Abstract
This paper presents a Kinect-based midair handwritten number recognition that can be used to dial a phone number and set a countdown timer. When cooking in the kitchen, making a phone call or setting a kitchen timer is often inconvenient. This number recognition system was based on previous studies of television remote controls. An average recognition accuracy of 94.6% was achieved for each number by using multiple segments and scaled coding. Two Android apps were developed for the recognition system. In addition, the four direction recognition system developed in a previous study was improved, increasing the recognition reliability. Experimental results verified the effectiveness of the system.
Original language | English |
---|---|
Article number | 6974236 |
Pages (from-to) | 2127-2130 |
Number of pages | 4 |
Journal | Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics |
Volume | 2014-January |
Issue number | January |
DOIs | |
Publication status | Published - 2014 Jan 1 |
Event | 2014 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2014 - San Diego, United States Duration: 2014 Oct 5 → 2014 Oct 8 |
Fingerprint
Keywords
- Android
- Hand gesture recognition
- Handwritten number recognition
- Kinect
- Support vector machine
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Control and Systems Engineering
- Human-Computer Interaction
Cite this
Kinect-based midair handwritten number recognition system for dialing numbers and setting a timer. / Su, Chung-Yen; Huang, Fu An; Shih, Che Yang; Chen, Yu Tang.
In: Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, Vol. 2014-January, No. January, 6974236, 01.01.2014, p. 2127-2130.Research output: Contribution to journal › Conference article
}
TY - JOUR
T1 - Kinect-based midair handwritten number recognition system for dialing numbers and setting a timer
AU - Su, Chung-Yen
AU - Huang, Fu An
AU - Shih, Che Yang
AU - Chen, Yu Tang
PY - 2014/1/1
Y1 - 2014/1/1
N2 - This paper presents a Kinect-based midair handwritten number recognition that can be used to dial a phone number and set a countdown timer. When cooking in the kitchen, making a phone call or setting a kitchen timer is often inconvenient. This number recognition system was based on previous studies of television remote controls. An average recognition accuracy of 94.6% was achieved for each number by using multiple segments and scaled coding. Two Android apps were developed for the recognition system. In addition, the four direction recognition system developed in a previous study was improved, increasing the recognition reliability. Experimental results verified the effectiveness of the system.
AB - This paper presents a Kinect-based midair handwritten number recognition that can be used to dial a phone number and set a countdown timer. When cooking in the kitchen, making a phone call or setting a kitchen timer is often inconvenient. This number recognition system was based on previous studies of television remote controls. An average recognition accuracy of 94.6% was achieved for each number by using multiple segments and scaled coding. Two Android apps were developed for the recognition system. In addition, the four direction recognition system developed in a previous study was improved, increasing the recognition reliability. Experimental results verified the effectiveness of the system.
KW - Android
KW - Hand gesture recognition
KW - Handwritten number recognition
KW - Kinect
KW - Support vector machine
UR - http://www.scopus.com/inward/record.url?scp=84938153054&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84938153054&partnerID=8YFLogxK
U2 - 10.1109/smc.2014.6974236
DO - 10.1109/smc.2014.6974236
M3 - Conference article
AN - SCOPUS:84938153054
VL - 2014-January
SP - 2127
EP - 2130
JO - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
JF - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
SN - 1062-922X
IS - January
M1 - 6974236
ER -