Writing in the air using kinect and growing neural gas network

Mohammad Reza Aminian Heidari, Azrulhizam Shapi`i, Riza Sulaiman

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper discusses an approach which helps us to recognize English language characters which are written in the air by hands. This method is done by using Kinect camera and growing neural gas network. The proposed character recognition method has three main steps: preprocessing, training and recognition. The system and the proposed method can be considered from two aspects: (a) runtime, and (b) accuracy. One of the main goals in this method is to provide noise tolerance which is necessary for these kinds of methods. IN addition, it has influence upon accuracy rate because the proposed method can remove more outliers. The results show that the proposed method provides good results with the accuracy rate of 95.54%, 97.86% and 99.08% for lower case letters, upper case letters and digits respectively.

Original languageEnglish
Pages (from-to)111-114
Number of pages4
JournalJurnal Teknologi
Volume72
Issue number5
Publication statusPublished - 2015

Fingerprint

Character recognition
Cameras
Air
Gases

Keywords

  • Growing neural gas
  • Kinect
  • Multi-layer perceptron network

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Writing in the air using kinect and growing neural gas network. / Heidari, Mohammad Reza Aminian; Shapi`i, Azrulhizam; Sulaiman, Riza.

In: Jurnal Teknologi, Vol. 72, No. 5, 2015, p. 111-114.

Research output: Contribution to journalArticle

@article{0d8e986d6cd947b9a7ec549aa2c64b84,
title = "Writing in the air using kinect and growing neural gas network",
abstract = "This paper discusses an approach which helps us to recognize English language characters which are written in the air by hands. This method is done by using Kinect camera and growing neural gas network. The proposed character recognition method has three main steps: preprocessing, training and recognition. The system and the proposed method can be considered from two aspects: (a) runtime, and (b) accuracy. One of the main goals in this method is to provide noise tolerance which is necessary for these kinds of methods. IN addition, it has influence upon accuracy rate because the proposed method can remove more outliers. The results show that the proposed method provides good results with the accuracy rate of 95.54{\%}, 97.86{\%} and 99.08{\%} for lower case letters, upper case letters and digits respectively.",
keywords = "Growing neural gas, Kinect, Multi-layer perceptron network",
author = "Heidari, {Mohammad Reza Aminian} and Azrulhizam Shapi`i and Riza Sulaiman",
year = "2015",
language = "English",
volume = "72",
pages = "111--114",
journal = "Jurnal Teknologi",
issn = "0127-9696",
publisher = "Penerbit Universiti Teknologi Malaysia",
number = "5",

}

TY - JOUR

T1 - Writing in the air using kinect and growing neural gas network

AU - Heidari, Mohammad Reza Aminian

AU - Shapi`i, Azrulhizam

AU - Sulaiman, Riza

PY - 2015

Y1 - 2015

N2 - This paper discusses an approach which helps us to recognize English language characters which are written in the air by hands. This method is done by using Kinect camera and growing neural gas network. The proposed character recognition method has three main steps: preprocessing, training and recognition. The system and the proposed method can be considered from two aspects: (a) runtime, and (b) accuracy. One of the main goals in this method is to provide noise tolerance which is necessary for these kinds of methods. IN addition, it has influence upon accuracy rate because the proposed method can remove more outliers. The results show that the proposed method provides good results with the accuracy rate of 95.54%, 97.86% and 99.08% for lower case letters, upper case letters and digits respectively.

AB - This paper discusses an approach which helps us to recognize English language characters which are written in the air by hands. This method is done by using Kinect camera and growing neural gas network. The proposed character recognition method has three main steps: preprocessing, training and recognition. The system and the proposed method can be considered from two aspects: (a) runtime, and (b) accuracy. One of the main goals in this method is to provide noise tolerance which is necessary for these kinds of methods. IN addition, it has influence upon accuracy rate because the proposed method can remove more outliers. The results show that the proposed method provides good results with the accuracy rate of 95.54%, 97.86% and 99.08% for lower case letters, upper case letters and digits respectively.

KW - Growing neural gas

KW - Kinect

KW - Multi-layer perceptron network

UR - http://www.scopus.com/inward/record.url?scp=84922261293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922261293&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84922261293

VL - 72

SP - 111

EP - 114

JO - Jurnal Teknologi

JF - Jurnal Teknologi

SN - 0127-9696

IS - 5

ER -