Rule based trajectory segmentation applied to an HMM-based isolated hand gesture recognizer

Jounghoon Beh, David Han, Hanseok Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we propose a simple but effective method of modeling hand drawn gestures based on their angles and curvature of the trajectories. Each gesture trajectory is composed of a unique series of straight and curved segments. In our Hidden Markov Model (HMM) implementation, these gestures are modeled as connected series of states analogous to series of phonemes in speech recognition. The novelty of the work presented here is the automated process we developed in segmenting gesture trajectories based on a simple set of threshold values in curvature and accumulated curvature angle. In order to represent its angular distribution of each separated states, the von Mises distribution is used. Likelihood based state segmentation was implemented in addition to the threshold based method to ensure that gesture sets are segmented consistently. The proposed method can separate each angular state of training data at the initialization step, thus providing a solution to mitigate ambiguity on initializing HMM. For comparative studies, the proposed automated state segmentation based HMM initialization was considered over the conventional method. Effectiveness of the proposed method is shown as it achieved higher recognition rates in experiments over conventional methods.

Original languageEnglish
Title of host publicationCommunications in Computer and Information Science
Pages146-150
Number of pages5
Volume174 CCIS
EditionPART 2
DOIs
Publication statusPublished - 2011 Jul 21
Event14th International Conference on Human-Computer Interaction, HCI International 2011 - Orlando, FL, United States
Duration: 2011 Jul 92011 Jul 14

Publication series

NameCommunications in Computer and Information Science
NumberPART 2
Volume174 CCIS
ISSN (Print)18650929

Other

Other14th International Conference on Human-Computer Interaction, HCI International 2011
CountryUnited States
CityOrlando, FL
Period11/7/911/7/14

Fingerprint

Hidden Markov models
Trajectories
Angular distribution
Speech recognition
Experiments

Keywords

  • hand gesture recognition
  • hidden Markov model
  • HMM initialization
  • Trajectory segmentation

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Beh, J., Han, D., & Ko, H. (2011). Rule based trajectory segmentation applied to an HMM-based isolated hand gesture recognizer. In Communications in Computer and Information Science (PART 2 ed., Vol. 174 CCIS, pp. 146-150). (Communications in Computer and Information Science; Vol. 174 CCIS, No. PART 2). https://doi.org/10.1007/978-3-642-22095-1_30

Rule based trajectory segmentation applied to an HMM-based isolated hand gesture recognizer. / Beh, Jounghoon; Han, David; Ko, Hanseok.

Communications in Computer and Information Science. Vol. 174 CCIS PART 2. ed. 2011. p. 146-150 (Communications in Computer and Information Science; Vol. 174 CCIS, No. PART 2).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Beh, J, Han, D & Ko, H 2011, Rule based trajectory segmentation applied to an HMM-based isolated hand gesture recognizer. in Communications in Computer and Information Science. PART 2 edn, vol. 174 CCIS, Communications in Computer and Information Science, no. PART 2, vol. 174 CCIS, pp. 146-150, 14th International Conference on Human-Computer Interaction, HCI International 2011, Orlando, FL, United States, 11/7/9. https://doi.org/10.1007/978-3-642-22095-1_30
Beh J, Han D, Ko H. Rule based trajectory segmentation applied to an HMM-based isolated hand gesture recognizer. In Communications in Computer and Information Science. PART 2 ed. Vol. 174 CCIS. 2011. p. 146-150. (Communications in Computer and Information Science; PART 2). https://doi.org/10.1007/978-3-642-22095-1_30
Beh, Jounghoon ; Han, David ; Ko, Hanseok. / Rule based trajectory segmentation applied to an HMM-based isolated hand gesture recognizer. Communications in Computer and Information Science. Vol. 174 CCIS PART 2. ed. 2011. pp. 146-150 (Communications in Computer and Information Science; PART 2).
@inproceedings{8539f185ba2846b8ab235d714cc47ea0,
title = "Rule based trajectory segmentation applied to an HMM-based isolated hand gesture recognizer",
abstract = "In this paper, we propose a simple but effective method of modeling hand drawn gestures based on their angles and curvature of the trajectories. Each gesture trajectory is composed of a unique series of straight and curved segments. In our Hidden Markov Model (HMM) implementation, these gestures are modeled as connected series of states analogous to series of phonemes in speech recognition. The novelty of the work presented here is the automated process we developed in segmenting gesture trajectories based on a simple set of threshold values in curvature and accumulated curvature angle. In order to represent its angular distribution of each separated states, the von Mises distribution is used. Likelihood based state segmentation was implemented in addition to the threshold based method to ensure that gesture sets are segmented consistently. The proposed method can separate each angular state of training data at the initialization step, thus providing a solution to mitigate ambiguity on initializing HMM. For comparative studies, the proposed automated state segmentation based HMM initialization was considered over the conventional method. Effectiveness of the proposed method is shown as it achieved higher recognition rates in experiments over conventional methods.",
keywords = "hand gesture recognition, hidden Markov model, HMM initialization, Trajectory segmentation",
author = "Jounghoon Beh and David Han and Hanseok Ko",
year = "2011",
month = "7",
day = "21",
doi = "10.1007/978-3-642-22095-1_30",
language = "English",
isbn = "9783642220944",
volume = "174 CCIS",
series = "Communications in Computer and Information Science",
number = "PART 2",
pages = "146--150",
booktitle = "Communications in Computer and Information Science",
edition = "PART 2",

}

TY - GEN

T1 - Rule based trajectory segmentation applied to an HMM-based isolated hand gesture recognizer

AU - Beh, Jounghoon

AU - Han, David

AU - Ko, Hanseok

PY - 2011/7/21

Y1 - 2011/7/21

N2 - In this paper, we propose a simple but effective method of modeling hand drawn gestures based on their angles and curvature of the trajectories. Each gesture trajectory is composed of a unique series of straight and curved segments. In our Hidden Markov Model (HMM) implementation, these gestures are modeled as connected series of states analogous to series of phonemes in speech recognition. The novelty of the work presented here is the automated process we developed in segmenting gesture trajectories based on a simple set of threshold values in curvature and accumulated curvature angle. In order to represent its angular distribution of each separated states, the von Mises distribution is used. Likelihood based state segmentation was implemented in addition to the threshold based method to ensure that gesture sets are segmented consistently. The proposed method can separate each angular state of training data at the initialization step, thus providing a solution to mitigate ambiguity on initializing HMM. For comparative studies, the proposed automated state segmentation based HMM initialization was considered over the conventional method. Effectiveness of the proposed method is shown as it achieved higher recognition rates in experiments over conventional methods.

AB - In this paper, we propose a simple but effective method of modeling hand drawn gestures based on their angles and curvature of the trajectories. Each gesture trajectory is composed of a unique series of straight and curved segments. In our Hidden Markov Model (HMM) implementation, these gestures are modeled as connected series of states analogous to series of phonemes in speech recognition. The novelty of the work presented here is the automated process we developed in segmenting gesture trajectories based on a simple set of threshold values in curvature and accumulated curvature angle. In order to represent its angular distribution of each separated states, the von Mises distribution is used. Likelihood based state segmentation was implemented in addition to the threshold based method to ensure that gesture sets are segmented consistently. The proposed method can separate each angular state of training data at the initialization step, thus providing a solution to mitigate ambiguity on initializing HMM. For comparative studies, the proposed automated state segmentation based HMM initialization was considered over the conventional method. Effectiveness of the proposed method is shown as it achieved higher recognition rates in experiments over conventional methods.

KW - hand gesture recognition

KW - hidden Markov model

KW - HMM initialization

KW - Trajectory segmentation

UR - http://www.scopus.com/inward/record.url?scp=79960415732&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960415732&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-22095-1_30

DO - 10.1007/978-3-642-22095-1_30

M3 - Conference contribution

AN - SCOPUS:79960415732

SN - 9783642220944

VL - 174 CCIS

T3 - Communications in Computer and Information Science

SP - 146

EP - 150

BT - Communications in Computer and Information Science

ER -