The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Para melhorar o desempenho do alinhamento não linear dos Modelos de Aparência Ativa (AAM), aplicamos uma variante do algoritmo de aprendizado de variedade não linear, Local Linear Embedded, para modelar a variedade forma-textura. Experimentos mostram que nosso método mantém um alinhamento residual menor para alguns movimentos de pequena escala em comparação com o AAM tradicional baseado na Análise de Componentes Principais (PCA) e faz um alinhamento bem-sucedido para movimentos de grande escala quando o PCA-AAM falha.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Xiaokan WANG, Xia MAO, Catalin-Daniel CALEANU, "Nonlinear Shape-Texture Manifold Learning" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 7, pp. 2016-2019, July 2010, doi: 10.1587/transinf.E93.D.2016.
Abstract: For improving the nonlinear alignment performance of Active Appearance Models (AAM), we apply a variant of the nonlinear manifold learning algorithm, Local Linear Embedded, to model shape-texture manifold. Experiments show that our method maintains a lower alignment residual to some small scale movements compared with traditional AAM based on Principal Component Analysis (PCA) and makes a successful alignment to large scale motions when PCA-AAM failed.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.2016/_p
Copiar
@ARTICLE{e93-d_7_2016,
author={Xiaokan WANG, Xia MAO, Catalin-Daniel CALEANU, },
journal={IEICE TRANSACTIONS on Information},
title={Nonlinear Shape-Texture Manifold Learning},
year={2010},
volume={E93-D},
number={7},
pages={2016-2019},
abstract={For improving the nonlinear alignment performance of Active Appearance Models (AAM), we apply a variant of the nonlinear manifold learning algorithm, Local Linear Embedded, to model shape-texture manifold. Experiments show that our method maintains a lower alignment residual to some small scale movements compared with traditional AAM based on Principal Component Analysis (PCA) and makes a successful alignment to large scale motions when PCA-AAM failed.},
keywords={},
doi={10.1587/transinf.E93.D.2016},
ISSN={1745-1361},
month={July},}
Copiar
TY - JOUR
TI - Nonlinear Shape-Texture Manifold Learning
T2 - IEICE TRANSACTIONS on Information
SP - 2016
EP - 2019
AU - Xiaokan WANG
AU - Xia MAO
AU - Catalin-Daniel CALEANU
PY - 2010
DO - 10.1587/transinf.E93.D.2016
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2010
AB - For improving the nonlinear alignment performance of Active Appearance Models (AAM), we apply a variant of the nonlinear manifold learning algorithm, Local Linear Embedded, to model shape-texture manifold. Experiments show that our method maintains a lower alignment residual to some small scale movements compared with traditional AAM based on Principal Component Analysis (PCA) and makes a successful alignment to large scale motions when PCA-AAM failed.
ER -