图像分析与识别

　　The two-volume set LNCS 3211/3212 constitutes the refereed proceedings of the International Conference on Image Analysis and Recognition， ICIAR 2004， held in Porto， Portugal， in September/October 2004.The 210 revised papers presented were carefully reviewed and selected from 316 full papers submitted. The papers are organized in topical sections on image segmentation， image processing and analysis， image analysis and synthesis， image and video coding， shape and matching， image de*ion and recognition， video processing and analysis， 3D imaging， image retrieval and indexing， morphology， biomedical applications， document processing， color analysis， texture analysis， motion analysis， surveillance and remote sensing， tracking， face detection and recognition， security systems， visual inspection.

暂缺《图像分析与识别》作者简介

Pattern Recognition for Image Analysis
Using Local Integral Invariants for Object Recognition in　Complex Scenes
　Sharing Visual Features for Animal Categorization: An Empirical　Study
　Object Categorization Using Kernels Combining Graphs and　Histograms of Gradients
　Alternative Approaches and Algorithms for Classification
　A Pool of Classifiers by SLP: A Multi-class Case
　A Graph Spectral Approach to Consistent Labelling
　Gesture Recognition Using a Marionette Model and Dynamic　Bayesian Networks (DBNs)
　On Subspace Distance
　Ant Based Fuzzy Modeling Applied to Marble Classification
　A General Weighted Fuzzy Clustering Algorithm
　Integration of Expert Knowledge and Image Analysis Techniques for　Medical Diagnosis
Computer Vision
　Depth Recovery from Motion and Defocus Blur
　Using Cartesian Models of Faces with a Data-Driven and Integrable　Fitting Framework
　A Novel Omnidirectional Stereo Vision System with a Single Camera
　A Neural Network for Simultaneously Reconstructing Transparent　and Opaque Surfaces
　A Light Scattering Model for Layered Rough Surfaces
　Model Based Selection and Classification of Local Features for　Recognition Using Gabor Filters
　Inferring Stochastic Regular Grammar with Nearness Information for　Human Action Recognition
　Real Time Vehicle Pose Using On-Board Stereo Vision System
　Content-Based 3D Retrieval by Krawtchouk Moments
　Uncalibrated Visual Servoing in 3D Workspace
　A Real-Time 3D Modeling System Using Multiple Stereo Cameras　for Free-Viewpoint Video Generation
　CAD Model Visual Registration from Closed-Contour Neighborhood　Descriptors
Biometrics
Shape and Matching
Biomedical Image Analysis
Special Session:Brain Imaging
Special Session:Sensing Image Processing
Applications
Author Index