Multiple Classifier Systems: 7th International Workshop, MCS 2007, Prague, Czech Republic, May 23-25, 2007, Proceedings [Paperback]

These proceedings are a record of the Multiple Classi?er Systems Workshop, MCS 2007, held at the Institute of Information Theory and Automation, Czech Academy of Sciences, Prague in May 2007. Being the seventh in a well-established series of meetings providing an international forum for the discussion of issues in multiple classi?er system design, the workshop achieved its objective of bringing together researchers from diverse communities (neural networks, pattern rec- nition, machine learning and statistics) concerned with this research topic. From more than 80 submissions, the Programme Committee selected 49 - pers to create an interesting scienti?c programme. The special focus of MCS 2007 was on the application of multiple classi?er systems in biometrics. This part- ular application area exercises all aspects of multiple classi?er fusion, from - tramodal classi?er combination, through con?dence-based fusion, to multimodal biometric systems. The sponsorship of MCS 2007 by the European Union N- work of Excellence in Biometrics BioSecure and in Multimedia Understanding through Semantics, Computation and Learning MUSCLE and their assistance in selecting the contributions to the MCS 2007 programme consistent with this theme is gratefully acknowledged.Kernel-Based Fusion.- Combining Pattern Recognition Modalities at the Sensor Level Via Kernel Fusion.- The Neutral Point Method for Kernel-Based Combination of Disjoint Training Data in Multi-modal Pattern Recognition.- Kernel Combination Versus Classifier Combination.- Deriving the Kernel from Training Data.- Applications.- On the Application of SVM-Ensembles Based on Adapted Random Subspace Sampling for Automatic Classification of NMR Data.- A New HMM-Based Ensemble Generation Method for Numeral Recognition.- Classifiers Fusion in Recognition of Wheat Varieties.- Multiple Classifier Methods for Offline Handwritten Text Line Recognition.- Applying Data Fusion Methods to Passage Retrieval in QAS.- A Co-training Approach l