creators_name: Kitts, B.
type: preprint
datestamp: 1998-06-14
lastmod: 2011-03-11 08:53:58
metadata_visibility: show
title: Real-time trajectory analysis using stacked invariance methods
ispublished: unpub
subjects: comp-sci-art-intel
subjects: comp-sci-complex-theory
full_text_status: public
keywords: invariance, stacking, stacked, invariant
abstract: Invariance methods are used widely in pattern recognition as a preprocessing stage before algorithms such as neural networks are applied to the problem. A pattern recognition system has to be able to recognise objects invariant to scale, translation, and rotation. Presumably the human eye implements some of these preprocessing transforms in making sense of incoming stimuli, for example, placing signals onto a log scale. This paper surveys many of the commonly used invariance methods, and assesses their performance on one particular problem, estimating the quality of human motor imitation invariant to rotation, scale and translation.
date: 1998
date_type: published
refereed: FALSE
citation:   Kitts, B.  (1998) Real-time trajectory analysis using stacked invariance methods.  [Preprint]    (Unpublished)  
document_url: http://cogprints.org/456/2/preproc21.ps