Computer Vision, Graphics and Image Processing: 5th Indian Conference, Icvgip 2006, Madurai, India, December 13-16, 2006, Proceedings

ISBN-13: 9783540683018 / Angielski / Miękka / 2006 / 966 str.

Prem Kalra

Opis

The Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) is a forum bringing together researchers and practitioners in these related areas, coming from national and international academic institutes, from government research and development laboratories, and from industry. ICVGIP has been held biannually since its inception in 1998, attracting more participants every year, including international participants. The proceedings of ICVGIP 2006, published in Springer's series Lecture Notes in Computer Science, comprise 85 papers that were selected for presentation from 284 papers, which were submitted from all over the world. Twenty-nine papers were oral presentations, and 56 papers were presented as posters. For the first time in ICVGIP, the review process was double-blind as common in the major international conferences. Each submitted paper was assigned at least three reviewers who are experts in the relevant area. It was difficult to select such a few papers, as there were many other deserving, but those could not be accommodated.

Spis treści

Image Restoration and Super-Resolution.- Edge Model Based High Resolution Image Generation.- Greyscale Photograph Geometry Informed by Dodging and Burning.- A Discontinuity Adaptive Method for Super-Resolution of License Plates.- Explicit Nonflat Time Evolution for PDE-Based Image Restoration.- Decimation Estimation and Super-Resolution Using Zoomed Observations.- Segmentation and Classification.- Description of Interest Regions with Center-Symmetric Local Binary Patterns.- An Automatic Image Segmentation Technique Based on Pseudo-convex Hull.- Single-Histogram Class Models for Image Segmentation.- Learning Class-Specific Edges for Object Detection and Segmentation.- Nonparametric Neural Network Model Based on Rough-Fuzzy Membership Function for Classification of Remotely Sensed Images.- Aggregation Pheromone Density Based Image Segmentation.- Remote Sensing Image Classification: A Neuro-fuzzy MCS Approach.- A Hierarchical Approach to Landform Classification of Satellite Images Using a Fusion Strategy.- Image Filtering/Processing.- An Improved ‘Gas of Circles’ Higher-Order Active Contour Model and Its Application to Tree Crown Extraction.- A New Extension of Kalman Filter to Non-Gaussian Priors.- A Computational Model for Boundary Detection.- Speckle Reduction in Images with WEAD and WECD.- Image Filtering in the Compressed Domain.- Significant Pixel Watermarking Using Human Visual System Model in Wavelet Domain.- Early Vision and Image Processing: Evidences Favouring a Dynamic Receptive Field Model.- An Alternative Curvature Measure for Topographic Feature Detection.- Nonlinear Enhancement of Extremely High Contrast Images for Visibility Improvement.- Graphics and Visualization.- Culling an Object Hierarchy to a Frustum Hierarchy.- Secondary and Tertiary Structural Fold Elucidation from 3D EM Maps of Macromolecules.- Real-Time Streaming and Rendering of Terrains.- Ad-Hoc Multi-planar Projector Displays.- PACE: Polygonal Approximation of Thick Digital Curves Using Cellular Envelope.- Texture Guided Realtime Painterly Rendering of Geometric Models.- Real-Time Camera Walks Using Light Fields.- Massive Autonomous Characters: Animation and Interaction.- Clickstream Visualization Based on Usage Patterns.- GPU Objects.- Progressive Decomposition of Point Clouds Without Local Planes.- Video Analysis.- Task Specific Factors for Video Characterization.- Video Shot Boundary Detection Algorithm.- Modeling of Echocardiogram Video Based on Views and States.- Video Completion for Indoor Scenes.- Reducing False Positives in Video Shot Detection Using Learning Techniques.- Text Driven Temporal Segmentation of Cricket Videos.- Tracking and Surveillance.- Learning Efficient Linear Predictors for Motion Estimation.- Object Localization by Subspace Clustering of Local Descriptors.- Integrated Tracking and Recognition of Human Activities in Shape Space.- Inverse Composition for Multi-kernel Tracking.- Tracking Facial Features Using Mixture of Point Distribution Models.- Improved Kernel-Based Object Tracking Under Occluded Scenarios.- Spatio-temporal Discovery: Appearance + Behavior = Agent.- Fusion of Thermal Infrared and Visible Spectrum Video for Robust Surveillance.- Dynamic Events as Mixtures of Spatial and Temporal Features.- Discriminative Actions for Recognising Events.- Recognition (Face/Gesture/Object).- Continuous Hand Gesture Segmentation and Co-articulation Detection.- OBJCUT for Face Detection.- Selection of Wavelet Subbands Using Genetic Algorithm for Face Recognition.- Object Recognition Using Reflex Fuzzy Min-Max Neural Network with Floating Neurons.- Extended Fitting Methods of Active Shape Model for the Location of Facial Feature Points.- Pose Invariant Generic Object Recognition with Orthogonal Axis Manifolds in Linear Subspace.- A Profilometric Approach to 3D Face Reconstruction and Its Application to Face Recognition.- Face Recognition Technique Using Symbolic Linear Discriminant Analysis Method.- Two-Dimensional Optimal Transform for Appearance Based Object Recognition.- Computing Eigen Space from Limited Number of Views for Recognition.- Face Recognition from Images with High Pose Variations by Transform Vector Quantization.- Compression.- An Integrated Approach for Downscaling MPEG Video.- DCT Domain Transcoding of H.264/AVC Video into MPEG-2 Video.- Adaptive Scalable Wavelet Difference Reduction Method for Efficient Image Transmission.- GAP-RBF Based NR Image Quality Measurement for JPEG Coded Images.- A Novel Error Resilient Temporal Adjacency Based Adaptive Multiple State Video Coding over Error Prone Channels.- Adaptive Data Hiding in Compressed Video Domain.- Document Processing/OCR.- Learning Segmentation of Documents with Complex Scripts.- Machine Learning for Signature Verification.- Text Localization and Extraction from Complex Gray Images.- OCR of Printed Telugu Text with High Recognition Accuracies.- A MLP Classifier for Both Printed and Handwritten Bangla Numeral Recognition.- Recognition of Off-Line Handwritten Devnagari Characters Using Quadratic Classifier.- On Recognition of Handwritten Bangla Characters.- Evaluation Framework for Video OCR.- Enabling Search over Large Collections of Telugu Document Images – An Automatic Annotation Based Approach.- Content Based Image Retrieval.- Retrieving Images for Remote Sensing Applications.- Content-Based Image Retrieval Using Wavelet Packets and Fuzzy Spatial Relations.- Content Based Image Retrieval Using Region Labelling.- Stereo/Camera Calibration.- Using Strong Shape Priors for Stereo.- An Efficient Adaptive Window Based Disparity Map Computation Algorithm by Dense Two Frame Stereo Correspondence.- Robust Homography-Based Control for Camera Positioning in Piecewise Planar Environments.- Direct Estimation of Homogeneous Vectors: An Ill-Solved Problem in Computer Vision.- Biometrics.- Fingerprint Matching Based on Octantal Nearest-Neighbor Structure and Core Points.- Dempster-Shafer Theory Based Classifier Fusion for Improved Fingerprint Verification Performance.- Fingerprint Image Enhancement Using Decimation Free Directional Adaptive Mean Filtering.