PATTERN CLUSTERING BASED ON NOISE MODELING IN WAVELET SPACE

Authors
MURTAGH F STARCK JL
Citation
F. Murtagh et Jl. Starck, PATTERN CLUSTERING BASED ON NOISE MODELING IN WAVELET SPACE, Pattern recognition, 31(7), 1998, pp. 847-855
Citations number
42
Categorie Soggetti
Computer Science Artificial Intelligence","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence
Journal title
Pattern recognition → ACNP
ISSN journal
00313203
Volume
31
Issue
7
Year of publication
1998
Pages
847 - 855
Database
ISI
SICI code
0031-3203(1998)31:7<847:PCBONM>2.0.ZU;2-3
Abstract
We describe an effective approach to object or feature detection in po int patterns via noise modeling. This is based on use of a redundant o r non-pyramidal wavelet transform. Noise modeling is based on a Poisso n process. We illustrate this new method with a range of examples. We use the close relationship between image (pixelated) and point represe ntations to achieve the result of a clustering method with constant-ti me computational cost. (C) 1998 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.