Driven by the requirements of a large number of practical and commercially - portant applications, the last decade has witnessed considerable advances in p- tern recognition. Better understanding of the design issues and new paradigms, such as the Support Vector Machine, have contributed to the development of - proved methods of pattern classi cation. However, while any performance gains are welcome, and often extremely signi cant from the practical point of view, it is increasingly more challenging to reach the point of perfection as de ned by the theoretical optimality of decision making in a given decision framework. The asymptoticity of gains that can be made for a single classi er is a re?- tion of the fact that any particular design, regardless of how good it is, simply provides just one estimate of the optimal decision rule. This observation has motivated the recent interest in Multiple Classi er Systems , which aim to make use of several designs jointly to obtain a better estimate of the optimal decision boundary and thus improve the system performance. This volume contains the proceedings of the international workshop on Multiple Classi er Systems held at Robinson College, Cambridge, United Kingdom (July 2{4, 2001), which was organized to provide a forum for researchers in this subject area to exchange views and report their latest results.
Author(s): Marina Skurichina, Robert P. W. Duin (auth.), Josef Kittler, Fabio Roli (eds.)
Series: Lecture Notes in Computer Science 2096
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2001
Language: English
Pages: 456
Tags: Pattern Recognition; Image Processing and Computer Vision; Artificial Intelligence (incl. Robotics); Computation by Abstract Devices; Algorithm Analysis and Problem Complexity
Bagging and the Random Subspace Method for Redundant Feature Spaces....Pages 1-10
Performance Degradation in Boosting....Pages 11-21
A Generalized Class of Boosting Algorithms Based on Recursive Decoding Models....Pages 22-31
Tuning Cost-Sensitive Boosting and Its Application to Melanoma Diagnosis....Pages 32-42
Learning Classification RBF Networks by Boosting....Pages 43-52
Data Complexity Analysis for Classifier Combination....Pages 53-67
Genetic Programming for Improved Receiver Operating Characteristics....Pages 68-77
Methods for Designing Multiple Classifier Systems....Pages 78-87
Decision-Level Fusion in Fingerprint Verification....Pages 88-98
Genetic Algorithms for Multi-classifier System Configuration: A Case Study in Character Recognition....Pages 99-108
Combined Classification of Handwritten Digits Using the ‘Virtual Test Sample Method’....Pages 109-118
Averaging Weak Classifiers....Pages 119-125
Mixing a Symbolic and a Subsymbolic Expert to Improve Carcinogenicity Prediction of Aromatic Compounds....Pages 126-135
Multiple Classifier Systems Based on Interpretable Linear Classifiers....Pages 136-147
Least Squares and Estimation Measures via Error Correcting Output Code....Pages 148-157
Dependence among Codeword Bits Errors in ECOC Learning Machines: An Experimental Analysis....Pages 158-167
Information Analysis of Multiple Classifier Fusion?....Pages 168-177
Limiting the Number of Trees in Random Forests....Pages 178-187
Learning-Data Selection Mechanism through Neural Networks Ensemble....Pages 188-197
A Multi-SVM Classification System....Pages 198-207
Automatic Classification of Clustered Microcalcifications by a Multiple Classifier System....Pages 208-217
Feature Weighted Ensemble Classifiers – A Modified Decision Scheme....Pages 218-227
Feature Subsets for Classifier Combination: An Enumerative Experiment....Pages 228-237
Input Decimation Ensembles: Decorrelation through Dimensionality Reduction....Pages 238-247
Classifier Combination as a Tomographic Process....Pages 248-258
A Robust Multiple Classifier System for a Partially Unsupervised Updating of Land-Cover Maps....Pages 259-268
Combining Supervised Remote Sensing Image Classifiers Based on Individual Class Performances....Pages 269-278
Boosting, Bagging, and Consensus Based Classification of Multisource Remote Sensing Data....Pages 279-288
Solar Wind Data Analysis Using Self-Organizing Hierarchical Neural Network Classifiers....Pages 289-298
Combining One-Class Classifiers....Pages 299-308
Finding Consistent Clusters in Data Partitions....Pages 309-318
A Self-Organising Approach to Multiple Classifier Fusion....Pages 319-328
Error Rejection in Linearly Combined Multiple Classifiers....Pages 329-338
Relationship of Sum and Vote Fusion Strategies....Pages 339-348
Complexity of Data Subsets Generated by the Random Subspace Method: An Experimental Investigation....Pages 349-358
On Combining Dissimilarity Representations....Pages 359-368
Application of Multiple Classifier Techniques to Subband Speaker Identification with an HMM/ANN System....Pages 369-377
Classification of Time Series Utilizing Temporal and Decision Fusion....Pages 378-387
Use of Positional Information in Sequence Alignment for Multiple Classifier Combination....Pages 388-398
Application of the Evolutionary Algorithms for Classifier Selection in Multiple Classifier Systems with Majority Voting....Pages 399-408
Tree-Structured Support Vector Machines for Multi-class Pattern Recognition....Pages 409-417
On the Combination of Different Template Matching Strategies for Fast Face Detection....Pages 418-428
Improving Product by Moderating k-NN Classifiers....Pages 429-439
Automatic Model Selection in a Hybrid Perceptron/Radial Network....Pages 440-454
