Static Pakistani Sign Language Classification using Support Vector Machine

In this study, a system is proposed that uses the Support Vector Machine (SVM) technique with Bag-of-Words (BoW) and recognizes static Pakistani Sign Language (PSL) alphabets. The application of the BoW technique with SVM, on a PSL images' dataset, has not been performed previously. Similarly,...

Full description

Saved in:
Bibliographic Details
Main Authors: Shaheer Mirza, Sheikh Muhammad Munaf, Shahid Ali, Muhammad Asif
Format: Article
Language:English
Published: Sir Syed University of Engineering and Technology, Karachi. 2022-12-01
Series:Sir Syed University Research Journal of Engineering and Technology
Subjects:
Online Access:http://www.sirsyeduniversity.edu.pk/ssurj/rj/index.php/ssurj/article/view/436
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434252658081792
author Shaheer Mirza
Sheikh Muhammad Munaf
Shahid Ali
Muhammad Asif
author_facet Shaheer Mirza
Sheikh Muhammad Munaf
Shahid Ali
Muhammad Asif
author_sort Shaheer Mirza
collection DOAJ
description In this study, a system is proposed that uses the Support Vector Machine (SVM) technique with Bag-of-Words (BoW) and recognizes static Pakistani Sign Language (PSL) alphabets. The application of the BoW technique with SVM, on a PSL images' dataset, has not been performed previously. Similarly, no publicly available dataset for PSL is available and previous studies have achieved a maximum classification accuracy of 91.98%. For this study, a total of 511 images are collected for 36 static PSL alphabet signs from a native signer. The Sign Language (SL) recognition system uses the collected images as input and converts them to grayscale. To segment the images, the system uses the thresholding technique and Speeded Up Robust Feature (SURF) to extract the features. The system uses K-means clustering to cluster the extracted features. To form the BoW, the system computes the Euclidean distance among SURF descriptors and clustered data. The system then uses 5-fold cross-validation to divide the codebooks obtained from the BoW into training and testing. The developed system yields an overall accuracy of 97.87% for the classification of static PSL signs at 1,500×1,500 image dimensions and 500 Bags.
format Article
id doaj-art-3dafb2c8b5484866858edcb6a5f49317
institution Kabale University
issn 1997-0641
2415-2048
language English
publishDate 2022-12-01
publisher Sir Syed University of Engineering and Technology, Karachi.
record_format Article
series Sir Syed University Research Journal of Engineering and Technology
spelling doaj-art-3dafb2c8b5484866858edcb6a5f493172025-08-20T03:26:43ZengSir Syed University of Engineering and Technology, Karachi.Sir Syed University Research Journal of Engineering and Technology1997-06412415-20482022-12-01122Static Pakistani Sign Language Classification using Support Vector MachineShaheer Mirza0Sheikh Muhammad Munaf1Shahid Ali2Muhammad Asif3Department of Biomedical Engineering, Faculty of Engineering, Science, Technology and Management, Ziauddin University, Karachi, PakistanDepartment of Software Engineering, Faculty of Engineering, Science, Technology and Management, Ziauddin University, Karachi, PakistanDepartment of Speech Language and Hearing Sciences, Faculty of Health Sciences, Ziauddin University, Karachi, PakistanDepartment of Electrical Engineering, Faculty of Engineering, Science, Technology and Management, Ziauddin University, Karachi, Pakistan In this study, a system is proposed that uses the Support Vector Machine (SVM) technique with Bag-of-Words (BoW) and recognizes static Pakistani Sign Language (PSL) alphabets. The application of the BoW technique with SVM, on a PSL images' dataset, has not been performed previously. Similarly, no publicly available dataset for PSL is available and previous studies have achieved a maximum classification accuracy of 91.98%. For this study, a total of 511 images are collected for 36 static PSL alphabet signs from a native signer. The Sign Language (SL) recognition system uses the collected images as input and converts them to grayscale. To segment the images, the system uses the thresholding technique and Speeded Up Robust Feature (SURF) to extract the features. The system uses K-means clustering to cluster the extracted features. To form the BoW, the system computes the Euclidean distance among SURF descriptors and clustered data. The system then uses 5-fold cross-validation to divide the codebooks obtained from the BoW into training and testing. The developed system yields an overall accuracy of 97.87% for the classification of static PSL signs at 1,500×1,500 image dimensions and 500 Bags. http://www.sirsyeduniversity.edu.pk/ssurj/rj/index.php/ssurj/article/view/436Pattern RecognitionPakistani Sign LanguageMachine LearningImage Processing
spellingShingle Shaheer Mirza
Sheikh Muhammad Munaf
Shahid Ali
Muhammad Asif
Static Pakistani Sign Language Classification using Support Vector Machine
Sir Syed University Research Journal of Engineering and Technology
Pattern Recognition
Pakistani Sign Language
Machine Learning
Image Processing
title Static Pakistani Sign Language Classification using Support Vector Machine
title_full Static Pakistani Sign Language Classification using Support Vector Machine
title_fullStr Static Pakistani Sign Language Classification using Support Vector Machine
title_full_unstemmed Static Pakistani Sign Language Classification using Support Vector Machine
title_short Static Pakistani Sign Language Classification using Support Vector Machine
title_sort static pakistani sign language classification using support vector machine
topic Pattern Recognition
Pakistani Sign Language
Machine Learning
Image Processing
url http://www.sirsyeduniversity.edu.pk/ssurj/rj/index.php/ssurj/article/view/436
work_keys_str_mv AT shaheermirza staticpakistanisignlanguageclassificationusingsupportvectormachine
AT sheikhmuhammadmunaf staticpakistanisignlanguageclassificationusingsupportvectormachine
AT shahidali staticpakistanisignlanguageclassificationusingsupportvectormachine
AT muhammadasif staticpakistanisignlanguageclassificationusingsupportvectormachine