Active Shape Model (ASM) is a powerful statistical tool for image interpretation, especially in face alignment. In the standard ASM, local appearances are described by intensity profiles, and the model parameter estimation is based on the assumption that the profiles follow a Gaussian distribution. It suffers from variations of poses, illumination, expressions and obstacles. In this paper, an improved ASM framework, GentleBoost based SIFT-ASM is proposed. Local appearances of landmarks are originally represented by SIFT (Scale-Invariant Feature Transform) descriptors, which are gradient orientation histograms based representations of image neighborhood. They can provide more robust and accurate guidance for search than grey-level profiles. Moreover, GentleBoost classifiers are applied to model and search the SIFT features instead of the unnecessary assumption of Gaussian distribution. Experimental results show that SIFT-ASM significantly outperforms the original ASM in aligning and localizing facial features.
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.
Copy
Zisheng LI, Jun-ichi IMAI, Masahide KANEKO, "Face Alignment Based on Statistical Models Using SIFT Descriptors" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 12, pp. 3336-3343, December 2009, doi: 10.1587/transfun.E92.A.3336.
Abstract: Active Shape Model (ASM) is a powerful statistical tool for image interpretation, especially in face alignment. In the standard ASM, local appearances are described by intensity profiles, and the model parameter estimation is based on the assumption that the profiles follow a Gaussian distribution. It suffers from variations of poses, illumination, expressions and obstacles. In this paper, an improved ASM framework, GentleBoost based SIFT-ASM is proposed. Local appearances of landmarks are originally represented by SIFT (Scale-Invariant Feature Transform) descriptors, which are gradient orientation histograms based representations of image neighborhood. They can provide more robust and accurate guidance for search than grey-level profiles. Moreover, GentleBoost classifiers are applied to model and search the SIFT features instead of the unnecessary assumption of Gaussian distribution. Experimental results show that SIFT-ASM significantly outperforms the original ASM in aligning and localizing facial features.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.3336/_p
Copy
@ARTICLE{e92-a_12_3336,
author={Zisheng LI, Jun-ichi IMAI, Masahide KANEKO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Face Alignment Based on Statistical Models Using SIFT Descriptors},
year={2009},
volume={E92-A},
number={12},
pages={3336-3343},
abstract={Active Shape Model (ASM) is a powerful statistical tool for image interpretation, especially in face alignment. In the standard ASM, local appearances are described by intensity profiles, and the model parameter estimation is based on the assumption that the profiles follow a Gaussian distribution. It suffers from variations of poses, illumination, expressions and obstacles. In this paper, an improved ASM framework, GentleBoost based SIFT-ASM is proposed. Local appearances of landmarks are originally represented by SIFT (Scale-Invariant Feature Transform) descriptors, which are gradient orientation histograms based representations of image neighborhood. They can provide more robust and accurate guidance for search than grey-level profiles. Moreover, GentleBoost classifiers are applied to model and search the SIFT features instead of the unnecessary assumption of Gaussian distribution. Experimental results show that SIFT-ASM significantly outperforms the original ASM in aligning and localizing facial features.},
keywords={},
doi={10.1587/transfun.E92.A.3336},
ISSN={1745-1337},
month={December},}
Copy
TY - JOUR
TI - Face Alignment Based on Statistical Models Using SIFT Descriptors
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 3336
EP - 3343
AU - Zisheng LI
AU - Jun-ichi IMAI
AU - Masahide KANEKO
PY - 2009
DO - 10.1587/transfun.E92.A.3336
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E92-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2009
AB - Active Shape Model (ASM) is a powerful statistical tool for image interpretation, especially in face alignment. In the standard ASM, local appearances are described by intensity profiles, and the model parameter estimation is based on the assumption that the profiles follow a Gaussian distribution. It suffers from variations of poses, illumination, expressions and obstacles. In this paper, an improved ASM framework, GentleBoost based SIFT-ASM is proposed. Local appearances of landmarks are originally represented by SIFT (Scale-Invariant Feature Transform) descriptors, which are gradient orientation histograms based representations of image neighborhood. They can provide more robust and accurate guidance for search than grey-level profiles. Moreover, GentleBoost classifiers are applied to model and search the SIFT features instead of the unnecessary assumption of Gaussian distribution. Experimental results show that SIFT-ASM significantly outperforms the original ASM in aligning and localizing facial features.
ER -