View in EDS PDF Full Text

Enhancing American Sign Language Recognition Through Transfer Learning Technique.

Saved in:
Bibliographic Details
Title: Enhancing American Sign Language Recognition Through Transfer Learning Technique.
Authors: Muslim Mashloosh, Wahhab1 wahhabmuslim@alkadhum-col.edu.iq, Hanoon Tuama, Murteza1, Adil Najm, Ghadah2
Source: Iraqi Journal for Electrical & Electronic Engineering. Jun2026, Vol. 22 Issue 1, p502-511. 10p.
Subjects: American Sign Language, Machine learning, Real-time computing, Deep learning, Sign language
Abstract (English): Aiming to enhance the accuracy of sign classification in sign language (SL), this research presents an innovative approach that combines hand-engineered characteristics with deep learning (DL) algorithms. The focus is on American Sign Language (ASL), a critical communication tool for the deaf and hard-of-hearing community. The goal is to bridge the existing communication chasm between SL users and the general public by designing a real-time SL recognition system that allows non- SL users to converse with the hearing-impaired individuals. The application and assessment of various machine learning (ML) models, such as VGG19, DenseNet, ResNet50, MobileNet, and NASNetMobile, yielded promising outcomes with superior evalu- ation metrics. These models exhibit utility in the classification of ASL signs as they can differentiate between diverse hand gestures with high accuracy (ACC). The paper highlights the potential of these models across an array of ASL recognition applica- tions, considering factors like computational resources, model dimension, and real-time functionality. The findings endorse the application of ML techniques in SL interpretation, promoting inclusive communication for those with hearing impairment. [ABSTRACT FROM AUTHOR]
Abstract (Arabic): تركز المقالة على تحسين التعرف على لغة الإشارة الأمريكية (ASL) باستخدام تقنيات التعلم بالنقل مع نماذج التعلم العميق (DL). تقوم بتقييم أداء خمسة من هياكل الشبكات العصبية التلافيفية—وهي VGG19، DenseNet، ResNet50، MobileNet، وNASNetMobile—على مجموعة بيانات أبجدية لغة الإشارة الأمريكية، التي تحتوي على صور معنونة لإيماءات اليد التي تمثل حروف لغة الإشارة الأمريكية. تطبق الدراسة خطوات معالجة البيانات المسبقة بما في ذلك تغيير الحجم والتطبيع، وتقيس دقة النموذج (ACC)، والدقة (PREC)، والاستدعاء (REC)، ومقياس F1 (F1-S)، وتجد أن جميع النماذج تحقق دقة عالية (حوالي 98–100%) في تصنيف إشارات لغة الإشارة الأمريكية. تبرز الدراسة إمكانيات هذه النماذج لتطبيقات التعرف على لغة الإشارة الأمريكية في الوقت الحقيقي، مع التأكيد على اعتبارات مثل الموارد الحاسوبية وحجم النموذج، وتقترح أعمالًا مستقبلية لتحسين المتانة تحت ظروف متغيرة ودمج بيانات متعددة الوسائط لتحقيق شمولية أوسع في التواصل مع مجتمعات الصم وضعاف السمع. [Extracted from the article]
Copyright of Iraqi Journal for Electrical & Electronic Engineering is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 194879623
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Enhancing American Sign Language Recognition Through Transfer Learning Technique.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Muslim+Mashloosh%2C+Wahhab%22">Muslim Mashloosh, Wahhab</searchLink><relatesTo>1</relatesTo><i> wahhabmuslim@alkadhum-col.edu.iq</i><br /><searchLink fieldCode="AR" term="%22Hanoon+Tuama%2C+Murteza%22">Hanoon Tuama, Murteza</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Adil+Najm%2C+Ghadah%22">Adil Najm, Ghadah</searchLink><relatesTo>2</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Iraqi+Journal+for+Electrical+%26+Electronic+Engineering%22">Iraqi Journal for Electrical & Electronic Engineering</searchLink>. Jun2026, Vol. 22 Issue 1, p502-511. 10p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22American+Sign+Language%22">American Sign Language</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Real-time+computing%22">Real-time computing</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Sign+language%22">Sign language</searchLink>
– Name: Abstract
  Label: Abstract (English)
  Group: Ab
  Data: Aiming to enhance the accuracy of sign classification in sign language (SL), this research presents an innovative approach that combines hand-engineered characteristics with deep learning (DL) algorithms. The focus is on American Sign Language (ASL), a critical communication tool for the deaf and hard-of-hearing community. The goal is to bridge the existing communication chasm between SL users and the general public by designing a real-time SL recognition system that allows non- SL users to converse with the hearing-impaired individuals. The application and assessment of various machine learning (ML) models, such as VGG19, DenseNet, ResNet50, MobileNet, and NASNetMobile, yielded promising outcomes with superior evalu- ation metrics. These models exhibit utility in the classification of ASL signs as they can differentiate between diverse hand gestures with high accuracy (ACC). The paper highlights the potential of these models across an array of ASL recognition applica- tions, considering factors like computational resources, model dimension, and real-time functionality. The findings endorse the application of ML techniques in SL interpretation, promoting inclusive communication for those with hearing impairment. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label: Abstract (Arabic)
  Group: Ab
  Data: تركز المقالة على تحسين التعرف على لغة الإشارة الأمريكية (ASL) باستخدام تقنيات التعلم بالنقل مع نماذج التعلم العميق (DL). تقوم بتقييم أداء خمسة من هياكل الشبكات العصبية التلافيفية—وهي VGG19، DenseNet، ResNet50، MobileNet، وNASNetMobile—على مجموعة بيانات أبجدية لغة الإشارة الأمريكية، التي تحتوي على صور معنونة لإيماءات اليد التي تمثل حروف لغة الإشارة الأمريكية. تطبق الدراسة خطوات معالجة البيانات المسبقة بما في ذلك تغيير الحجم والتطبيع، وتقيس دقة النموذج (ACC)، والدقة (PREC)، والاستدعاء (REC)، ومقياس F1 (F1-S)، وتجد أن جميع النماذج تحقق دقة عالية (حوالي 98–100%) في تصنيف إشارات لغة الإشارة الأمريكية. تبرز الدراسة إمكانيات هذه النماذج لتطبيقات التعرف على لغة الإشارة الأمريكية في الوقت الحقيقي، مع التأكيد على اعتبارات مثل الموارد الحاسوبية وحجم النموذج، وتقترح أعمالًا مستقبلية لتحسين المتانة تحت ظروف متغيرة ودمج بيانات متعددة الوسائط لتحقيق شمولية أوسع في التواصل مع مجتمعات الصم وضعاف السمع. [Extracted from the article]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Iraqi Journal for Electrical & Electronic Engineering is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194879623
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.37917/ijeee.22.1.44
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 502
    Subjects:
      – SubjectFull: American Sign Language
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Real-time computing
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Sign language
        Type: general
    Titles:
      – TitleFull: Enhancing American Sign Language Recognition Through Transfer Learning Technique.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Muslim Mashloosh, Wahhab
      – PersonEntity:
          Name:
            NameFull: Hanoon Tuama, Murteza
      – PersonEntity:
          Name:
            NameFull: Adil Najm, Ghadah
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 18145892
          Numbering:
            – Type: volume
              Value: 22
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Iraqi Journal for Electrical & Electronic Engineering
              Type: main
ResultId 1