A sign language to text converter using leap motion

Fazlur Rahman Khan; Huey Fang Ong; Nurhidayah Bahar

doi:10.18517/ijaseit.6.6.1252

A sign language to text converter using leap motion

Fazlur Rahman Khan, Huey Fang Ong, Nurhidayah Bahar

Research output: Contribution to journal › Article › Research › peer-review

16 Citations (Scopus)

Abstract

This paper presents a prototype that can convert sign language into text. A Leap Motion controller was utilised as an interface for hand motion tracking without the need of wearing any external instruments. Three recognition techniques were employed to measure the performance of the prototype, namely the Geometric Template Matching, Artificial Neural Network and Cross Correlation. 26 alphabets from American Sign Language were chosen for training and testing the proposed prototype. The experimental results showed that Geometric Template Matching achieved the highest recognition accuracy compared to the other recognition techniques.

Original language	English
Pages (from-to)	1089-1095
Number of pages	7
Journal	International Journal on Advanced Science, Engineering and Information Technology
Volume	6
Issue number	6
DOIs	https://doi.org/10.18517/ijaseit.6.6.1252
Publication status	Published - 2016
Externally published	Yes

Keywords

American sign language
Artificial neural network
Cross correlation
Geometric template matching
Leap motion
Sign language to text

Access to Document

10.18517/ijaseit.6.6.1252

344571465-oaFinal published version, 1.04 MB

Cite this

@article{ceeb60fbdb014c32aae79359836b1d8e,

title = "A sign language to text converter using leap motion",

abstract = "This paper presents a prototype that can convert sign language into text. A Leap Motion controller was utilised as an interface for hand motion tracking without the need of wearing any external instruments. Three recognition techniques were employed to measure the performance of the prototype, namely the Geometric Template Matching, Artificial Neural Network and Cross Correlation. 26 alphabets from American Sign Language were chosen for training and testing the proposed prototype. The experimental results showed that Geometric Template Matching achieved the highest recognition accuracy compared to the other recognition techniques.",

keywords = "American sign language, Artificial neural network, Cross correlation, Geometric template matching, Leap motion, Sign language to text",

author = "Khan, {Fazlur Rahman} and Ong, {Huey Fang} and Nurhidayah Bahar",

year = "2016",

doi = "10.18517/ijaseit.6.6.1252",

language = "English",

volume = "6",

pages = "1089--1095",

journal = "International Journal on Advanced Science, Engineering and Information Technology",

issn = "2088-5334",

publisher = "Indonesian Society for Knowledge and Human Development",

number = "6",

}

TY - JOUR

T1 - A sign language to text converter using leap motion

AU - Khan, Fazlur Rahman

AU - Ong, Huey Fang

AU - Bahar, Nurhidayah

PY - 2016

Y1 - 2016

N2 - This paper presents a prototype that can convert sign language into text. A Leap Motion controller was utilised as an interface for hand motion tracking without the need of wearing any external instruments. Three recognition techniques were employed to measure the performance of the prototype, namely the Geometric Template Matching, Artificial Neural Network and Cross Correlation. 26 alphabets from American Sign Language were chosen for training and testing the proposed prototype. The experimental results showed that Geometric Template Matching achieved the highest recognition accuracy compared to the other recognition techniques.

AB - This paper presents a prototype that can convert sign language into text. A Leap Motion controller was utilised as an interface for hand motion tracking without the need of wearing any external instruments. Three recognition techniques were employed to measure the performance of the prototype, namely the Geometric Template Matching, Artificial Neural Network and Cross Correlation. 26 alphabets from American Sign Language were chosen for training and testing the proposed prototype. The experimental results showed that Geometric Template Matching achieved the highest recognition accuracy compared to the other recognition techniques.

KW - American sign language

KW - Artificial neural network

KW - Cross correlation

KW - Geometric template matching

KW - Leap motion

KW - Sign language to text

UR - http://www.scopus.com/inward/record.url?scp=85010197176&partnerID=8YFLogxK

U2 - 10.18517/ijaseit.6.6.1252

DO - 10.18517/ijaseit.6.6.1252

M3 - Article

AN - SCOPUS:85010197176

SN - 2088-5334

VL - 6

SP - 1089

EP - 1095

JO - International Journal on Advanced Science, Engineering and Information Technology

JF - International Journal on Advanced Science, Engineering and Information Technology

IS - 6

ER -

A sign language to text converter using leap motion

Abstract

Keywords

Access to Document

Other files and links

Cite this