Procedings of the British Machine Vision Conference 2004 2004
DOI: 10.5244/c.18.28
|View full text |Cite
|
Sign up to set email alerts
|

HMM and IOHMM for the Recognition of Mono- and Bi-Manual 3D Hand Gestures

Abstract: In this paper, we address the problem of the recognition of isolated complex mono-and bi-manual hand gestures. In the proposed system, hand gestures are represented by the 3D trajectories of blobs obtained by tracking colored body parts. In this paper, we study the results obtained on a complex database of mono-and bi-manual gestures. These results are obtained by using Input/Output Hidden Markov Model (IOHMM), implemented within the framework of an open source machine learning library, and are compared to Hid… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
12
0

Year Published

2005
2005
2015
2015

Publication Types

Select...
5
2
2

Relationship

0
9

Authors

Journals

citations
Cited by 26 publications
(12 citation statements)
references
References 15 publications
0
12
0
Order By: Relevance
“…A survey on human body tracking is given in [12]. Hand gesture recognition is reviewed in [13] and a 3-D gesture recognition system is presented in [14]. Tracking the user's face and estimating its pose from monocular camera views is another important issue.…”
Section: Video Analysis Of Human Gesturesmentioning
confidence: 99%
“…A survey on human body tracking is given in [12]. Hand gesture recognition is reviewed in [13] and a 3-D gesture recognition system is presented in [14]. Tracking the user's face and estimating its pose from monocular camera views is another important issue.…”
Section: Video Analysis Of Human Gesturesmentioning
confidence: 99%
“…The systems stated below have used non-structured gestures to test their developed algorithms. Just et al (2004) have proposed a hand gesture recognition using 3D trajectories of hands. The results obtained on a complex background using Input/output HMM (IOHMM).Their system were able to reach an accuracy of 74% on isolated complex mono and bi-manual hand gestures.…”
Section: General Non-structured Gestures Recognition Systems Using Hmmmentioning
confidence: 99%
“…High level features are preferred because of their compact representation and ease of describing gestures from a structural approach. In some studies [3] [4] [5] anchor points, color gloves and other sensors are used to extract different features, but these methods are rather invasive and reduce considerably the naturalness of gestures. More recently, in [6] fingertips are obtained by analyzing curvature segments extracted from contours, using an approach similar to that in [7].…”
Section: Introductionmentioning
confidence: 99%