LSTM-Based Hand Gesture Recognition for Indonesian Sign Language System (SIBI) on Affix, Alphabet, Number, and Word

Sign language plays a critical role in enabling communication for the Deaf and hard-of-hearing community in Indonesia, yet there remains a significant gap in technological support for recognizing the official Indonesian sign language, Sistem Isyarat Bahasa Indonesia (SIBI). This study presents a dee...

Full description

Saved in:
Bibliographic Details
Main Authors: Patricia Ho, Handri Santoso
Format: Article
Language:English
Published: Politeknik Negeri Batam 2025-06-01
Series:Journal of Applied Informatics and Computing
Subjects:
Online Access:https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849729395858604032
author Patricia Ho
Handri Santoso
author_facet Patricia Ho
Handri Santoso
author_sort Patricia Ho
collection DOAJ
description Sign language plays a critical role in enabling communication for the Deaf and hard-of-hearing community in Indonesia, yet there remains a significant gap in technological support for recognizing the official Indonesian sign language, Sistem Isyarat Bahasa Indonesia (SIBI). This study presents a deep learning-based hand gesture recognition system for SIBI, focusing on four primary gesture categories: affix, alphabet, number, and word. A large and diverse dataset of 21,351 videos was collected, covering 18 affix, 26 alphabet, 35 number, and 29 word classes. Hand keypoints were extracted using MediaPipe Holistic, and a bidirectional long short-term memory (BiLSTM) model was trained using 5-fold stratified cross-validation. The model achieved high recognition performance in the alphabet, number, and word categories, with mean test accuracies of 93.94%, 91.48%, and 92.41%, respectively, and slightly lower performance in the affix category at 68.17%. The affix category posed particular challenges due to subtle hand shape differences and high variability between signers, while the alphabet category consistently showed the highest accuracy due to its distinct and static handshapes. Evaluation metrics, including precision, recall, F1-score, and confusion matrix analysis, provided further insights into model strengths and limitations. Overall, the study demonstrates the effectiveness of LSTM models for sequential hand gesture recognition in SIBI and highlights areas for future improvement, such as handling non-manual features and improving generalization across signers.
format Article
id doaj-art-627004bdf5a44fbd9a51e7f516de2ced
institution DOAJ
issn 2548-6861
language English
publishDate 2025-06-01
publisher Politeknik Negeri Batam
record_format Article
series Journal of Applied Informatics and Computing
spelling doaj-art-627004bdf5a44fbd9a51e7f516de2ced2025-08-20T03:09:13ZengPoliteknik Negeri BatamJournal of Applied Informatics and Computing2548-68612025-06-019392893710.30871/jaic.v9i3.96077152LSTM-Based Hand Gesture Recognition for Indonesian Sign Language System (SIBI) on Affix, Alphabet, Number, and WordPatricia Ho0Handri Santoso1Pradita UniversityPradita UniversitySign language plays a critical role in enabling communication for the Deaf and hard-of-hearing community in Indonesia, yet there remains a significant gap in technological support for recognizing the official Indonesian sign language, Sistem Isyarat Bahasa Indonesia (SIBI). This study presents a deep learning-based hand gesture recognition system for SIBI, focusing on four primary gesture categories: affix, alphabet, number, and word. A large and diverse dataset of 21,351 videos was collected, covering 18 affix, 26 alphabet, 35 number, and 29 word classes. Hand keypoints were extracted using MediaPipe Holistic, and a bidirectional long short-term memory (BiLSTM) model was trained using 5-fold stratified cross-validation. The model achieved high recognition performance in the alphabet, number, and word categories, with mean test accuracies of 93.94%, 91.48%, and 92.41%, respectively, and slightly lower performance in the affix category at 68.17%. The affix category posed particular challenges due to subtle hand shape differences and high variability between signers, while the alphabet category consistently showed the highest accuracy due to its distinct and static handshapes. Evaluation metrics, including precision, recall, F1-score, and confusion matrix analysis, provided further insights into model strengths and limitations. Overall, the study demonstrates the effectiveness of LSTM models for sequential hand gesture recognition in SIBI and highlights areas for future improvement, such as handling non-manual features and improving generalization across signers.https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9607deep learninghand gesture recognitionindonesian sign language system (sibi)lstm
spellingShingle Patricia Ho
Handri Santoso
LSTM-Based Hand Gesture Recognition for Indonesian Sign Language System (SIBI) on Affix, Alphabet, Number, and Word
Journal of Applied Informatics and Computing
deep learning
hand gesture recognition
indonesian sign language system (sibi)
lstm
title LSTM-Based Hand Gesture Recognition for Indonesian Sign Language System (SIBI) on Affix, Alphabet, Number, and Word
title_full LSTM-Based Hand Gesture Recognition for Indonesian Sign Language System (SIBI) on Affix, Alphabet, Number, and Word
title_fullStr LSTM-Based Hand Gesture Recognition for Indonesian Sign Language System (SIBI) on Affix, Alphabet, Number, and Word
title_full_unstemmed LSTM-Based Hand Gesture Recognition for Indonesian Sign Language System (SIBI) on Affix, Alphabet, Number, and Word
title_short LSTM-Based Hand Gesture Recognition for Indonesian Sign Language System (SIBI) on Affix, Alphabet, Number, and Word
title_sort lstm based hand gesture recognition for indonesian sign language system sibi on affix alphabet number and word
topic deep learning
hand gesture recognition
indonesian sign language system (sibi)
lstm
url https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9607
work_keys_str_mv AT patriciaho lstmbasedhandgesturerecognitionforindonesiansignlanguagesystemsibionaffixalphabetnumberandword
AT handrisantoso lstmbasedhandgesturerecognitionforindonesiansignlanguagesystemsibionaffixalphabetnumberandword