Feature-Based Dissimilarity Space Classification

• Published in: Recognizing Patterns in Signals, Speech, Images and Videos pp. 46 - 55
• Main Authors: Duin, Robert P. W., Loog, Marco, Pȩkalska, Elżbieta, Tax, David M. J.
• Format: Book Chapter
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2010
• Series: Lecture Notes in Computer Science
• Subjects: Dissimilarity Measure; Feature Space; Linear Support Vector Machine; Neighbor Rule; Training Object
• ISBN: 9783642177101; 3642177107
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-642-17711-8_5

General dissimilarity-based learning approaches have been proposed for dissimilarity data sets [1,2]. They often arise in problems in which direct comparisons of objects are made by computing pairwise distances between images, spectra, graphs or strings. Dissimilarity-based classifiers can also be defined in vector spaces [3]. A large comparative study has not been undertaken so far. This paper compares dissimilarity-based classifiers with traditional feature-based classifiers, including linear and nonlinear SVMs, in the context of the ICPR 2010 Classifier Domains of Competence contest. It is concluded that the feature-based dissimilarity space classification performs similar or better than the linear and nonlinear SVMs, as averaged over all 301 datasets of the contest and in a large subset of its datasets. This indicates that these classifiers have their own domain of competence.