Sign language detection dataset: A resource for AI-based recognition systemsMendeley Data

Sign language is a very important mode of communication among deaf and hard-of-hearing populations. Automatic sign language detection based on deep learning model is the theme of this study. Hand gestures are classified by the Convolutional Neural Network (CNN) model to different signs. For training...

Full description

Saved in:
Bibliographic Details
Main Authors: Bindu Garg, Manisha Kasar, Priyanka Paygude, Amol Dhumane, Srinivas Ambala, Jitendra Rajpurohit, Abhay Sharma, Vidula Meshram, Amber Vats, Achyut Kashyap
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Data in Brief
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352340925004330
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849685038599241728
author Bindu Garg
Manisha Kasar
Priyanka Paygude
Amol Dhumane
Srinivas Ambala
Jitendra Rajpurohit
Abhay Sharma
Vidula Meshram
Amber Vats
Achyut Kashyap
author_facet Bindu Garg
Manisha Kasar
Priyanka Paygude
Amol Dhumane
Srinivas Ambala
Jitendra Rajpurohit
Abhay Sharma
Vidula Meshram
Amber Vats
Achyut Kashyap
author_sort Bindu Garg
collection DOAJ
description Sign language is a very important mode of communication among deaf and hard-of-hearing populations. Automatic sign language detection based on deep learning model is the theme of this study. Hand gestures are classified by the Convolutional Neural Network (CNN) model to different signs. For training purposes, there are 26,000 images available with 3000 images for every alphabet letter such that there is complete representation of sign language gesture. Photos were taken in controlled lighting with a consistent black background to facilitate better feature extraction. The data contains varied participants of various age groups, skin types, and hand shapes to enhance generalization. Data collection was standardized through iPhone 15 Pro Max, black background cloth, tripod stand, and remote-controlled Drodcam app to maintain consistency in image quality and framing. For diversity and realism, three participants were involved in data collection, each providing 1000 images per sign, resulting in a rich and diverse dataset. Preprocessing of data methods were used for achieving the best quality of data, such as resizing, conversion to grayscale, normalization, and augmentation. Different techniques of data augmentation like rotation, flipping, scaling, brightness change, and addition of Gaussian noise were used to introduce variations in hand gestures and make the model robust against various environmental conditions. The dataset was then partitioned into 70 % training, 15 % validation, and 15 % test sets for maximizing model performance and ensuring good generalization. The dataset show high accuracy, reflecting the potential of the model for real-world usage, such as accessibility tools for the deaf community, educational tools, and real-time sign language recognition systems.
format Article
id doaj-art-8cb897c5945e457696d9f0f10cffbfff
institution DOAJ
issn 2352-3409
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Data in Brief
spelling doaj-art-8cb897c5945e457696d9f0f10cffbfff2025-08-20T03:23:16ZengElsevierData in Brief2352-34092025-08-016111170310.1016/j.dib.2025.111703Sign language detection dataset: A resource for AI-based recognition systemsMendeley DataBindu Garg0Manisha Kasar1Priyanka Paygude2Amol Dhumane3Srinivas Ambala4Jitendra Rajpurohit5Abhay Sharma6Vidula Meshram7Amber Vats8Achyut Kashyap9Bharati Vidyapeeth (Deemed to be University) College of Engineering, Pune, IndiaBharati Vidyapeeth (Deemed to be University) College of Engineering, Pune, India; Corresponding authors.Bharati Vidyapeeth (Deemed to be University) College of Engineering, Pune, India; Corresponding authors.Symbiosis Institute of Technology, Pune, IndiaPimpri Chinchwad College of Engineering, Pune, IndiaSymbiosis Institute of Technology, Pune, IndiaManipal University Jaipur, Jaipur, IndiaVishwakarma Institute of Technology, Pune, IndiaBharati Vidyapeeth (Deemed to be University) College of Engineering, Pune, IndiaBharati Vidyapeeth (Deemed to be University) College of Engineering, Pune, IndiaSign language is a very important mode of communication among deaf and hard-of-hearing populations. Automatic sign language detection based on deep learning model is the theme of this study. Hand gestures are classified by the Convolutional Neural Network (CNN) model to different signs. For training purposes, there are 26,000 images available with 3000 images for every alphabet letter such that there is complete representation of sign language gesture. Photos were taken in controlled lighting with a consistent black background to facilitate better feature extraction. The data contains varied participants of various age groups, skin types, and hand shapes to enhance generalization. Data collection was standardized through iPhone 15 Pro Max, black background cloth, tripod stand, and remote-controlled Drodcam app to maintain consistency in image quality and framing. For diversity and realism, three participants were involved in data collection, each providing 1000 images per sign, resulting in a rich and diverse dataset. Preprocessing of data methods were used for achieving the best quality of data, such as resizing, conversion to grayscale, normalization, and augmentation. Different techniques of data augmentation like rotation, flipping, scaling, brightness change, and addition of Gaussian noise were used to introduce variations in hand gestures and make the model robust against various environmental conditions. The dataset was then partitioned into 70 % training, 15 % validation, and 15 % test sets for maximizing model performance and ensuring good generalization. The dataset show high accuracy, reflecting the potential of the model for real-world usage, such as accessibility tools for the deaf community, educational tools, and real-time sign language recognition systems.http://www.sciencedirect.com/science/article/pii/S2352340925004330American Sign LanguageDeep LearningConvolutional Neural NetworkSign Language Recognition
spellingShingle Bindu Garg
Manisha Kasar
Priyanka Paygude
Amol Dhumane
Srinivas Ambala
Jitendra Rajpurohit
Abhay Sharma
Vidula Meshram
Amber Vats
Achyut Kashyap
Sign language detection dataset: A resource for AI-based recognition systemsMendeley Data
Data in Brief
American Sign Language
Deep Learning
Convolutional Neural Network
Sign Language Recognition
title Sign language detection dataset: A resource for AI-based recognition systemsMendeley Data
title_full Sign language detection dataset: A resource for AI-based recognition systemsMendeley Data
title_fullStr Sign language detection dataset: A resource for AI-based recognition systemsMendeley Data
title_full_unstemmed Sign language detection dataset: A resource for AI-based recognition systemsMendeley Data
title_short Sign language detection dataset: A resource for AI-based recognition systemsMendeley Data
title_sort sign language detection dataset a resource for ai based recognition systemsmendeley data
topic American Sign Language
Deep Learning
Convolutional Neural Network
Sign Language Recognition
url http://www.sciencedirect.com/science/article/pii/S2352340925004330
work_keys_str_mv AT bindugarg signlanguagedetectiondatasetaresourceforaibasedrecognitionsystemsmendeleydata
AT manishakasar signlanguagedetectiondatasetaresourceforaibasedrecognitionsystemsmendeleydata
AT priyankapaygude signlanguagedetectiondatasetaresourceforaibasedrecognitionsystemsmendeleydata
AT amoldhumane signlanguagedetectiondatasetaresourceforaibasedrecognitionsystemsmendeleydata
AT srinivasambala signlanguagedetectiondatasetaresourceforaibasedrecognitionsystemsmendeleydata
AT jitendrarajpurohit signlanguagedetectiondatasetaresourceforaibasedrecognitionsystemsmendeleydata
AT abhaysharma signlanguagedetectiondatasetaresourceforaibasedrecognitionsystemsmendeleydata
AT vidulameshram signlanguagedetectiondatasetaresourceforaibasedrecognitionsystemsmendeleydata
AT ambervats signlanguagedetectiondatasetaresourceforaibasedrecognitionsystemsmendeleydata
AT achyutkashyap signlanguagedetectiondatasetaresourceforaibasedrecognitionsystemsmendeleydata