Keystroke recognition for virtual keyboard

Jani Mantyjarvi; Jussi Koivumaki; Petri Vuori

doi:10.1109/ICME.2002.1035630

Keystroke recognition for virtual keyboard

Jani Mantyjarvi^*
, Jussi Koivumaki
, Petri Vuori

^*Corresponding author for this work

Not published at VTT

Nokia Oyj

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

32 Citations (Scopus)

Abstract

The progress in the field of human-computer interaction with hand held electronic devices, such as, personal digital assistants (PDAs) and mobile phones searches for new interaction techniques. Proximity sensing extends the concept of computer-human interaction beyond actual physical contact with a device. In this paper, a virtual keyboard implementation is presented and keystroke recognition experiments with the keyboard utilizing proximity measurements are described. An infrared (IR) transceiver array is used for detecting the proximity of a finger. Keystroke recognition accuracy is examined with k-nearest neighbor (k-NN) classifier while a multilayer perceptron (MLP) classifier is designed for online implementation. Experiments and results of keystroke classification are presented for both classifiers. The recognition accuracy, which is between 78% and 99% for k-NN classifier and between 69% and 96% for MLP classifier, depends mainly on the location of a specific key on the keyboard area.

Original language	English
Title of host publication	Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	429-432
Number of pages	4
Volume	2
ISBN (Print)	0-7803-7304-9
DOIs	https://doi.org/10.1109/ICME.2002.1035630
Publication status	Published - 1 Jan 2002
MoE publication type	A4 Article in a conference publication
Event	2002 IEEE International Conference on Multimedia and Expo, ICME 2002 - Lausanne, Switzerland Duration: 26 Aug 2002 → 29 Aug 2002

Conference

Conference	2002 IEEE International Conference on Multimedia and Expo, ICME 2002
Country/Territory	Switzerland
City	Lausanne
Period	26/08/02 → 29/08/02

Access to Document

10.1109/ICME.2002.1035630

Cite this

@inproceedings{6057583508034e9eb12abcb9bfc5cba9,

title = "Keystroke recognition for virtual keyboard",

abstract = "The progress in the field of human-computer interaction with hand held electronic devices, such as, personal digital assistants (PDAs) and mobile phones searches for new interaction techniques. Proximity sensing extends the concept of computer-human interaction beyond actual physical contact with a device. In this paper, a virtual keyboard implementation is presented and keystroke recognition experiments with the keyboard utilizing proximity measurements are described. An infrared (IR) transceiver array is used for detecting the proximity of a finger. Keystroke recognition accuracy is examined with k-nearest neighbor (k-NN) classifier while a multilayer perceptron (MLP) classifier is designed for online implementation. Experiments and results of keystroke classification are presented for both classifiers. The recognition accuracy, which is between 78\% and 99\% for k-NN classifier and between 69\% and 96\% for MLP classifier, depends mainly on the location of a specific key on the keyboard area.",

author = "Jani Mantyjarvi and Jussi Koivumaki and Petri Vuori",

year = "2002",

month = jan,

day = "1",

doi = "10.1109/ICME.2002.1035630",

language = "English",

isbn = "0-7803-7304-9",

volume = "2",

pages = "429--432",

booktitle = "Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

address = "United States",

note = "2002 IEEE International Conference on Multimedia and Expo, ICME 2002 ; Conference date: 26-08-2002 Through 29-08-2002",

}

Mantyjarvi, J, Koivumaki, J & Vuori, P 2002, Keystroke recognition for virtual keyboard. in Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002. vol. 2, 1035630, IEEE Institute of Electrical and Electronic Engineers, pp. 429-432, 2002 IEEE International Conference on Multimedia and Expo, ICME 2002, Lausanne, Switzerland, 26/08/02. https://doi.org/10.1109/ICME.2002.1035630

Keystroke recognition for virtual keyboard. / Mantyjarvi, Jani; Koivumaki, Jussi; Vuori, Petri.
Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002. Vol. 2 IEEE Institute of Electrical and Electronic Engineers, 2002. p. 429-432 1035630.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Keystroke recognition for virtual keyboard

AU - Mantyjarvi, Jani

AU - Koivumaki, Jussi

AU - Vuori, Petri

PY - 2002/1/1

Y1 - 2002/1/1

N2 - The progress in the field of human-computer interaction with hand held electronic devices, such as, personal digital assistants (PDAs) and mobile phones searches for new interaction techniques. Proximity sensing extends the concept of computer-human interaction beyond actual physical contact with a device. In this paper, a virtual keyboard implementation is presented and keystroke recognition experiments with the keyboard utilizing proximity measurements are described. An infrared (IR) transceiver array is used for detecting the proximity of a finger. Keystroke recognition accuracy is examined with k-nearest neighbor (k-NN) classifier while a multilayer perceptron (MLP) classifier is designed for online implementation. Experiments and results of keystroke classification are presented for both classifiers. The recognition accuracy, which is between 78% and 99% for k-NN classifier and between 69% and 96% for MLP classifier, depends mainly on the location of a specific key on the keyboard area.

AB - The progress in the field of human-computer interaction with hand held electronic devices, such as, personal digital assistants (PDAs) and mobile phones searches for new interaction techniques. Proximity sensing extends the concept of computer-human interaction beyond actual physical contact with a device. In this paper, a virtual keyboard implementation is presented and keystroke recognition experiments with the keyboard utilizing proximity measurements are described. An infrared (IR) transceiver array is used for detecting the proximity of a finger. Keystroke recognition accuracy is examined with k-nearest neighbor (k-NN) classifier while a multilayer perceptron (MLP) classifier is designed for online implementation. Experiments and results of keystroke classification are presented for both classifiers. The recognition accuracy, which is between 78% and 99% for k-NN classifier and between 69% and 96% for MLP classifier, depends mainly on the location of a specific key on the keyboard area.

UR - https://www.scopus.com/pages/publications/84908209180

U2 - 10.1109/ICME.2002.1035630

DO - 10.1109/ICME.2002.1035630

M3 - Conference article in proceedings

AN - SCOPUS:84908209180

SN - 0-7803-7304-9

VL - 2

SP - 429

EP - 432

BT - Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002

Y2 - 26 August 2002 through 29 August 2002

ER -

Keystroke recognition for virtual keyboard

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this