Static hand gestures: Fingertips detection based on segmented images

Ahmad Yahya Dawod, Md. Jan Nordin, Junaidi Abdullah

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Fingertips detection is important for recognition of static gesture in sign language. This paper presents a new method that is based on YCbCr colour space and skeletonization for fingertips detection towards gesture segmentation and recognition. The method begins with the conversion of an image in RGB colour space into YCbCr colour space. Then, the chrominance Cb and Cr are extracted from the YCbCr colour space. A thresholding technique, which is based on a pre-defined range for Cb and Cr components representing the skin colour value is used to extract the hand from the background and to achieve the binary image. A morphological processing is performed on the obtained binary image to remove noise and unwanted image pixels. The candidate fingertips position is then calculated based on skeletonization algorithm and tracing process. The centroid is subsequently found, after which the Euclidean distances between the pixels' coordinates that belong to the candidate fingertips and the centroid are calculated towards validating their representation of the actual fingertips. Based on the proposed method, the fingertips of twentysix American Sign Language (ASL) alphabets hand sign samples were detected successfully and the gesture was correctly recognized with an accuracy of 96.3% during the conducted experiments.

Original languageEnglish
Pages (from-to)1090-1098
Number of pages9
JournalJournal of Computer Science
Volume11
Issue number12
DOIs
Publication statusPublished - 2015

Fingerprint

Color
Binary images
Pixels
Skin
Processing
Experiments

Keywords

  • Hand centroid
  • Morphological processing
  • Skin colour segmentation
  • Static gesture
  • YCbCr colour space

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Static hand gestures : Fingertips detection based on segmented images. / Dawod, Ahmad Yahya; Nordin, Md. Jan; Abdullah, Junaidi.

In: Journal of Computer Science, Vol. 11, No. 12, 2015, p. 1090-1098.

Research output: Contribution to journalArticle

Dawod, Ahmad Yahya ; Nordin, Md. Jan ; Abdullah, Junaidi. / Static hand gestures : Fingertips detection based on segmented images. In: Journal of Computer Science. 2015 ; Vol. 11, No. 12. pp. 1090-1098.
@article{af03f33ed62f4131be9aa33cd52268d9,
title = "Static hand gestures: Fingertips detection based on segmented images",
abstract = "Fingertips detection is important for recognition of static gesture in sign language. This paper presents a new method that is based on YCbCr colour space and skeletonization for fingertips detection towards gesture segmentation and recognition. The method begins with the conversion of an image in RGB colour space into YCbCr colour space. Then, the chrominance Cb and Cr are extracted from the YCbCr colour space. A thresholding technique, which is based on a pre-defined range for Cb and Cr components representing the skin colour value is used to extract the hand from the background and to achieve the binary image. A morphological processing is performed on the obtained binary image to remove noise and unwanted image pixels. The candidate fingertips position is then calculated based on skeletonization algorithm and tracing process. The centroid is subsequently found, after which the Euclidean distances between the pixels' coordinates that belong to the candidate fingertips and the centroid are calculated towards validating their representation of the actual fingertips. Based on the proposed method, the fingertips of twentysix American Sign Language (ASL) alphabets hand sign samples were detected successfully and the gesture was correctly recognized with an accuracy of 96.3{\%} during the conducted experiments.",
keywords = "Hand centroid, Morphological processing, Skin colour segmentation, Static gesture, YCbCr colour space",
author = "Dawod, {Ahmad Yahya} and Nordin, {Md. Jan} and Junaidi Abdullah",
year = "2015",
doi = "10.3844/jcssp.2015.1090.1098",
language = "English",
volume = "11",
pages = "1090--1098",
journal = "Journal of Computer Science",
issn = "1549-3636",
publisher = "Science Publications",
number = "12",

}

TY - JOUR

T1 - Static hand gestures

T2 - Fingertips detection based on segmented images

AU - Dawod, Ahmad Yahya

AU - Nordin, Md. Jan

AU - Abdullah, Junaidi

PY - 2015

Y1 - 2015

N2 - Fingertips detection is important for recognition of static gesture in sign language. This paper presents a new method that is based on YCbCr colour space and skeletonization for fingertips detection towards gesture segmentation and recognition. The method begins with the conversion of an image in RGB colour space into YCbCr colour space. Then, the chrominance Cb and Cr are extracted from the YCbCr colour space. A thresholding technique, which is based on a pre-defined range for Cb and Cr components representing the skin colour value is used to extract the hand from the background and to achieve the binary image. A morphological processing is performed on the obtained binary image to remove noise and unwanted image pixels. The candidate fingertips position is then calculated based on skeletonization algorithm and tracing process. The centroid is subsequently found, after which the Euclidean distances between the pixels' coordinates that belong to the candidate fingertips and the centroid are calculated towards validating their representation of the actual fingertips. Based on the proposed method, the fingertips of twentysix American Sign Language (ASL) alphabets hand sign samples were detected successfully and the gesture was correctly recognized with an accuracy of 96.3% during the conducted experiments.

AB - Fingertips detection is important for recognition of static gesture in sign language. This paper presents a new method that is based on YCbCr colour space and skeletonization for fingertips detection towards gesture segmentation and recognition. The method begins with the conversion of an image in RGB colour space into YCbCr colour space. Then, the chrominance Cb and Cr are extracted from the YCbCr colour space. A thresholding technique, which is based on a pre-defined range for Cb and Cr components representing the skin colour value is used to extract the hand from the background and to achieve the binary image. A morphological processing is performed on the obtained binary image to remove noise and unwanted image pixels. The candidate fingertips position is then calculated based on skeletonization algorithm and tracing process. The centroid is subsequently found, after which the Euclidean distances between the pixels' coordinates that belong to the candidate fingertips and the centroid are calculated towards validating their representation of the actual fingertips. Based on the proposed method, the fingertips of twentysix American Sign Language (ASL) alphabets hand sign samples were detected successfully and the gesture was correctly recognized with an accuracy of 96.3% during the conducted experiments.

KW - Hand centroid

KW - Morphological processing

KW - Skin colour segmentation

KW - Static gesture

KW - YCbCr colour space

UR - http://www.scopus.com/inward/record.url?scp=84958951920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958951920&partnerID=8YFLogxK

U2 - 10.3844/jcssp.2015.1090.1098

DO - 10.3844/jcssp.2015.1090.1098

M3 - Article

AN - SCOPUS:84958951920

VL - 11

SP - 1090

EP - 1098

JO - Journal of Computer Science

JF - Journal of Computer Science

SN - 1549-3636

IS - 12

ER -