Robust Active Shape Model Using AdaBoosted Histogram Classifiers and Shape Parameter Optimization

Yuanzhong LI; Wataru ITO

doi:10.1093/ietisy/e89-d.7.2117

Robust Active Shape Model Using AdaBoosted Histogram Classifiers and Shape Parameter Optimization

Yuanzhong LI, Wataru ITO

Full Text Views

0

Share
Cite this

Summary :

Active Shape Model (ASM) has been shown to be a powerful tool to aid the interpretation of images, especially in face alignment. ASM local appearance model parameter estimation is based on the assumption that residuals between model fit and data have a Gaussian distribution. Moreover, to generate an allowable face shape, ASM truncates coefficients of shape principal components into the bounds determined by eigenvalues. In this paper, an algorithm of modeling local appearances, called AdaBoosted ASM, and a shape parameter optimization method are proposed. In the algorithm of modeling the local appearances, we describe our novel modeling method by using AdaBoosted histogram classifiers, in which the assumption of the Gaussian distribution is not necessary. In the shape parameter optimization, we describe that there is an inadequacy on controlling shape parameters in ASM, and our novel method on how to solve it. Experimental results demonstrate that the AdaBoosted histogram classifiers improve robustness of landmark displacement greatly, and the shape parameter optimization solves the inadequacy problem of ASM on shape constraint effectively.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.7 pp.2117-2123

Publication Date: 2006/07/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.7.2117

Type of Manuscript: Special Section PAPER (Special Section on Machine Vision Applications)

Category: Shape Models

Cite this

Copy

Yuanzhong LI, Wataru ITO, "Robust Active Shape Model Using AdaBoosted Histogram Classifiers and Shape Parameter Optimization" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 7, pp. 2117-2123, July 2006, doi: 10.1093/ietisy/e89-d.7.2117.
Abstract: Active Shape Model (ASM) has been shown to be a powerful tool to aid the interpretation of images, especially in face alignment. ASM local appearance model parameter estimation is based on the assumption that residuals between model fit and data have a Gaussian distribution. Moreover, to generate an allowable face shape, ASM truncates coefficients of shape principal components into the bounds determined by eigenvalues. In this paper, an algorithm of modeling local appearances, called AdaBoosted ASM, and a shape parameter optimization method are proposed. In the algorithm of modeling the local appearances, we describe our novel modeling method by using AdaBoosted histogram classifiers, in which the assumption of the Gaussian distribution is not necessary. In the shape parameter optimization, we describe that there is an inadequacy on controlling shape parameters in ASM, and our novel method on how to solve it. Experimental results demonstrate that the AdaBoosted histogram classifiers improve robustness of landmark displacement greatly, and the shape parameter optimization solves the inadequacy problem of ASM on shape constraint effectively.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.7.2117/_p

Copy

@ARTICLE{e89-d_7_2117,
author={Yuanzhong LI, Wataru ITO, },
journal={IEICE TRANSACTIONS on Information},
title={Robust Active Shape Model Using AdaBoosted Histogram Classifiers and Shape Parameter Optimization},
year={2006},
volume={E89-D},
number={7},
pages={2117-2123},
abstract={Active Shape Model (ASM) has been shown to be a powerful tool to aid the interpretation of images, especially in face alignment. ASM local appearance model parameter estimation is based on the assumption that residuals between model fit and data have a Gaussian distribution. Moreover, to generate an allowable face shape, ASM truncates coefficients of shape principal components into the bounds determined by eigenvalues. In this paper, an algorithm of modeling local appearances, called AdaBoosted ASM, and a shape parameter optimization method are proposed. In the algorithm of modeling the local appearances, we describe our novel modeling method by using AdaBoosted histogram classifiers, in which the assumption of the Gaussian distribution is not necessary. In the shape parameter optimization, we describe that there is an inadequacy on controlling shape parameters in ASM, and our novel method on how to solve it. Experimental results demonstrate that the AdaBoosted histogram classifiers improve robustness of landmark displacement greatly, and the shape parameter optimization solves the inadequacy problem of ASM on shape constraint effectively.},
keywords={},
doi={10.1093/ietisy/e89-d.7.2117},
ISSN={1745-1361},
month={July},}

Copy

TY - JOUR
TI - Robust Active Shape Model Using AdaBoosted Histogram Classifiers and Shape Parameter Optimization
T2 - IEICE TRANSACTIONS on Information
SP - 2117
EP - 2123
AU - Yuanzhong LI
AU - Wataru ITO
PY - 2006
DO - 10.1093/ietisy/e89-d.7.2117
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2006
AB - Active Shape Model (ASM) has been shown to be a powerful tool to aid the interpretation of images, especially in face alignment. ASM local appearance model parameter estimation is based on the assumption that residuals between model fit and data have a Gaussian distribution. Moreover, to generate an allowable face shape, ASM truncates coefficients of shape principal components into the bounds determined by eigenvalues. In this paper, an algorithm of modeling local appearances, called AdaBoosted ASM, and a shape parameter optimization method are proposed. In the algorithm of modeling the local appearances, we describe our novel modeling method by using AdaBoosted histogram classifiers, in which the assumption of the Gaussian distribution is not necessary. In the shape parameter optimization, we describe that there is an inadequacy on controlling shape parameters in ASM, and our novel method on how to solve it. Experimental results demonstrate that the AdaBoosted histogram classifiers improve robustness of landmark displacement greatly, and the shape parameter optimization solves the inadequacy problem of ASM on shape constraint effectively.
ER -