 - 40
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (632 KB) | HTML iconHTML

    Self-validation and efficient global optimization are two important objectives for feature space clustering. The Gibbs energy minimization of Markov random field (MRF) provides a general framework for the clustering problem. However, the large computational burden makes most MRF-based methods cannot efficiently achieve these two targets simultaneously. In this paper, we propose a fast clustering a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object localization/segmentation using generic shape priors

    Publication Year: 2006, Page(s):41 - 44
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (386 KB) | HTML iconHTML

    Generally object segmentation is an ill-posed problem. Approaches that use only plain image information will often fail. To overcome these limitations, prior knowledge (like information of the object contour) can be added to the segmentation process. In this paper, we present a novel generic shape model. We use the expertise from the field of object class recognition, namely a boundary-fragment-mo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Object-of-Interest segmentation from natural images

    Publication Year: 2006, Page(s):45 - 48
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (266 KB) | HTML iconHTML

    In this paper, we propose a novel OOI (object-of-interest) segmentation algorithm from natural images that is based on human attention and semantic region merging. To do this, we segment an image into regions and merge them as a semantic object. Then, we create an attention window based on saliency map and saliency points from an image. Within the AW, a support vector machine is used to select the... View full abstract»

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