Home > Research > Publications & Outputs > Gestimator

Links

Text available via DOI:

View graph of relations

Gestimator: Shape and Stroke Similarity Based Gesture Recognition

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Gestimator: Shape and Stroke Similarity Based Gesture Recognition. / Ye, Yina; Nurmi, Petteri.
ICMI '15 Proceedings of the 2015 ACM on International Conference on Multimodal Interaction. New York, NY, USA: ACM, 2015. p. 219-226.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Ye, Y & Nurmi, P 2015, Gestimator: Shape and Stroke Similarity Based Gesture Recognition. in ICMI '15 Proceedings of the 2015 ACM on International Conference on Multimodal Interaction. ACM, New York, NY, USA, pp. 219-226. https://doi.org/10.1145/2818346.2820734

APA

Ye, Y., & Nurmi, P. (2015). Gestimator: Shape and Stroke Similarity Based Gesture Recognition. In ICMI '15 Proceedings of the 2015 ACM on International Conference on Multimodal Interaction (pp. 219-226). ACM. https://doi.org/10.1145/2818346.2820734

Vancouver

Ye Y, Nurmi P. Gestimator: Shape and Stroke Similarity Based Gesture Recognition. In ICMI '15 Proceedings of the 2015 ACM on International Conference on Multimodal Interaction. New York, NY, USA: ACM. 2015. p. 219-226 doi: 10.1145/2818346.2820734

Author

Ye, Yina ; Nurmi, Petteri. / Gestimator : Shape and Stroke Similarity Based Gesture Recognition. ICMI '15 Proceedings of the 2015 ACM on International Conference on Multimodal Interaction. New York, NY, USA : ACM, 2015. pp. 219-226

Bibtex

@inproceedings{f429d9a61a034830a2c70d62f156fe20,
title = "Gestimator: Shape and Stroke Similarity Based Gesture Recognition",
abstract = "Template-based approaches are currently the most popular gesture recognition solution for interactive systems as they provide accurate and runtime efficient performance in a wide range of applications. The basic idea in these approaches is to measure similarity between a user gesture and a set of pre-recorded templates, and to determine the appropriate gesture type using a nearest neighbor classifier. While simple and elegant, this approach performs well only when the gestures are relatively simple and unambiguous. In increasingly many scenarios, such as authentication, interactive learning, and health care applications, the gestures of interest are complex, consist of multiple sub-strokes, and closely resemble other gestures. Merely considering the shape of the gesture is not sufficient for these scenarios, and robust identification of the constituent sequence of sub-strokes is also required. The present paper contributes by introducing Gestimator, a novel gesture recognizer that combines shape and stroke-based similarity into a sequential classification framework for robust gesture recognition. Experiments carried out using three datasets demonstrate significant performance gains compared to current state-of-the-art techniques. The performance improvements are highest for complex gestures, but consistent improvements are achieved even for simple and widely studied gesture types.",
keywords = "gesture recognition, pattern matching, segmentation",
author = "Yina Ye and Petteri Nurmi",
year = "2015",
month = nov,
day = "9",
doi = "10.1145/2818346.2820734",
language = "English",
isbn = "9781450339124",
pages = "219--226",
booktitle = "ICMI '15 Proceedings of the 2015 ACM on International Conference on Multimodal Interaction",
publisher = "ACM",

}

RIS

TY - GEN

T1 - Gestimator

T2 - Shape and Stroke Similarity Based Gesture Recognition

AU - Ye, Yina

AU - Nurmi, Petteri

PY - 2015/11/9

Y1 - 2015/11/9

N2 - Template-based approaches are currently the most popular gesture recognition solution for interactive systems as they provide accurate and runtime efficient performance in a wide range of applications. The basic idea in these approaches is to measure similarity between a user gesture and a set of pre-recorded templates, and to determine the appropriate gesture type using a nearest neighbor classifier. While simple and elegant, this approach performs well only when the gestures are relatively simple and unambiguous. In increasingly many scenarios, such as authentication, interactive learning, and health care applications, the gestures of interest are complex, consist of multiple sub-strokes, and closely resemble other gestures. Merely considering the shape of the gesture is not sufficient for these scenarios, and robust identification of the constituent sequence of sub-strokes is also required. The present paper contributes by introducing Gestimator, a novel gesture recognizer that combines shape and stroke-based similarity into a sequential classification framework for robust gesture recognition. Experiments carried out using three datasets demonstrate significant performance gains compared to current state-of-the-art techniques. The performance improvements are highest for complex gestures, but consistent improvements are achieved even for simple and widely studied gesture types.

AB - Template-based approaches are currently the most popular gesture recognition solution for interactive systems as they provide accurate and runtime efficient performance in a wide range of applications. The basic idea in these approaches is to measure similarity between a user gesture and a set of pre-recorded templates, and to determine the appropriate gesture type using a nearest neighbor classifier. While simple and elegant, this approach performs well only when the gestures are relatively simple and unambiguous. In increasingly many scenarios, such as authentication, interactive learning, and health care applications, the gestures of interest are complex, consist of multiple sub-strokes, and closely resemble other gestures. Merely considering the shape of the gesture is not sufficient for these scenarios, and robust identification of the constituent sequence of sub-strokes is also required. The present paper contributes by introducing Gestimator, a novel gesture recognizer that combines shape and stroke-based similarity into a sequential classification framework for robust gesture recognition. Experiments carried out using three datasets demonstrate significant performance gains compared to current state-of-the-art techniques. The performance improvements are highest for complex gestures, but consistent improvements are achieved even for simple and widely studied gesture types.

KW - gesture recognition

KW - pattern matching

KW - segmentation

U2 - 10.1145/2818346.2820734

DO - 10.1145/2818346.2820734

M3 - Conference contribution/Paper

SN - 9781450339124

SP - 219

EP - 226

BT - ICMI '15 Proceedings of the 2015 ACM on International Conference on Multimodal Interaction

PB - ACM

CY - New York, NY, USA

ER -