Approximate convex hulls family for one-class classification

Authors:
Pierluigi Casale;Oriol Pujol;Petia Radeva
Affiliations:
Computer Vision Center, Barcelona, Spain and Dept. Applied Mathematics and Analysis, University of Barcelona, Barcelona, Spain;Computer Vision Center, Barcelona, Spain and Dept. Applied Mathematics and Analysis, University of Barcelona, Barcelona, Spain;Computer Vision Center, Barcelona, Spain and Dept. Applied Mathematics and Analysis, University of Barcelona, Barcelona, Spain
Venue:
MCS'11 Proceedings of the 10th international conference on Multiple classifier systems
Year:
2011

Citing 9
Cited 2

Computational geometry: an introduction

Computational geometry: an introduction
Bagging predictors

Machine Learning
Duality and Geometry in SVM Classifiers

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Application of computational geometry to pattern recognition problems

Application of computational geometry to pattern recognition problems
Kernel subclass convex hull sample selection method for SVM on face recognition

Neurocomputing
Margin Preserved Approximate Convex Hulls for Classification

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Random projection, margins, kernels, and feature-selection

SLSFS'05 Proceedings of the 2005 international conference on Subspace, Latent Structure and Feature Selection
A geometric approach to Support Vector Machine (SVM) classification

IEEE Transactions on Neural Networks
Neurocomputing Model for Computation of an Approximate Convex Hull of a Set of Points and Spheres

IEEE Transactions on Neural Networks

One-class classification with Gaussian processes

Pattern Recognition
Approximate polytope ensemble for one-class classification

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work, a new method for one-class classification based on the Convex Hull geometric structure is proposed. The new method creates a family of convex hulls able to fit the geometrical shape of the training points. The increased computational cost due to the creation of the convex hull in multiple dimensions is circumvented using random projections. This provides an approximation of the original structure with multiple bi-dimensional views. In the projection planes, a mechanism for noisy points rejection has also been elaborated and evaluated. Results show that the approach performs considerably well with respect to the state the art in one-class classification.