{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T04:08:24Z","timestamp":1785989304814,"version":"3.56.0"},"reference-count":36,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T00:00:00Z","timestamp":1764115200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Sign language is a vital communication tool for individuals with hearing and speech impairments, yet Arabic Sign Language (ArSL) recognition remains challenging due to signer variability, occlusions, and limited benchmark datasets. To address these challenges, we propose a two-hand static and dynamic gesture recognition system that integrates keypoint-based descriptors (ORB (Oriented FAST and Rotated BRIEF), AKAZE (Accelerated-KAZE), SIFT (Scale-Invariant Feature Transform), and BRISK (Binary Robust Invariant Scalable Keypoints)) with shape-based features (smoothness, convexity, compactness, symmetry) for enhanced gesture discrimination. A distance map-based method is also used to extract fingertip keypoints by identifying local maxima from the hand centroid. An attention-enabled feature fusion strategy effectively combines these diverse features, and a long short-term memory (LSTM) network captures temporal dependencies in dynamic gestures for improved classification. Evaluated on KArSL-100, KArSL-190, and KArSL-502, the proposed system achieved 77.34%, 62.53%, and 47.58% accuracy, respectively, demonstrating its robustness in recognizing both static and dynamic ArSL gestures. These results highlight the effectiveness of combining spatial and temporal features, paving the way for more accurate and inclusive sign language recognition systems.<\/jats:p>","DOI":"10.7717\/peerj-cs.3275","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T08:00:21Z","timestamp":1764144021000},"page":"e3275","source":"Crossref","is-referenced-by-count":10,"title":["Two-hand static and dynamic Arabic sign language recognition using keypoints and shape descriptors with attention-driven feature fusion"],"prefix":"10.7717","volume":"11","author":[{"given":"Zarnab","family":"Kausar","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Riphah International University, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaheryar","family":"Najam","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Bahria University, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed","family":"Alshehri","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Applied College, King Khalid University, Abha, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yahya","family":"AlQahtani","sequence":"additional","affiliation":[{"name":"Department of Informatics and Computer Systems, King Khalid University, Abha, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdulmonem","family":"Alshahrani","sequence":"additional","affiliation":[{"name":"Department of Informatics and Computer Systems, King Khalid University, Abha, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad","family":"Jalal","sequence":"additional","affiliation":[{"name":"Department of Computing and AI, Air University, Islamabad, Pakistan"},{"name":"Department of Computer Science and Engineering, College of Informatics, Korea University, Seoul, Republic of South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeongmin","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Tech University of Korea, Sangidaehak-ro, Siheung-si, Republic of South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2025,11,26]]},"reference":[{"key":"10.7717\/peerj-cs.3275\/ref-1","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/IBCAST59916.2023.10712949","article-title":"Robust handgesture tracking and recognition for healthcare via recurrent neural network","author":"Ansar","year":"2023"},{"issue":"17","key":"10.7717\/peerj-cs.3275\/ref-2","doi-asserted-by":"publisher","first-page":"7523","DOI":"10.3390\/s23177523","article-title":"Smart home automation-based hand gesture recognition using feature fusion and recurrent neural network","volume":"23","author":"Alabdullah","year":"2023","journal-title":"Sensors"},{"key":"10.7717\/peerj-cs.3275\/ref-3","doi-asserted-by":"publisher","first-page":"77019","DOI":"10.1109\/ACCESS.2024.3405341","article-title":"Enhanced weak spatial modeling through CNN-based deep sign language skeletal feature transformation","volume":"12","author":"Alamri","year":"2024","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3275\/ref-4","doi-asserted-by":"publisher","first-page":"128871\u2013128895","DOI":"10.1109\/ACCESS.2024.3457692","article-title":"Advancements in sign language recognition: A comprehensive review and future prospects","volume":"12","author":"Al Abdullah","year":"2024","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3275\/ref-5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.11932","article-title":"RGB Arabic alphabets sign language dataset","author":"Al-Barham","year":"2023"},{"issue":"4","key":"10.7717\/peerj-cs.3275\/ref-6","doi-asserted-by":"publisher","first-page":"20250586","DOI":"10.57197\/JDR-2025-0586","article-title":"Attention-Based Approach for Arabic Sign Language Recognition, Supporting Differently Abled Persons","volume":"4","author":"Almufareh","year":"2025","journal-title":"Journal of Disability Research"},{"issue":"1","key":"10.7717\/peerj-cs.3275\/ref-7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3584984","article-title":"Isolated Arabic sign language recognition using a transformer-based model and landmark keypoints","volume":"23","author":"Alyami","year":"2024","journal-title":"ACM Transactions on Asian and Low-Resource Language Information Processing"},{"issue":"13","key":"10.7717\/peerj-cs.3275\/ref-8","doi-asserted-by":"publisher","first-page":"6481","DOI":"10.3390\/app12136481","article-title":"Dynamic hand gesture recognition for smart lifecare routines via K-ary tree hashing classifier","volume":"12","author":"Ansar","year":"2022","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.3275\/ref-9","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11042-020-09829-y","article-title":"CNN-based feature extraction and classification for sign language","volume":"80","author":"Barbhuiya","year":"2021","journal-title":"Multimedia Tools and Applications"},{"key":"10.7717\/peerj-cs.3275\/ref-10","first-page":"1","article-title":"Indian sign language gesture recognition using image processing and deep learning","author":"Bhagat","year":"2019"},{"key":"10.7717\/peerj-cs.3275\/ref-11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2018.02.029","article-title":"Learning a deep network with spherical part model for 3D hand pose estimation","volume":"80","author":"Chen","year":"2018","journal-title":"Pattern Recognition"},{"issue":"1","key":"10.7717\/peerj-cs.3275\/ref-12","doi-asserted-by":"publisher","first-page":"118559","DOI":"10.1016\/j.eswa.2022.118559","article-title":"Static hand gesture recognition in sign language based on convolutional neural network with feature extraction method using ORB descriptor and Gabor filter","volume":"211","author":"Damaneh","year":"2023","journal-title":"Expert Systems with Applications"},{"issue":"8","key":"10.7717\/peerj-cs.3275\/ref-13","doi-asserted-by":"publisher","first-page":"10035","DOI":"10.1007\/s11042-018-6565-5","article-title":"On the role of multimodal learning in the recognition of sign language","volume":"78","author":"Ferreira","year":"2019","journal-title":"Multimedia Tools and Applications"},{"key":"10.7717\/peerj-cs.3275\/ref-14","article-title":"Recognition of Indian sign language using SURF, BoW & CNN","author":"Gangwar","year":"2024"},{"key":"10.7717\/peerj-cs.3275\/ref-15","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.patrec.2020.11.011","article-title":"A multi-scale descriptor for real time RGB-D hand gesture recognition","volume":"144","author":"Huang","year":"2021","journal-title":"Pattern Recognition Letters"},{"key":"10.7717\/peerj-cs.3275\/ref-16","first-page":"573","article-title":"American sign language posture understanding with deep neural networks","author":"Jalal","year":"2018"},{"key":"10.7717\/peerj-cs.3275\/ref-17","doi-asserted-by":"publisher","first-page":"14727","DOI":"10.1109\/ACCESS.2024.3524431","article-title":"IoT-based multisensors fusion for activity recognition via key features and hybrid transfer learning","volume":"13","author":"Jalal","year":"2024","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3275\/ref-18","first-page":"335","article-title":"Image enhancement using morphological techniques","author":"Kaur","year":"2024"},{"issue":"3","key":"10.7717\/peerj-cs.3275\/ref-19","doi-asserted-by":"publisher","first-page":"451","DOI":"10.3390\/s17030451","article-title":"An effective 3D shape descriptor for object recognition with RGB-D sensors","volume":"17","author":"Liu","year":"2017","journal-title":"Sensors"},{"issue":"7","key":"10.7717\/peerj-cs.3275\/ref-20","doi-asserted-by":"publisher","first-page":"2508","DOI":"10.55730\/1300-0632.3952","article-title":"Utilizing motion and spatial features for sign language gesture recognition using cascaded CNN and LSTM models","volume":"30","author":"Luqman","year":"2022","journal-title":"Turkish Journal of Electrical Engineering and Computer Sciences"},{"key":"10.7717\/peerj-cs.3275\/ref-21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.10060","article-title":"ViT-HGR: vision transformer-based hand gesture recognition from high density surface EMG signals","author":"Montazerin","year":"2022"},{"key":"10.7717\/peerj-cs.3275\/ref-22","doi-asserted-by":"publisher","first-page":"1401803","DOI":"10.3389\/fbioe.2024.1401803","article-title":"Innovative healthcare solutions: robust hand gesture recognition of daily life routines using 1D CNN","volume":"12","author":"Mudawi","year":"2024","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"issue":"3","key":"10.7717\/peerj-cs.3275\/ref-23","doi-asserted-by":"publisher","first-page":"e2415","DOI":"10.7717\/peerj-cs.2415","article-title":"Comprehensive empirical evaluation of feature extractors in computer vision","volume":"10","author":"Murat","year":"2024","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.3275\/ref-24","doi-asserted-by":"publisher","first-page":"100723","DOI":"10.1016\/j.mlwa.2025.100723","article-title":"Framework for detecting and recognizing sign language using absolute pose estimation difference and deep learning","volume":"21","author":"Myagila","year":"2025","journal-title":"Machine Learning with Applications"},{"key":"10.7717\/peerj-cs.3275\/ref-25","first-page":"1196","article-title":"Hand gesture recognition using temporal convolutions and attention mechanism","author":"Rahimian","year":"2022"},{"issue":"3","key":"10.7717\/peerj-cs.3275\/ref-26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.eswa.2021.115657","article-title":"Vision-based hand gesture recognition using deep learning for the interpretation of sign language","volume":"182","author":"Sharma","year":"2021","journal-title":"Expert Systems with Applications"},{"issue":"17","key":"10.7717\/peerj-cs.3275\/ref-27","doi-asserted-by":"publisher","first-page":"5856","DOI":"10.3390\/s21175856","article-title":"American Sign Language alphabet recognition by extracting features from hand pose estimation","volume":"21","author":"Shin","year":"2021","journal-title":"Sensors"},{"key":"10.7717\/peerj-cs.3275\/ref-28","first-page":"1","article-title":"A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK","author":"Tareen","year":"2018"},{"issue":"22","key":"10.7717\/peerj-cs.3275\/ref-29","doi-asserted-by":"publisher","first-page":"12204","DOI":"10.3390\/app132212204","article-title":"SDViT: Stacking of Distilled Vision Transformers for Hand Gesture Recognition","volume":"13","author":"Tan","year":"2023","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.3275\/ref-30","first-page":"1","article-title":"Face recognition system using Haar Cascade algorithm","author":"Vijaya","year":"2024"},{"issue":"3","key":"10.7717\/peerj-cs.3275\/ref-31","doi-asserted-by":"publisher","first-page":"121055","DOI":"10.1016\/j.eswa.2023.121055","article-title":"A deep learning approach using attention mechanism and transfer learning for electromyographic hand gesture estimation","volume":"234","author":"Wang","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.7717\/peerj-cs.3275\/ref-32","volume-title":"World report on hearing","author":"World Health Organization","year":"2021"},{"issue":"16","key":"10.7717\/peerj-cs.3275\/ref-33","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1049\/joe.2018.8327","article-title":"RGB-D static gesture recognition based on convolutional neural network","volume":"2018","author":"Xie","year":"2018","journal-title":"The Journal of Engineering"},{"issue":"1","key":"10.7717\/peerj-cs.3275\/ref-34","doi-asserted-by":"publisher","first-page":"157","DOI":"10.32604\/cmes.2022.020035","article-title":"A novel SE-CNN attention architecture for sEMG-based hand gesture recognition","volume":"134","author":"Xu","year":"2023","journal-title":"Computer Modeling in Engineering & Sciences"},{"issue":"11","key":"10.7717\/peerj-cs.3275\/ref-35","doi-asserted-by":"publisher","first-page":"1324","DOI":"10.3390\/bioengineering10111324","article-title":"Gesture classification in electromyography signals for real-time prosthetic hand control using a convolutional neural network-enhanced channel attention model","volume":"10","author":"Yu","year":"2023","journal-title":"Bioengineering"},{"key":"10.7717\/peerj-cs.3275\/ref-36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.00553","article-title":"A spatio-temporal graph convolutional network for gesture recognition from high-density electromyography","author":"Zhong","year":"2023"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3275.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3275.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3275.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3275.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T08:00:25Z","timestamp":1764144025000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3275"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,26]]},"references-count":36,"alternative-id":["10.7717\/peerj-cs.3275"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3275","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,26]]},"article-number":"e3275"}}