Computer Recognition Systems: Proceedings of 4th International Conference on Computer Recognition Systems CORES'05

ISBN-13: 9783540250548 / Angielski / Miękka / 2005 / 903 str.

Marek Kurzynski;Edward Puchala;Michal Wozniak

Opis

th This book contains papers accepted for presentation at the 4 International Conference on Computer Recognition Systems CORES'05, May 22-25, 2005, Rydzyna Castle (Poland), This conference is a continuation of a series of con ferences on similar topics (KOSYR) organized each second year, since 1999, by the Chair of Systems and Computer Networks, Wroclaw University of Tech nology. An increasing interest to those conferences paid not only by home but also by foreign participants inspired the organizers to transform them into conferences of international range. Our expectations that the community of specialists in computer recognizing systems will find CORES'05 a proper form of maintaining the tradition of the former conferences have been confirmed by a large number of submitted papers. Alas, organizational constraints caused a necessity to narrow the acceptance criteria so that only 100 papers have been finally included into the conference program. The area covered by accepted papers is still very large and it shows how vivacious is scientific activity in the domain of computer recognition methods and systems. It contains vari ous theoretical approaches to the recognition problem based on mathematical statistics, fuzzy sets, morphological methods, wavelets, syntactic methods, genetic algorithms, artificial neural networks, ontological models, etc. Most attention is still paid to visual objects recognition; however, acoustic, tex tual and other objects are also considered. Among application areas medical problems are in majority; recognition of faces, speech signals and textual in formation processing methods being also investigated."

Spis treści

Invited Papers.- Neural Network-Based Chaotic Pattern Recognition — Part 2: Stability and Algorithmic Issues.- A Brief Survey of Dynamic Texture Description and Recognition.- Open Issues in Pattern Recognition.- The Role of Ontological Models in Pattern Recognition.- Current Feature Selection Techniques in Statistical Pattern Recognition.- Features, Learning and Classifiers.- Margin-based Diversity Measures for Ensemble Classifiers.- Boosting the Fisher Linear Discriminant with Random Feature Subsets.- A Look-Ahead Branch and Bound Pruning Scheme for Trie-Based Approximate String Matching.- Feature Selection for High-Dimensional Data: A Kolmogorov-Smirnov Correlation-Based Filter.- Linear Ranked Regression - Designing Principles.- Time Series Patterns Recognition with Genetic Algorithms.- Selection of Fuzzy-Valued Loss Function in Two Stage Binary Classifier.- A New Rejection Strategy for Convolutional Neural Network by Adaptive Topology.- Fast PCA and LDA for JPEG Images.- A Hybrid ?-Insensitive Learning of Fuzzy Systems.- The Incremental Method for Discovery of Association Rules.- Feature Extraction with Wavelet Transformation for Statistical Object Recognition.- Digital Filter Design with Constraints in Time and Frequency Domains.- Efficient Implementation of Nearest Neighbor Classification.- Inductive Development of Customer e-Loyalty Theory with Bayesian Networks.- Reference Set Size Reduction for 1-NN Rule Based on Finding Mutually Nearest and Mutually Furthest Pairs of Points.- Learning from a Test Set.- Image Clustering with Median and Myriad Spatial Constraint Enhanced FCM.- Feature Selection in Unsupervised Context: Clustering Based Approach.- Conceptual Ontological Object Knowledge Base and Language.- A Method of Supervised Discrimination of Textures Based on Serial Statistical Tests.- Approximation Algorithm for the Argument Reduction Problem.- Spread Histogram — A Method for Calculating Spatial Relations Between Objects.- Comparing Modifcation Operators Used in Clustering Algorithm Based on a Sequence of Discriminant Rules.- Multi-Channels Time-Domain-Constrained Fuzzy c-Regression Models.- Pairwise Selection of Features and Prototypes.- Evolutionary Method in Grouping of Units.- Interpretation of Medical Symptoms Using Fuzzy Focal Elements.- User Model for Conceptual and Personalized Search.- On the Relationship Between Active Contours and Contextual Classification.- An Improvement on LDA Algorithm for Face Recognition.- Estimating and Calculating Consensus with Simple Dependencies of Attributes.- The Empirical Study of the Naive Bayes Classifier in the Case of Markov Chain Recognition Task.- Using Diversity Measure in Building Classifier Ensembles for Combination Method Analysis.- Image Processing and Computer Vision.- An Evolutionary Algorithm for Solving the Inverse Problem for Iterated Function Systems for a Two Dimensional Image.- Specification of the Evidence Accumulation-Based Line Detection Algorithm.- Scale and Rotation Invariance of the Evidence Accumulation-Based Line Detection Algorithm.- Content Based Image Retrieval Technique.- Scanning Faces Surroudings - New Concept in 3D Exact Multiviews of Nonconvex Polyhedron Generation.- Image Decomposition by Grade Analysis - an Illustration.- Detection of Rectangular Landmarks.- Q-shift Complex Wavelet-based Image Registration Algorithm.- Concept of 3D View Model of Non-Convex Polyhedra Generation Using View Sphere Partitioning into Single-View Areas.- Using Modified Hough Transform for Grouping of Image Features.- Planning Positioning Actions of a Mobile Robot Cooperating with Distributed Sensors.- Merging Probabilistic and Fuzzy Frameworks for Uncertain Spatial Knowledge Modelling.- Detection of Elliptical Shapes Using Contour Grouping.- Active Shape Models in Practice.- Fast Detection and Impulsive Noise Attenuation in Color Images.- Medical Applications.- Adaptive Wearable Vital Signs Monitor for Home Care and Sports.- Fractal Based Approaches to Morphological Analysis of Fundus Eye Images.- Recognition of Subtle Microcalcifications in High-Resolution Mammograms.- The Gait Characteristic Data Spectrum Extraction.- On The Construction of the Syntactic Pattern Recognition-Based Expert System for Auditory Brainstem Response Analysis.- Active Contour Technique in Post-segmentation Edge Smoothing Applied to Hand Radiograph Regions of Interest.- Classification of Medical Images in the Domain of Melanoid Skin Lesions.- Baseline and Acceleration Episodes - Clinically Significant Nonstationarities in FHR Signal: Part I. Coefficients of Inconsistency.- Baseline and Acceleration Episodes - Clinically Significant Nonstationarities in FHR Signal: Part II. Indirect Comparison.- Bias Field Correction for MRI Images.- SEM Image Analysis for Roughness Assessment of Implant Materials.- Output Flow Estimation of Pneumatically Controlled Ventricular Assist Device with the help of Artificial Neural Network.- The Cell Structures Segmentation.- Analysis of Stem Cell Clonal Growth.- Feature Extraction Optimization in Neural Classifier of Heart Rate Variability Signals.- Clustering DNA Microarray Data.- Cytomorphometry of Fine Needle Biopsy Material from the Breast Cancer.- Feature Ranking for Protein Classification.- Recognition of the Medical Structures in Computerized Chest Radiograph Processing.- Correlation-based Method for Automatic Mitotic Cell Detection in Phase Contrast Microscopy.- Watershed Extraction of the Exact Shape of Microcalcifications in Mammograms.- Computer Recognition of Biological Objects’ Internal Structure Using Ultrasonic Projection.- Machine Learning Methods for Dialysis Therapy Decision Problem — Comparative Study.- Removing Artefacts from Microscopic Images of Cytological Smears. A Shape-Based Approach.- Automatic Recognition of the Arterial Input Function in MRI Studies.- Mean Shift Segmentation, Genetic Algorithms and Support Vector Machines for Identification of Glaucoma in Fundus Eye Images.- Speech and Word Recognition.- Automatic Recognition and Verification of Voice Commands in Natural Language Given by the Operator of the Technological Device Using Artificial Neural Networks.- Recognition of Isolated Words of the Polish Sign Language.- Simple Measure of Typewriter Prints Quality.- Conversion of Textual Information to Speech for Polish Language.- Multilevel Recognition of Structured Handprinted Documents - Probabilistic Approach.- Application of Statistic Properties of Letters Succession in Polish Language to Handprint Recognition.- Speaker Recognition for VoIP Transmission Using Gaussian Mixture Models.- Semi-Automatic Segmentation of Speech: Manual Segmentation Strategy. Problem Space Analysis.- Fingerprint and Face Recognition.- HMM and WT Fusion for Face Identification.- Restoration of Partially Occluded Shapes of Faces Using Neural Networks.- Comparison of Minutiae Matching Techniques.- Application of Active Shapes to the Structural Face Model.- Comparison of Statistical Classifiers as Applied to the Face Recognition System Based on Active Shape Models.- Face Recognition Using DCT and LDA.- The New Algorithm of Fingerprint Reference Point Location Based on Identification Masks.- Person Identification Using Fast Face Learning of Lifting Dyadic Wavelet Filters.- Various Applications.- Dynamic Design with the Use of Intelligent Agents.- Optical Music Recognition: the Case Study of Pattern Recognition.- An Application for Tyre-Ground Contact Area Analysis.- On the Use of Syntactic Pattern Recognition Methods, Neural Networks, and Fuzzy Systems for Short-Term Electrical Load Forecasting.- A Real-Time Head Tracker Supporting Human Computer Interaction.- Wavelet Packets Features Extraction and Selection for Discriminating Plucked Sounds of Violins.- Pattern Recognition and Fault Detection in MEMS.- Representation of Structures and Changes in 3D Objects with Graph Grammars and Artificial Evolution.- Recognition of Polish Car License Plates.

Blurb

CORES'05 is the 4th International Conference on Computer Recognition Systems organized by Chair of Computer Systems and Networks of Wroclaw University of  Technology each two years. The conference is endorsed by the International Association for Pattern Recognition. The CORES'05 Conference aims to bring together researches and to provide an international forum for the sharing, exchange, presentation and discussion of original research results in both methodological issues and different application areas of pattern recognition. The conference covers all topics in pattern recognition including:

1. Classification and interpretation of text, video, voice

2. Statistical, soft and structural methods of pattern recognition

3. Image processing, analysis and interpretation

4. Features extraction and selection

5. Machine learning

6. Trends and relations recognition and analysis

7. Data and Web mining

8. Machine-oriented knowledge representation and inference methods

9. Knowledge-based decision support systems

10. Advanced signal processing methods

11. Special hardware architecture

12. Applications