A generalization of dissimilarity representations using feature lines and feature planes

Authors:
Mauricio Orozco-Alzate;Robert P. W. Duin;Germán Castellanos-Domínguez
Affiliations:
Departamento de Informática y Computación, Universidad Nacional de Colombia Sede Manizales, Kilómetro 7 Vía al Aeropuerto, Campus La Nubia - Bloque Q, Piso 2, Manizales (Caldas ...;Information and Communication Theory Group, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, P.O. Box 5031, 2600GA Delft, The Netherlands;Grupo de Control y Procesamiento Digital de Señales, Universidad Nacional de Colombia Sede Manizales, Kilómetro 7 Vía al Aeropuerto, Campus La Nubia - Bloque Q, Piso 2, Manizales (C ...
Venue:
Pattern Recognition Letters
Year:
2009

Citing 13
Cited 3

Performance Evaluation of the Nearest Feature Line Method in Image Classification and Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Discriminant Waveletfaces and Nearest Feature Classifiers for Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Dissimilarity representations allow for building good classifiers

Pattern Recognition Letters
On the use of nearest feature line for speaker identification

Pattern Recognition Letters
A generalized kernel approach to dissimilarity-based classification

The Journal of Machine Learning Research
Comparison of the nearest feature classifiers for face recognition

Machine Vision and Applications
Dissimilarity-based classification for vectorial representations

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Experimental study on prototype optimisation algorithms for prototype-based classification in vector spaces

Pattern Recognition
Prototype selection for dissimilarity-based classifiers

Pattern Recognition
Rectified nearest feature line segment for pattern classification

Pattern Recognition
Multiresolution face recognition

Image and Vision Computing
Nearest neighbor pattern classification

IEEE Transactions on Information Theory
Face recognition using the nearest feature line method

IEEE Transactions on Neural Networks

The dissimilarity representation for structural pattern recognition

CIARP'11 Proceedings of the 16th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Dissimilarity-Based classifications in eigenspaces

CIARP'11 Proceedings of the 16th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Selecting feature lines in generalized dissimilarity representations for pattern recognition

Digital Signal Processing

Quantified Score

Hi-index	0.10

Visualization

Abstract

Even though, under representational restrictions, the nearest feature rules and the dissimilarity-based classifiers are feasible alternatives to the nearest neighbor method; individually, they may not be sufficiently powerful if a very small set of prototypes is required, e.g. when it is computationally expensive to deal with larger sets of prototypes. In this paper, we show that combining both strategies, taking advantage of their individual properties, provides an improvement, particularly for correlated data sets. The combined strategy consists in deriving an enriched (generalized) dissimilarity representation by using the nearest feature rules, namely feature lines and feature planes. On top of that enriched representation, Bayesian classifiers can be constructed in order to obtain a good generalization.