A modified EM algorithm for hand gesture segmentation in RGB-D data

Zhaojie Ju; Yuehui Wang; Wei Zeng; Haibin Cai; Honghai Liu

doi:10.1109/FUZZ-IEEE.2014.6891777

A modified EM algorithm for hand gesture segmentation in RGB-D data

Zhaojie Ju, Yuehui Wang, Wei Zeng, Haibin Cai, Honghai Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

193 Downloads (Pure)

Abstract

This paper proposes a novel method with a modified Expectation-Maximisation (EM) Algorithm to segment hand gestures in the RGB-D data captured by Kinect. With the depth map and RGB image aligned by the genetic algorithm to estimate the key points from both depth and RGB images, a novel approach is proposed to refine the edge of the tracked hand gesture, which is used to segment the RGB image of the hand gestures, by applying a modified EM algorithm based on Bayesian networks. The experimental results demonstrated the modified EM algorithm effectively adjusts the RGB edges of the segmented hand gestures. The proposed methods have potential to improve the performance of hand gesture recognition in Human-Computer Interaction (HCI).

Original language	English
Title of host publication	Proceedings of the 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Publisher	IEEE
Pages	1736-1742
ISBN (Electronic)	978-1-4799-2072-3
DOIs	https://doi.org/10.1109/FUZZ-IEEE.2014.6891777
Publication status	Published - 8 Sep 2014
Event	2014 IEEE International Conference on Fuzzy Systems - Beijing, China Duration: 6 Jul 2014 → 11 Jul 2014

Publication series

Name
ISSN (Print)	1098-7584

Conference

Conference	2014 IEEE International Conference on Fuzzy Systems
Abbreviated title	FUZZ-IEEE 2014
Country/Territory	China
City	Beijing
Period	6/07/14 → 11/07/14

Access to Document

10.1109/FUZZ-IEEE.2014.6891777

A Modified EM Algorithm for Hand Gesture Segmentation in
© © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 2.91 MB

Cite this

@inproceedings{15bc7fc588ea46238393ecfe9c7147b3,

title = "A modified EM algorithm for hand gesture segmentation in RGB-D data",

abstract = "This paper proposes a novel method with a modified Expectation-Maximisation (EM) Algorithm to segment hand gestures in the RGB-D data captured by Kinect. With the depth map and RGB image aligned by the genetic algorithm to estimate the key points from both depth and RGB images, a novel approach is proposed to refine the edge of the tracked hand gesture, which is used to segment the RGB image of the hand gestures, by applying a modified EM algorithm based on Bayesian networks. The experimental results demonstrated the modified EM algorithm effectively adjusts the RGB edges of the segmented hand gestures. The proposed methods have potential to improve the performance of hand gesture recognition in Human-Computer Interaction (HCI).",

author = "Zhaojie Ju and Yuehui Wang and Wei Zeng and Haibin Cai and Honghai Liu",

year = "2014",

month = sep,

day = "8",

doi = "10.1109/FUZZ-IEEE.2014.6891777",

language = "English",

publisher = "IEEE",

pages = "1736--1742",

booktitle = "Proceedings of the 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)",

note = "2014 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2014 ; Conference date: 06-07-2014 Through 11-07-2014",

}

TY - GEN

T1 - A modified EM algorithm for hand gesture segmentation in RGB-D data

AU - Ju, Zhaojie

AU - Wang, Yuehui

AU - Zeng, Wei

AU - Cai, Haibin

AU - Liu, Honghai

PY - 2014/9/8

Y1 - 2014/9/8

N2 - This paper proposes a novel method with a modified Expectation-Maximisation (EM) Algorithm to segment hand gestures in the RGB-D data captured by Kinect. With the depth map and RGB image aligned by the genetic algorithm to estimate the key points from both depth and RGB images, a novel approach is proposed to refine the edge of the tracked hand gesture, which is used to segment the RGB image of the hand gestures, by applying a modified EM algorithm based on Bayesian networks. The experimental results demonstrated the modified EM algorithm effectively adjusts the RGB edges of the segmented hand gestures. The proposed methods have potential to improve the performance of hand gesture recognition in Human-Computer Interaction (HCI).

AB - This paper proposes a novel method with a modified Expectation-Maximisation (EM) Algorithm to segment hand gestures in the RGB-D data captured by Kinect. With the depth map and RGB image aligned by the genetic algorithm to estimate the key points from both depth and RGB images, a novel approach is proposed to refine the edge of the tracked hand gesture, which is used to segment the RGB image of the hand gestures, by applying a modified EM algorithm based on Bayesian networks. The experimental results demonstrated the modified EM algorithm effectively adjusts the RGB edges of the segmented hand gestures. The proposed methods have potential to improve the performance of hand gesture recognition in Human-Computer Interaction (HCI).

UR - https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=32436

U2 - 10.1109/FUZZ-IEEE.2014.6891777

DO - 10.1109/FUZZ-IEEE.2014.6891777

M3 - Conference contribution

SP - 1736

EP - 1742

BT - Proceedings of the 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

PB - IEEE

T2 - 2014 IEEE International Conference on Fuzzy Systems

Y2 - 6 July 2014 through 11 July 2014

ER -

A modified EM algorithm for hand gesture segmentation in RGB-D data

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this