Comparison of Four SVM Classifiers Used with Depth Sensors to Recognize Arabic Sign Language Words
The objective of this research was to recognize the hand gestures of Arabic Sign Language (ArSL) words using two depth sensors. The researchers developed a model to examine 143 signs gestured by 10 users for 5 ArSL words (the dataset). The sensors captured depth images of the upper human body, from...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-06-01
|
Series: | Computers |
Subjects: | |
Online Access: | http://www.mdpi.com/2073-431X/6/2/20 |
_version_ | 1811299823627796480 |
---|---|
author | Miada A. Almasre Hana Al-Nuaim |
author_facet | Miada A. Almasre Hana Al-Nuaim |
author_sort | Miada A. Almasre |
collection | DOAJ |
description | The objective of this research was to recognize the hand gestures of Arabic Sign Language (ArSL) words using two depth sensors. The researchers developed a model to examine 143 signs gestured by 10 users for 5 ArSL words (the dataset). The sensors captured depth images of the upper human body, from which 235 angles (features) were extracted for each joint and between each pair of bones. The dataset was divided into a training set (109 observations) and a testing set (34 observations). The support vector machine (SVM) classifier was set using different parameters on the gestured words’ dataset to produce four SVM models, with linear kernel (SVMLD and SVMLT) and radial kernel (SVMRD and SVMRT) functions. The overall identification accuracy for the corresponding words in the training set for the SVMLD, SVMLT, SVMRD, and SVMRT models was 88.92%, 88.92%, 90.88%, and 90.884%, respectively. The accuracy from the testing set for SVMLD, SVMLT, SVMRD, and SVMRT was 97.059%, 97.059%, 94.118%, and 97.059%, respectively. Therefore, since the two kernels in the models were close in performance, it is far more efficient to use the less complex model (linear kernel) set with a default parameter. |
first_indexed | 2024-04-13T06:42:26Z |
format | Article |
id | doaj.art-ce45a980317b4cafb8b2d10ac13f3b6a |
institution | Directory Open Access Journal |
issn | 2073-431X |
language | English |
last_indexed | 2024-04-13T06:42:26Z |
publishDate | 2017-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Computers |
spelling | doaj.art-ce45a980317b4cafb8b2d10ac13f3b6a2022-12-22T02:57:42ZengMDPI AGComputers2073-431X2017-06-01622010.3390/computers6020020computers6020020Comparison of Four SVM Classifiers Used with Depth Sensors to Recognize Arabic Sign Language WordsMiada A. Almasre0Hana Al-Nuaim1Department of Computer Science, Faculty of Computing and Information Technology, King AbdulAziz University, Jeddah 21499, Saudi ArabiaDepartment of Computer Science, Faculty of Computing and Information Technology, King AbdulAziz University, Jeddah 21499, Saudi ArabiaThe objective of this research was to recognize the hand gestures of Arabic Sign Language (ArSL) words using two depth sensors. The researchers developed a model to examine 143 signs gestured by 10 users for 5 ArSL words (the dataset). The sensors captured depth images of the upper human body, from which 235 angles (features) were extracted for each joint and between each pair of bones. The dataset was divided into a training set (109 observations) and a testing set (34 observations). The support vector machine (SVM) classifier was set using different parameters on the gestured words’ dataset to produce four SVM models, with linear kernel (SVMLD and SVMLT) and radial kernel (SVMRD and SVMRT) functions. The overall identification accuracy for the corresponding words in the training set for the SVMLD, SVMLT, SVMRD, and SVMRT models was 88.92%, 88.92%, 90.88%, and 90.884%, respectively. The accuracy from the testing set for SVMLD, SVMLT, SVMRD, and SVMRT was 97.059%, 97.059%, 94.118%, and 97.059%, respectively. Therefore, since the two kernels in the models were close in performance, it is far more efficient to use the less complex model (linear kernel) set with a default parameter.http://www.mdpi.com/2073-431X/6/2/20depth sensorgesture recognitionsupport vector machineclassificationlinearradialSVM |
spellingShingle | Miada A. Almasre Hana Al-Nuaim Comparison of Four SVM Classifiers Used with Depth Sensors to Recognize Arabic Sign Language Words Computers depth sensor gesture recognition support vector machine classification linear radial SVM |
title | Comparison of Four SVM Classifiers Used with Depth Sensors to Recognize Arabic Sign Language Words |
title_full | Comparison of Four SVM Classifiers Used with Depth Sensors to Recognize Arabic Sign Language Words |
title_fullStr | Comparison of Four SVM Classifiers Used with Depth Sensors to Recognize Arabic Sign Language Words |
title_full_unstemmed | Comparison of Four SVM Classifiers Used with Depth Sensors to Recognize Arabic Sign Language Words |
title_short | Comparison of Four SVM Classifiers Used with Depth Sensors to Recognize Arabic Sign Language Words |
title_sort | comparison of four svm classifiers used with depth sensors to recognize arabic sign language words |
topic | depth sensor gesture recognition support vector machine classification linear radial SVM |
url | http://www.mdpi.com/2073-431X/6/2/20 |
work_keys_str_mv | AT miadaaalmasre comparisonoffoursvmclassifiersusedwithdepthsensorstorecognizearabicsignlanguagewords AT hanaalnuaim comparisonoffoursvmclassifiersusedwithdepthsensorstorecognizearabicsignlanguagewords |