Static fingerspelling recognition based on boundary tracing algorithm and chain code

Ahmad Yahya Dawod, Md. Jan Nordin, Junaidi Abdullah

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents a novel method for the detection and extraction of shape feature for fingerspelling recognition using boundary tracing and chain code. The method includes several steps such as conversion of RGB to YCbCr color space of an image and segmentation of skin pixel regions using thresholding method in order to construct binary images. Edge detection is applied and the location of candidate fingertips is estimated based on boundary tracing process and local extrema. The modified 2D chain code algorithm is then applied to the edge image to extract the fingerspelling shape feature and Support Vector Machine (SVM) is used for the classification task. The experimental findings show that the accuracy of the proposed method is 97.75% and 96.48% for alphabets and numbers, respectively.

Original languageEnglish
Title of host publicationISMSI 2018 - 2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence
PublisherAssociation for Computing Machinery
Pages104-109
Number of pages6
ISBN (Electronic)9781450364126
DOIs
Publication statusPublished - 24 Mar 2018
Event2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence, ISMSI 2018 - Phuket, Thailand
Duration: 24 Mar 201825 Mar 2018

Other

Other2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence, ISMSI 2018
CountryThailand
CityPhuket
Period24/3/1825/3/18

Fingerprint

Binary images
Edge detection
Support vector machines
Skin
Pixels
Color

Keywords

  • Chain code
  • Fingerspelling
  • Fingertips detection
  • Hand tracing
  • Shape feature

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Dawod, A. Y., Nordin, M. J., & Abdullah, J. (2018). Static fingerspelling recognition based on boundary tracing algorithm and chain code. In ISMSI 2018 - 2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence (pp. 104-109). Association for Computing Machinery. https://doi.org/10.1145/3206185.3206195

Static fingerspelling recognition based on boundary tracing algorithm and chain code. / Dawod, Ahmad Yahya; Nordin, Md. Jan; Abdullah, Junaidi.

ISMSI 2018 - 2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence. Association for Computing Machinery, 2018. p. 104-109.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dawod, AY, Nordin, MJ & Abdullah, J 2018, Static fingerspelling recognition based on boundary tracing algorithm and chain code. in ISMSI 2018 - 2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence. Association for Computing Machinery, pp. 104-109, 2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence, ISMSI 2018, Phuket, Thailand, 24/3/18. https://doi.org/10.1145/3206185.3206195
Dawod AY, Nordin MJ, Abdullah J. Static fingerspelling recognition based on boundary tracing algorithm and chain code. In ISMSI 2018 - 2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence. Association for Computing Machinery. 2018. p. 104-109 https://doi.org/10.1145/3206185.3206195
Dawod, Ahmad Yahya ; Nordin, Md. Jan ; Abdullah, Junaidi. / Static fingerspelling recognition based on boundary tracing algorithm and chain code. ISMSI 2018 - 2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence. Association for Computing Machinery, 2018. pp. 104-109
@inproceedings{5afd76b9cc784c238699b3788fd04082,
title = "Static fingerspelling recognition based on boundary tracing algorithm and chain code",
abstract = "This paper presents a novel method for the detection and extraction of shape feature for fingerspelling recognition using boundary tracing and chain code. The method includes several steps such as conversion of RGB to YCbCr color space of an image and segmentation of skin pixel regions using thresholding method in order to construct binary images. Edge detection is applied and the location of candidate fingertips is estimated based on boundary tracing process and local extrema. The modified 2D chain code algorithm is then applied to the edge image to extract the fingerspelling shape feature and Support Vector Machine (SVM) is used for the classification task. The experimental findings show that the accuracy of the proposed method is 97.75{\%} and 96.48{\%} for alphabets and numbers, respectively.",
keywords = "Chain code, Fingerspelling, Fingertips detection, Hand tracing, Shape feature",
author = "Dawod, {Ahmad Yahya} and Nordin, {Md. Jan} and Junaidi Abdullah",
year = "2018",
month = "3",
day = "24",
doi = "10.1145/3206185.3206195",
language = "English",
pages = "104--109",
booktitle = "ISMSI 2018 - 2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Static fingerspelling recognition based on boundary tracing algorithm and chain code

AU - Dawod, Ahmad Yahya

AU - Nordin, Md. Jan

AU - Abdullah, Junaidi

PY - 2018/3/24

Y1 - 2018/3/24

N2 - This paper presents a novel method for the detection and extraction of shape feature for fingerspelling recognition using boundary tracing and chain code. The method includes several steps such as conversion of RGB to YCbCr color space of an image and segmentation of skin pixel regions using thresholding method in order to construct binary images. Edge detection is applied and the location of candidate fingertips is estimated based on boundary tracing process and local extrema. The modified 2D chain code algorithm is then applied to the edge image to extract the fingerspelling shape feature and Support Vector Machine (SVM) is used for the classification task. The experimental findings show that the accuracy of the proposed method is 97.75% and 96.48% for alphabets and numbers, respectively.

AB - This paper presents a novel method for the detection and extraction of shape feature for fingerspelling recognition using boundary tracing and chain code. The method includes several steps such as conversion of RGB to YCbCr color space of an image and segmentation of skin pixel regions using thresholding method in order to construct binary images. Edge detection is applied and the location of candidate fingertips is estimated based on boundary tracing process and local extrema. The modified 2D chain code algorithm is then applied to the edge image to extract the fingerspelling shape feature and Support Vector Machine (SVM) is used for the classification task. The experimental findings show that the accuracy of the proposed method is 97.75% and 96.48% for alphabets and numbers, respectively.

KW - Chain code

KW - Fingerspelling

KW - Fingertips detection

KW - Hand tracing

KW - Shape feature

UR - http://www.scopus.com/inward/record.url?scp=85057589652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057589652&partnerID=8YFLogxK

U2 - 10.1145/3206185.3206195

DO - 10.1145/3206185.3206195

M3 - Conference contribution

AN - SCOPUS:85057589652

SP - 104

EP - 109

BT - ISMSI 2018 - 2nd International Conference on Intelligent Systems, Metaheuristics and Swarm Intelligence

PB - Association for Computing Machinery

ER -