Improvement of pose imitation method

A signal processing perspective

Tiezheng Mao, Aihua Mao, Osamu Yoshie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Pose imitation is for two shapes to study pose from each other. It has been a hot area in shape deformation and we improve the original graphical pose imitation method by introducing signal thought. Laplace framework is often used in pose imitation and geometrical information involved Laplace operator performs better in preserving original shape's mass smooth part by carrying much intrinsic information of graph. However, the two shapes' bases in Laplace feature space need to be well mapped before utilizing classical pose imitation algorithm, which makes it an obstacle to introduce the geometry related Laplace operator. In our work, the problem is solved by proposing signal transfer algorithm and based on it, we put out an effective pose imitation framework using edge length related Laplace operator. Our method well suits to 2-dimension shape and good results of pose imitation have been achieved.

Original languageEnglish
Title of host publicationEighth International Conference on Digital Image Processing, ICDIP 2016
PublisherSPIE
Volume10033
ISBN (Electronic)9781510605039
DOIs
Publication statusPublished - 2016
Event8th International Conference on Digital Image Processing, ICDIP 2016 - Chengu, China
Duration: 2016 May 202016 May 23

Other

Other8th International Conference on Digital Image Processing, ICDIP 2016
CountryChina
CityChengu
Period16/5/2016/5/23

Fingerprint

Imitation
Signal Processing
signal processing
Signal processing
Laplace transformation
Laplace Operator
Mathematical operators
Laplace
Geometry
Shape Preserving
preserving
Feature Space
geometry
Graph in graph theory

Keywords

  • Laplace operator
  • Pose imitation
  • Signal transfer
  • Spectral analysis.

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Mao, T., Mao, A., & Yoshie, O. (2016). Improvement of pose imitation method: A signal processing perspective. In Eighth International Conference on Digital Image Processing, ICDIP 2016 (Vol. 10033). [100335C] SPIE. https://doi.org/10.1117/12.2244949

Improvement of pose imitation method : A signal processing perspective. / Mao, Tiezheng; Mao, Aihua; Yoshie, Osamu.

Eighth International Conference on Digital Image Processing, ICDIP 2016. Vol. 10033 SPIE, 2016. 100335C.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mao, T, Mao, A & Yoshie, O 2016, Improvement of pose imitation method: A signal processing perspective. in Eighth International Conference on Digital Image Processing, ICDIP 2016. vol. 10033, 100335C, SPIE, 8th International Conference on Digital Image Processing, ICDIP 2016, Chengu, China, 16/5/20. https://doi.org/10.1117/12.2244949
Mao T, Mao A, Yoshie O. Improvement of pose imitation method: A signal processing perspective. In Eighth International Conference on Digital Image Processing, ICDIP 2016. Vol. 10033. SPIE. 2016. 100335C https://doi.org/10.1117/12.2244949
Mao, Tiezheng ; Mao, Aihua ; Yoshie, Osamu. / Improvement of pose imitation method : A signal processing perspective. Eighth International Conference on Digital Image Processing, ICDIP 2016. Vol. 10033 SPIE, 2016.
@inproceedings{e5a42a91383d4564828322d8a1545b50,
title = "Improvement of pose imitation method: A signal processing perspective",
abstract = "Pose imitation is for two shapes to study pose from each other. It has been a hot area in shape deformation and we improve the original graphical pose imitation method by introducing signal thought. Laplace framework is often used in pose imitation and geometrical information involved Laplace operator performs better in preserving original shape's mass smooth part by carrying much intrinsic information of graph. However, the two shapes' bases in Laplace feature space need to be well mapped before utilizing classical pose imitation algorithm, which makes it an obstacle to introduce the geometry related Laplace operator. In our work, the problem is solved by proposing signal transfer algorithm and based on it, we put out an effective pose imitation framework using edge length related Laplace operator. Our method well suits to 2-dimension shape and good results of pose imitation have been achieved.",
keywords = "Laplace operator, Pose imitation, Signal transfer, Spectral analysis.",
author = "Tiezheng Mao and Aihua Mao and Osamu Yoshie",
year = "2016",
doi = "10.1117/12.2244949",
language = "English",
volume = "10033",
booktitle = "Eighth International Conference on Digital Image Processing, ICDIP 2016",
publisher = "SPIE",
address = "United States",

}

TY - GEN

T1 - Improvement of pose imitation method

T2 - A signal processing perspective

AU - Mao, Tiezheng

AU - Mao, Aihua

AU - Yoshie, Osamu

PY - 2016

Y1 - 2016

N2 - Pose imitation is for two shapes to study pose from each other. It has been a hot area in shape deformation and we improve the original graphical pose imitation method by introducing signal thought. Laplace framework is often used in pose imitation and geometrical information involved Laplace operator performs better in preserving original shape's mass smooth part by carrying much intrinsic information of graph. However, the two shapes' bases in Laplace feature space need to be well mapped before utilizing classical pose imitation algorithm, which makes it an obstacle to introduce the geometry related Laplace operator. In our work, the problem is solved by proposing signal transfer algorithm and based on it, we put out an effective pose imitation framework using edge length related Laplace operator. Our method well suits to 2-dimension shape and good results of pose imitation have been achieved.

AB - Pose imitation is for two shapes to study pose from each other. It has been a hot area in shape deformation and we improve the original graphical pose imitation method by introducing signal thought. Laplace framework is often used in pose imitation and geometrical information involved Laplace operator performs better in preserving original shape's mass smooth part by carrying much intrinsic information of graph. However, the two shapes' bases in Laplace feature space need to be well mapped before utilizing classical pose imitation algorithm, which makes it an obstacle to introduce the geometry related Laplace operator. In our work, the problem is solved by proposing signal transfer algorithm and based on it, we put out an effective pose imitation framework using edge length related Laplace operator. Our method well suits to 2-dimension shape and good results of pose imitation have been achieved.

KW - Laplace operator

KW - Pose imitation

KW - Signal transfer

KW - Spectral analysis.

UR - http://www.scopus.com/inward/record.url?scp=85000400621&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85000400621&partnerID=8YFLogxK

U2 - 10.1117/12.2244949

DO - 10.1117/12.2244949

M3 - Conference contribution

VL - 10033

BT - Eighth International Conference on Digital Image Processing, ICDIP 2016

PB - SPIE

ER -