arrow
Return

Wavelet kernel learning

delete2011-10-01
delete20
PRE
AI
F
Florian Yger
A
Alain Rakotomamonjy *
DOI:10.1016/j.patcog.2011.03.006delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
This paper addresses the problem of optimal feature extraction from a wavelet representation. Our work aims at building features by selecting wavelet coefficients resulting from signal or image decomposition on an adapted wavelet basis. For this purpose, we jointly learn in a kernelized large-margin context the wavelet shape as well as the appropriate scale and translation of the wavelets, hence the name wavelet kernel learning. This problem is posed as a multiple kernel learning problem, where the number of kernels can be very large. For solving such a problem, we introduce a novel multiple kernel learning algorithm based on active constraints methods. We furthermore propose some variants of this algorithm that can produce approximate solutions more efficiently. Empirical analysis show that our active constraint MKL algorithm achieves state-of-the art efficiency. When used for wavelet kernel learning, our experimental results show that the approaches we propose are competitive with respect to the state-of-the-art on brain-computer interface and Brodatz texture datasets. (C) 2011 Elsevier Ltd. All rights reserved.
Keywords:
Wavelet
Multiple kernel learning
SVM
Quadratic mirror filter

Journal

Pattern Recognition cover
Pattern Recognition
IF:
7.6
Papers:
1.4W
Citations:
6.1W

Organization

U
universite de rouen normandie
Scholars:
121
Papers: 52
Citations: 3.3K
Cited Papers

Cited Papers

errShare
errSave
Feature extraction by shape-adapted local discriminant bases
err2003-02-01
err22
PREAI
errStrauss, DJ; Steidl, G; Delb, W
errShare
errSave
errShare
errSave
errShare
errSave
err2020-04-01
err0
PREAI
err
errShare
errSave
Hematologic and hepatic function profile comparison between pig and baboon in an orthotopic liver xenotransplantation model
err1999-09-01
err0
PREAI
errV Munı́tiz; P Ramı́rez; Q Hernández; M Loba; R Chavez; A Muñoz; A Rı́os; A Minguela; P Parrilla
errShare
errSave
errShare
errSave
errShare
errSave
researcher View more