Advances in Pattern Recognition: Joint Iapr International Workshops Sspr 2000 and Spr 2000 Alicante, Spain, August 30 - September 1, 2000 Proceedings

ISBN-13: 9783540679462 / Angielski / Miękka / 2000 / 904 str.

F. J. Ferri; J. M. Inesta; Francesc J. Ferri

Opis

This volume constitutes the joint refereed proceedings of the 8th International Workshop on Structural and Syntactic Pattern Recognition and the 3rd International Workshop on Statistical Techniques in Pattern Recognition, SSPR 2000 and SPR 2000, held in Alicante, Spain in August - September 2000. The 52 revised full papers presented together with five invited papers and 35 posters were carefully reviewed and selected from a total of 130 submissions. From a total of 130 submissions, the book offers sections on: hybrid and combined methods; document image analysis; grammar and language methods; structural matching; graph-based methods; shape analysis; clustering and density estimation; object recognition; general methodology; and feature extraction and selection.

Spis treści

Invited Papers.- Some Notes on Twenty One 21 Nearest Prototype Classifiers.- Adaptive Graphical Pattern Recognition Beyond Connectionist-Based Approaches.- Current Trends in Grammatical Inference.- Classifier’s Complexity Control while Training Multilayer Perceptrons.- Pierre Devijver Lecture.- A Framework for Classifier Fusion: Is It Still Needed?.- Hybrid and Combined Methods.- Image Pattern Recognition Based on Examples— A Combined Statistical and Structural-Syntactic Approach.- A Hybrid System for the Recognition of Hand-Written Characters.- Improving Statistical Measures of Feature Subsets by Conventional and Evolutionary Approaches.- Selection of Classifiers Based on Multiple Classifier Behaviour.- Applications.- The Adaptive Subspace Map for Image Description and Image Database Retrieval.- Adaptive Automatic Target Recognition with SVM Boosting for Outlier Detection.- A Multiresolution Causal Colour Texture Model.- Writer Identification: Statistical Analysis and Dichotomizer.- Document Image Analysis.- Syntactic Pattern Recognition by Error Correcting Analysis on Tree Automata.- Offline Recognition of Syntax-Constrained Cursive Handwritten Text.- Structural Classification for Retrospective Conversion of Documents.- Segmentation of Date Field on Bank Cheques.- Grammar and Language Methods.- Grammars and Discourse Theory to Describe and Recognize Mechanical Assemblies.- Computation of the N Best Parse Trees for Weighted and Stochastic Context-Free Grammars.- Partitional vs Hierarchical Clustering Using a Minimum Grammar Complexity Approach.- Encoding Nondeterministic Finite-State Tree Automata in Sigmoid Recursive Neural Networks.- Structural Matching.- Retrieval of Partially Visible Shapes through Structural Feature Indexing.- A Structural Matching Algorithm Using Generalized Deterministic Annealing.- Alignment and Correspondence Using Singular Value Decomposition.- Graph Matching: Fast Candidate Elimination Using Machine Learning Techniques.- Efficient Alignment and Correspondence Using Edit Distance.- Graph-Based Methods.- Irregular Pyramids with Combinatorial Maps.- A New Error-Correcting Distance for Attributed Relational Graph Problems.- Distance between Attributed Graphs and Function-Described Graphs Relaxing 2nd Order Restrictions.- A Graph Labelling Approach for Connected Feature Selection.- Region-Based Representation for Object Recognition by Relaxation Labelling.- Shape Analysis.- Shape Boundary Tracking with Hidden Markov Models.- Parallel Techniques for Rule-Based Scene Interpretation.- Curvature Estimation Using Shape-from-Texture.- Efficient Techniques for a Very Accurate Measurement of Dissimilarities between Cyclic Patterns.- SSPR Poster Session.- Planar Symmetry Detection by Random Sampling and Voting Process.- Assessing the Computational Effort for Structural 3D Vehicle Recognition.- Guided Relinking of Graph Pyramids.- Texture Indexing by a Hierarchical Representation.- Surface Skeletons Detected on the D6 Distance Transform.- Selection Strategies for Ambiguous Graph Matching by Evolutionary Optimisation.- Studies of Radical Model for Retrieval of Cursive Chinese Handwritten Annotations.- A Statistical-Estimation Method for Stochastic Finite-State Transducers Based on Entropy Measures.- Efficient Subgraph Isomorphism with ‘A Priori’ Knowledge.- Pyramid and Interior.- Prototype Learning with Attributed Relational Graphs.- Lossless Compression of Surfaces Described as Points.- A Class of Solvable Consistent Labeling Problems.- Character Recognition, Orientation, and Scale Estimation Thanks to the Fourier Mellin Transform.- Using the Dual of Proximity Graphs for Binary Decision Tree Design.- Clustering and Density Estimation.- Bayesian Approach to Mixture Models for Discrimination.- Pattern Classification Based on a Piecewise Multi-linear Model for the Class Probability Densities.- Selection of the Number of Components Using a Genetic Algorithm for Mixture Model Classifiers.- The Moments of the Mixel Distribution and Its Application to Statistical Image Classification.- Object Recognition.- Statistical Pattern Recognition Using the Normalized Complex Moment Components Vector.- Initial Matching of Multiple-View Images by Affine Approximation of Relative Distortions.- Local Discriminant Regions Using Support Vector Machines for Object Recognition.- Stochastic Models for Recognition of Occluded Objects.- General Methodology I.- A Vector Approach to the Analysis of (Patterns with) Spatial Dependence.- The Foundational Theory of Optimal Bayesian Pairwise Linear Classifiers.- The Optimum Classifier and the Performance Evaluation by Bayesian Approach.- A New Approximation Method of the Quadratic Discriminant Function.- An Optimal Reject Rule for Binary Classifiers.- General Methodology II.- Decontamination of Training Samples for Supervised Pattern Recognition Methods.- The Role of Combining Rules in Bagging and Boosting.- Confidence Combination Methods in Multi-expert Systems.- Reducing the Training Times of Neural Classifiers with Dataset Condensing.- Non-linear Invertible Representation for Joint Statistical and Perceptual Feature Decorrelation.- Feature Extraction and Selection.- A Divergence Criterion for Classifier-Independent Feature Selection.- Comparison of Classifier-Specific Feature Selection Algorithms.- Combined Classifier Optimisation via Feature Selection.- Design Choices and Theoretical Issues for Relative Feature Importance, a Metric for Nonparametric Discriminatory Power.- SPR Poster Session.- Real-Coded Genetic Algorithms Based on Mathematical Morphology.- A New Model and Process Architecture for Facial Expression Recognition.- Biologically Inspired Architecture of Feedforward Networks for Signal Classification.- Optimal Threshold Estimation Using Prototype Selection.- Basic and Fine Structure of Pairwise Interactions in Gibbs Texture Models.- Segmentation of Text and Graphics/Images Using the Gray-Level Histogram Fourier Transform.- Fast and Accurate Handwritten Character Recognition Using Approximate Nearest Neighbours Search on Large Databases.- A Family of Divergences between ?-Probabilistic Sets with Application to Handshape Recognition.- Rotated, Scaled, and Noisy 2D and 3D Texture Classification with the Bispectrum-Based Invariant Feature.- Multiple Comparison Procedures for Determining the Optimal Complexity of a Model.- Image Pattern Recognition in Natural Environment Using Morphological Feature Extraction.- A Statistical Matrix Representation Using Sliced Orthogonal Nonlinear Correlations for Pattern Recognition.- A Fast Approximately k—Nearest—Neighbour Search Algorithm For Clasification Tasks.- Design of a Telerobotic Interface System by Using Object Recognition Techniques.- Comparison of Four Initialization Techniques for the K-Medians Clustering Algorithm.- Sensory Flow Segmentation Using a Resource Allocating Vector Quantizer.- Multiple Reject Thresholds for Improving Classification Reliability.- Clustering with EM: Complex Models vs. Robust Estimation.- A Simple Implementation of the Stochastic Discrimination for Pattern Recognition.- Adaptive Image Filtering and Segmentation Using Robust Estimation of Intensity.