Signature features with the visibility transformation

Yue Wu; Hao Ni; Terence J Lyons; Robin L Hudson

doi:10.1109/ICPR48806.2021.9412642

Signature features with the visibility transformation

Yue Wu^*, Hao Ni, Terence J Lyons, Robin L Hudson

^*Corresponding author for this work

Mathematics And Statistics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

1 Citation (Scopus)

Abstract

In this paper we put the visibility transformation on a clear theoretical footing and show that this transform is able to embed the effect of the absolute position of the data stream into signature features in a unified and efficient way. The generated feature set is particularly useful in pattern recognition tasks, for its simplifying role in allowing the signature feature set to accommodate nonlinear functions of absolute and relative values.

Original language	English
Title of host publication	2020 25th International Conference on Pattern Recognition (ICPR)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	4665-4672
Number of pages	8
ISBN (Electronic)	978-1-7281-8808-9
DOIs	https://doi.org/10.1109/ICPR48806.2021.9412642
Publication status	Published - 5 May 2021

Keywords

task analysis
pattern recognition
hidden markov model
skeleton data

Access to Document

10.1109/ICPR48806.2021.9412642

Cite this

@inproceedings{5b0887dd6c34435093339070d95a9009,

title = "Signature features with the visibility transformation",

abstract = "In this paper we put the visibility transformation on a clear theoretical footing and show that this transform is able to embed the effect of the absolute position of the data stream into signature features in a unified and efficient way. The generated feature set is particularly useful in pattern recognition tasks, for its simplifying role in allowing the signature feature set to accommodate nonlinear functions of absolute and relative values.",

keywords = "task analysis, pattern recognition, hidden markov model, skeleton data",

author = "Yue Wu and Hao Ni and Lyons, \{Terence J\} and Hudson, \{Robin L\}",

year = "2021",

month = may,

day = "5",

doi = "10.1109/ICPR48806.2021.9412642",

language = "English",

pages = "4665--4672",

booktitle = "2020 25th International Conference on Pattern Recognition (ICPR)",

publisher = "IEEE",

}

TY - GEN

T1 - Signature features with the visibility transformation

AU - Wu, Yue

AU - Ni, Hao

AU - Lyons, Terence J

AU - Hudson, Robin L

PY - 2021/5/5

Y1 - 2021/5/5

N2 - In this paper we put the visibility transformation on a clear theoretical footing and show that this transform is able to embed the effect of the absolute position of the data stream into signature features in a unified and efficient way. The generated feature set is particularly useful in pattern recognition tasks, for its simplifying role in allowing the signature feature set to accommodate nonlinear functions of absolute and relative values.

AB - In this paper we put the visibility transformation on a clear theoretical footing and show that this transform is able to embed the effect of the absolute position of the data stream into signature features in a unified and efficient way. The generated feature set is particularly useful in pattern recognition tasks, for its simplifying role in allowing the signature feature set to accommodate nonlinear functions of absolute and relative values.

KW - task analysis

KW - pattern recognition

KW - hidden markov model

KW - skeleton data

U2 - 10.1109/ICPR48806.2021.9412642

DO - 10.1109/ICPR48806.2021.9412642

M3 - Conference contribution book

SP - 4665

EP - 4672

BT - 2020 25th International Conference on Pattern Recognition (ICPR)

PB - IEEE

CY - Piscataway, NJ

ER -

Signature features with the visibility transformation

Abstract

Keywords

Access to Document

Fingerprint

Cite this