We present a method to track and recognize shape-changing hand gestures simultaneously. The switching linear model using active contour model well corresponds to temporal shapes and motions of hands. However, inference in the switching linear model is computationally intractable, and therefore the learning process cannot be performed via the exact EM (Expectation Maximization) algorithm. Thus, we present an approximate EM algorithm using a collapsing method in which some Gaussians are merged into a single Gaussian. Tracking is performed through the forward algorithm based on Kalman filtering and the collapsing method. We also present a regularized smoothing, which plays a role of reducing jump changes between the training sequences of shape vectors representing complex-variable hand shapes. The recognition process is performed by the selection of a model with the maximum likelihood from some trained models while tracking is being performed. Experiments for several shape-changing hand gestures are demonstrated.
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
Mun-Ho JEONG, Yoshinori KUNO, Nobutaka SHIMADA, Yoshiaki SHIRAI, "Recognition of Shape-Changing Hand Gestures" in IEICE TRANSACTIONS on Information,
vol. E85-D, no. 10, pp. 1678-1687, October 2002, doi: .
Abstract: We present a method to track and recognize shape-changing hand gestures simultaneously. The switching linear model using active contour model well corresponds to temporal shapes and motions of hands. However, inference in the switching linear model is computationally intractable, and therefore the learning process cannot be performed via the exact EM (Expectation Maximization) algorithm. Thus, we present an approximate EM algorithm using a collapsing method in which some Gaussians are merged into a single Gaussian. Tracking is performed through the forward algorithm based on Kalman filtering and the collapsing method. We also present a regularized smoothing, which plays a role of reducing jump changes between the training sequences of shape vectors representing complex-variable hand shapes. The recognition process is performed by the selection of a model with the maximum likelihood from some trained models while tracking is being performed. Experiments for several shape-changing hand gestures are demonstrated.
URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_10_1678/_p
Copy
@ARTICLE{e85-d_10_1678,
author={Mun-Ho JEONG, Yoshinori KUNO, Nobutaka SHIMADA, Yoshiaki SHIRAI, },
journal={IEICE TRANSACTIONS on Information},
title={Recognition of Shape-Changing Hand Gestures},
year={2002},
volume={E85-D},
number={10},
pages={1678-1687},
abstract={We present a method to track and recognize shape-changing hand gestures simultaneously. The switching linear model using active contour model well corresponds to temporal shapes and motions of hands. However, inference in the switching linear model is computationally intractable, and therefore the learning process cannot be performed via the exact EM (Expectation Maximization) algorithm. Thus, we present an approximate EM algorithm using a collapsing method in which some Gaussians are merged into a single Gaussian. Tracking is performed through the forward algorithm based on Kalman filtering and the collapsing method. We also present a regularized smoothing, which plays a role of reducing jump changes between the training sequences of shape vectors representing complex-variable hand shapes. The recognition process is performed by the selection of a model with the maximum likelihood from some trained models while tracking is being performed. Experiments for several shape-changing hand gestures are demonstrated.},
keywords={},
doi={},
ISSN={},
month={October},}
Copy
TY - JOUR
TI - Recognition of Shape-Changing Hand Gestures
T2 - IEICE TRANSACTIONS on Information
SP - 1678
EP - 1687
AU - Mun-Ho JEONG
AU - Yoshinori KUNO
AU - Nobutaka SHIMADA
AU - Yoshiaki SHIRAI
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E85-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2002
AB - We present a method to track and recognize shape-changing hand gestures simultaneously. The switching linear model using active contour model well corresponds to temporal shapes and motions of hands. However, inference in the switching linear model is computationally intractable, and therefore the learning process cannot be performed via the exact EM (Expectation Maximization) algorithm. Thus, we present an approximate EM algorithm using a collapsing method in which some Gaussians are merged into a single Gaussian. Tracking is performed through the forward algorithm based on Kalman filtering and the collapsing method. We also present a regularized smoothing, which plays a role of reducing jump changes between the training sequences of shape vectors representing complex-variable hand shapes. The recognition process is performed by the selection of a model with the maximum likelihood from some trained models while tracking is being performed. Experiments for several shape-changing hand gestures are demonstrated.
ER -