Prototype selection for the nearest neighbour rule through proximity graphs

Abstract In this paper, the Gabriel and Relative Neighbourhood graphs are used to select a suitable subset of prototypes for the Nearest Neighbour rule. Experiments and results are reported showing the effectiveness of the method and comparing its performance to those obtained by classical techniques.

[1]  E. L. Battiste,et al.  Computer Science And Statistics , 1978, ACM Annual Conference.

[2]  Ludmila I. Kuncheva,et al.  Editing for the k-nearest neighbors rule by a genetic algorithm , 1995, Pattern Recognit. Lett..

[3]  Dennis L. Wilson,et al.  Asymptotic Properties of Nearest Neighbor Rules Using Edited Data , 1972, IEEE Trans. Syst. Man Cybern..

[4]  Mihran Tuceryan,et al.  Relative sensitivity of a family of closest-point graphs in computer vision applications , 1991, Pattern Recognit..

[5]  Peter E. Hart,et al.  The condensed nearest neighbor rule (Corresp.) , 1968, IEEE Trans. Inf. Theory.

[6]  Filiberto Pla,et al.  On the use of neighbourhood-based non-parametric classifiers , 1997, Pattern Recognit. Lett..

[7]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[8]  Francesc J. Ferri,et al.  Small sample size effects in the use of editing techniques , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[9]  Filiberto Pla,et al.  Colour segmentation based on a light reflection model to locate citrus fruits for robotic harvesting , 1993 .

[10]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .