상세정보

This volume presents the proceedings of the 10th International Conference on Computer Analysis of Images and Patterns (CAIP 2003). This conference - ries started about 18 years ago in Berlin. Initially, the conference served as a forum for meetings between scientists from Western- and Eastern-bloc co- tries. Nowadays, the conference attracts participants from all over the world. The conference gives equal weight to posters and oral presentations, and the selected presentation mode is based on the most appropriate communication medium. The programme follows a single-track format, rather than parallel s- sions. Non-overlapping oral and poster sessions ensure that all attendees have the opportunity to interact personally with presenters. As for the numbers, we received a total of 160 submissions. All papers were reviewed by two to three members of the Programme Committee. The ?nal - lection was carried out by the Conference Chairs. Out of the 160 papers, 42 were selected for oral presentation and 52 as posters. At this point, we wish to thank the Programme Committee and additional referees for their timely and high-quality reviews. The paper submission and review procedure was carried out electronically. We thank Marcin Morg´ os from Scalar?IT Solutions for p- viding us with the Web-based participant registration system. We also thank the invited speakers Nicholas Ayache, John Daugman, and Dariu Gavrila, for kindly accepting our invitation.

This volume presents the proceedings of the 10th International Conference on Computer Analysis of Images and Patterns (CAIP 2003). This conference - ries started about 18 years ago in Berlin. Initially, the conference served as a forum for meetings between scientists from Western- and Eastern-bloc co- tries. Nowadays, the conference attracts participants from all over the world. The conference gives equal weight to posters and oral presentations, and the selected presentation mode is based on the most appropriate communication medium. The programme follows a single-track format, rather than parallel s- sions. Non-overlapping oral and poster sessions ensure that all attendees have the opportunity to interact personally with presenters. As for the numbers, we received a total of 160 submissions. All papers were reviewed by two to three members of the Programme Committee. The ?nal - lection was carried out by the Conference Chairs. Out of the 160 papers, 42 were selected for oral presentation and 52 as posters. At this point, we wish to thank the Programme Committee and additional referees for their timely and high-quality reviews. The paper submission and review procedure was carried out electronically. We thank Marcin Morg´ os from Scalar?IT Solutions for p- viding us with the Web-based participant registration system. We also thank the invited speakers Nicholas Ayache, John Daugman, and Dariu Gavrila, for kindly accepting our invitation.

정보제공 :

Analysis and Understanding.- On Design and Applications of Cylindrical Panoramas.- Finding the Symmetry Axis of a Perspectively Projected Plane Curve.- Representing Orientation in n-Dimensional Spaces.- Docking of Polygons Using Boundary Descriptor.- Area and Moment Computation for Objects with a Closed Spline Boundary.- Construction of Complete and Independent Systems of Rotation Moment Invariants.- A Structural Framework for Assembly Modeling and Recognition.- Simple Points in 2D and 3D Binary Images.- Viewpoint Selection - Planning Optimal Sequences of Views for Object Recognition.- Epipolar Plane Images as a Tool to Seek Correspondences in a Dense Sequence.- Computing Neck-Shaft Angle of Femur for X-Ray Fracture Detection.- Illuminance Flow.- Rough Surface Correction and Re-illumination Using the Modified Beckmann Model.- Towards a Real Time Panoramic Depth Sensor.- Depth Recovery from Noisy Gradient Vector Fields Using Regularization.- Bunch Sampling for Fast Texture Synthesis.- Automatic Detection of Specular Reflectance in Colour Images Using the MS Diagram.- Skeletonization of Character Based on Wavelet Transform.- A New Sharpness Measure Based on Gaussian Lines and Edges.- Video.- A New Tracking Technique: Object Tracking and Identification from Motion.- Evaluation of an Adaptive Composite Gaussian Model in Video Surveillance.- Low Complexity Motion Estimation Based on Spatio-Temporal Correlations and Direction of Motion Vectors.- Stereo System for Tracking Moving Object Using Log-Polar Transformation and Zero Disparity Filtering.- Monte Carlo Visual Tracking Using Color Histograms and a Spatially Weighted Oriented Hausdorff Measure.- Object Classification and Tracking in Video Surveillance.- Video Retrieval by Context-Based Interpretation of Time-to-Collision Descriptors.- Trajectory Estimation Based on Globally Consistent Homography.- Real-Time Optic Flow Computation with Variational Methods.- Adaptive Stabilization of Vibration on Archive Films.- A Genetic Algorithm with Automatic Parameter Adaptation for Video Segmentation.- Two-Step Unassisted Video Segmentation Using Fast Marching Method.- Video Mosaicking for Arbitrary Scene Imaged under Arbitrary Camera Motion.- Multi-loop Scalable MPEG-2 Video Coders.- Multimedia Simulation of Colour Blindness and Colour Enhancement Assisted Colour Blindness.- Coefficient Partitioning Scanning Order Wavelet Packet Algorithm for Satellite Images.- Segmentation.- Support Vector Machines for Road Extraction from Remotely Sensed Images.- Fingerprint Matching Based on Directional Image Feature in Polar Coordinate System.- Efficient Algorithm of Eye Image Check for Robust Iris Recognition System.- Recognition of Car License Plate by Using Dynamical Thresholding Method and Enhanced Neural Networks.- Generalizing the Active Shape Model by Integrating Structural Knowledge to Recognize Hand Drawn Sketches.- Automatic Segmentation of Diatom Images.- Topological Active Volumes.- Genetic Algorithm to Set Active Contour.- Unsupervised Segmentation Incorporating Colour, Texture, and Motion.- Image Segmentation Based on Transformations with Reconstruction Criteria.- Gaussian-Weighted Moving-Window Robust Automatic Threshold Selection.- Shape.- Shape from Photometric Stereo and Contours.- A Fast Algorithm for Constructing Parameterizations of Three-Dimensional Simply Connected Digital Objects.- A Visual Comparison of Shape Descriptors Using Multi-Dimensional Scaling.- Part-Based Shape Recognition Using Gradient Vector Field Histograms.- Measuring Sigmoidality.- Optimization and Tracking of Polygon Vertices for Shape Coding.- Classification.- Greedy Algorithm for a Training Set Reduction in the Kernel Methods.- Learning Statistical Structure for Object Detection.- Blind Source Separation Using Variational Expectation-Maximization Algorithm.- Graph Clustering with Tree-Unions.- Writer Style from Oriented Edge Fragments.- Font Classification Using NMF.- Arabic Character Recognition Using Str

정보제공 :