{ "ok": true, "doi": "10.46243/jst.2023.v8.i07.pp47-57", "events": [ { "seq": 1, "kind": "register", "at": "2026-09-29 22:00:41", "by": "Administrator (admin)", "by_kind": "user", "note": "registered at Crossref; record read from api.crossref.org", "changes": [ { "path": "abstract.lang", "from": null, "to": "en" }, { "path": "abstract.value", "from": null, "to": "Sign Language Recognition (SLR) targets on interpreting the sign language into text or speech, so as to facilitate the communication between deaf-mute people and ordinary people. This task has broad social impact, but is still very challenging due to the complexity and large variations in hand actions. Existing methods for SLR use hand-crafted features to describe sign language motion and build classification models based on those features. However, it is difficult to design reliable features to adapt to the large variations of hand gestures. To approach this problem, we propose a novel convolutional neural network (CNN) which extracts discriminative spatial-temporal features from raw video stream automatically without any prior knowledge, avoiding designing features. To boost the performance, multi-channels of video streams, including color information, depth clue, and body joint positions, are used as input to the CNN in order to integrate color, depth and trajectory information. We validate the proposed model on a real dataset collected with Microsoft Kinect and demonstrate its effectiveness over the traditional approaches based on hand-crafted features" }, { "path": "agents.0.name.family", "from": null, "to": "SREEKANTH" }, { "path": "agents.0.name.given", "from": null, "to": "DR.N." }, { "path": "agents.0.role", "from": null, "to": "author" }, { "path": "agents.0.sequence", "from": null, "to": "first" }, { "path": "agents.1.name.family", "from": null, "to": "PRACHI" }, { "path": "agents.1.name.given", "from": null, "to": "" }, { "path": "agents.1.role", "from": null, "to": "author" }, { "path": "agents.1.sequence", "from": null, "to": "additional" }, { "path": "agents.2.name.family", "from": null, "to": "KIRTHANA" }, { "path": "agents.2.name.given", "from": null, "to": "K.SAI" }, { "path": "agents.2.role", "from": null, "to": "author" }, { "path": "agents.2.sequence", "from": null, "to": "additional" }, { "path": "agents.3.name.org", "from": null, "to": "Longman Publishers" }, { "path": "agents.3.role", "from": null, "to": "publisher" }, { "path": "characters.0", "from": null, "to": "Language" }, { "path": "container.identifiers.0.medium", "from": null, "to": "electronic" }, { "path": "container.identifiers.0.type", "from": null, "to": "ISSN" }, { "path": "container.identifiers.0.value", "from": null, "to": "2456-5660" }, { "path": "container.issue", "from": null, "to": "07" }, { "path": "container.pages.first", "from": null, "to": "47" }, { "path": "container.pages.last", "from": null, "to": "57" }, { "path": "container.titles.0.type", "from": null, "to": "PrincipalTitle" }, { "path": "container.titles.0.value", "from": null, "to": "Journal of Science & Technology" }, { "path": "container.type", "from": null, "to": "Journal" }, { "path": "container.volume", "from": null, "to": "08" }, { "path": "dates.date_type", "from": null, "to": "PublicationDate" }, { "path": "dates.online", "from": null, "to": "2023-07-24" }, { "path": "dates.published", "from": null, "to": "2023-07-24" }, { "path": "doi", "from": null, "to": "10.46243/jst.2023.v8.i07.pp47-57" }, { "path": "format", "from": null, "to": "smartscholars-doi-metadata/1.0" }, { "path": "identifiers.0.type", "from": null, "to": "DOI" }, { "path": "identifiers.0.value", "from": null, "to": "10.46243/jst.2023.v8.i07.pp47-57" }, { "path": "language", "from": null, "to": "en" }, { "path": "license.applies_to", "from": null, "to": "vor" }, { "path": "license.start", "from": null, "to": "2023-07-24" }, { "path": "license.url", "from": null, "to": "https://creativecommons.org/licenses/by/4.0/" }, { "path": "links.0.primary", "from": null, "to": true }, { "path": "links.0.return_type", "from": null, "to": "text/html" }, { "path": "links.0.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/view/713" }, { "path": "links.1.purpose", "from": null, "to": "text-mining" }, { "path": "links.1.return_type", "from": null, "to": "application/pdf" }, { "path": "links.1.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/download/713/643" }, { "path": "links.2.purpose", "from": null, "to": "text-mining" }, { "path": "links.2.return_type", "from": null, "to": "application/xml" }, { "path": "links.2.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/download/713/4084" }, { "path": "links.3.purpose", "from": null, "to": "similarity-checking" }, { "path": "links.3.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/view/713/643" }, { "path": "modes.0", "from": null, "to": "Visual" }, { "path": "record.issue_number", "from": null, "to": 1 }, { "path": "record.registered", "from": null, "to": "2026-09-18" }, { "path": "record.registrant", "from": null, "to": "Longman Publishers" }, { "path": "record.source", "from": null, "to": "crossref-api" }, { "path": "record.source_agency", "from": null, "to": "Crossref (member 25296)" }, { "path": "record.updated", "from": null, "to": "2026-09-21" }, { "path": "references.0.doi", "from": null, "to": "10.1145/3065386" }, { "path": "references.0.key", "from": null, "to": "ref1" }, { "path": "references.0.unstructured", "from": null, "to": "Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in neural information processing systems, 2012, pp. 1097–1105" }, { "path": "references.1.doi", "from": null, "to": "10.1109/cvpr.2014.223" }, { "path": "references.1.key", "from": null, "to": "ref2" }, { "path": "references.1.unstructured", "from": null, "to": "Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, and Li Fei-Fei, “Large-scale video classification with convolutional neural networks,” in CVPR, 2014" }, { "path": "references.2.doi", "from": null, "to": "10.1109/5.726791" }, { "path": "references.2.key", "from": null, "to": "ref3" }, { "path": "references.2.unstructured", "from": null, "to": "Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick ´ Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998" }, { "path": "references.3.doi", "from": null, "to": "10.1109/iccv.2007.4408988" }, { "path": "references.3.key", "from": null, "to": "ref4" }, { "path": "references.3.unstructured", "from": null, "to": "Hueihan Jhuang, Thomas Serre, Lior Wolf, and Tomaso Poggio, “A biologically inspired system for action recognition,” in Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on. Ieee, 2007, pp. 1–8" }, { "path": "references.4.doi", "from": null, "to": "10.1109/tpami.2012.59" }, { "path": "references.4.key", "from": null, "to": "ref5" }, { "path": "references.4.unstructured", "from": null, "to": "Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu, “3D convolutional neural networks for human action recognition,” IEEE TPAMI, vol. 35, no. 1, pp. 221–231, 2013" }, { "path": "references.5.doi", "from": null, "to": "10.1109/icsmc.1997.625742" }, { "path": "references.5.key", "from": null, "to": "ref6" }, { "path": "references.5.unstructured", "from": null, "to": "Kirsti Grobel and Marcell Assan, “Isolated sign language recognition using hidden markov models,” in Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on. IEEE, 1997, vol. 1, pp. 162–167" }, { "path": "references.6.doi", "from": null, "to": "10.1109/34.735811" }, { "path": "references.6.key", "from": null, "to": "ref7" }, { "path": "references.6.unstructured", "from": null, "to": "Thad Starner, Joshua Weaver, and Alex Pentland, “Realtime american sign language recognition using desk and wearable computer based video,” IEEE TPAMI, vol. 20, no. 12, pp. 1371–1375, 1998" }, { "path": "references.7.doi", "from": null, "to": "10.1109/iccv.1999.791206" }, { "path": "references.7.key", "from": null, "to": "ref8" }, { "path": "references.7.unstructured", "from": null, "to": "Christian Vogler and Dimitris Metaxas, “Parallel hidden markov models for american sign language recognition,” in Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on. IEEE, 1999, vol. 1, pp. 116–122" }, { "path": "references.8.doi", "from": null, "to": "10.1145/108844.108900" }, { "path": "references.8.key", "from": null, "to": "ref9" }, { "path": "references.8.unstructured", "from": null, "to": "Kouichi Murakami and Hitomi Taguchi, “Gesture recognition using recurrent neural networks,” in Proceedings of the SIGCHI conference on Human factors in computing systems. ACM, 1991, pp. 237–242" }, { "path": "references.9.doi", "from": null, "to": "10.1007/s001380050080" }, { "path": "references.9.key", "from": null, "to": "ref10" }, { "path": "references.9.unstructured", "from": null, "to": "Chung-Lin Huang and Wen-Yi Huang, “Sign language recognition using model-based tracking and a 3D hopfield neural network,” Machine vision and applications, vol. 10, no. 5-6, pp. 292–307, 1998" }, { "path": "referent", "from": null, "to": "Creation" }, { "path": "structural_type", "from": null, "to": "Digital" }, { "path": "titles.0.lang", "from": null, "to": "en" }, { "path": "titles.0.type", "from": null, "to": "PrincipalTitle" }, { "path": "titles.0.value", "from": null, "to": "SIGN LANGUAGE RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS" }, { "path": "type", "from": null, "to": "JournalArticle" } ], "record_after": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2023.v8.i07.pp47-57", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "SIGN LANGUAGE RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2023.v8.i07.pp47-57" } ], "agents": [ { "role": "author", "name": { "given": "DR.N.", "family": "SREEKANTH" }, "sequence": "first" }, { "role": "author", "name": { "given": "", "family": "PRACHI" }, "sequence": "additional" }, { "role": "author", "name": { "given": "K.SAI", "family": "KIRTHANA" }, "sequence": "additional" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2023-07-24", "date_type": "PublicationDate", "online": "2023-07-24" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "08", "issue": "07", "pages": { "first": "47", "last": "57" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/713", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/713/643", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/713/4084", "purpose": "text-mining", "return_type": "application/xml" }, { "url": "https://www.jst.org.in/index.php/pub/article/view/713/643", "purpose": "similarity-checking" } ], "abstract": { "value": "Sign Language Recognition (SLR) targets on interpreting the sign language into text or speech, so as to facilitate the communication between deaf-mute people and ordinary people. This task has broad social impact, but is still very challenging due to the complexity and large variations in hand actions. Existing methods for SLR use hand-crafted features to describe sign language motion and build classification models based on those features. However, it is difficult to design reliable features to adapt to the large variations of hand gestures. To approach this problem, we propose a novel convolutional neural network (CNN) which extracts discriminative spatial-temporal features from raw video stream automatically without any prior knowledge, avoiding designing features. To boost the performance, multi-channels of video streams, including color information, depth clue, and body joint positions, are used as input to the CNN in order to integrate color, depth and trajectory information. We validate the proposed model on a real dataset collected with Microsoft Kinect and demonstrate its effectiveness over the traditional approaches based on hand-crafted features", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2023-07-24", "applies_to": "vor" }, "references": [ { "key": "ref1", "doi": "10.1145/3065386", "unstructured": "Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in neural information processing systems, 2012, pp. 1097–1105" }, { "key": "ref2", "doi": "10.1109/cvpr.2014.223", "unstructured": "Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, and Li Fei-Fei, “Large-scale video classification with convolutional neural networks,” in CVPR, 2014" }, { "key": "ref3", "doi": "10.1109/5.726791", "unstructured": "Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick ´ Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998" }, { "key": "ref4", "doi": "10.1109/iccv.2007.4408988", "unstructured": "Hueihan Jhuang, Thomas Serre, Lior Wolf, and Tomaso Poggio, “A biologically inspired system for action recognition,” in Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on. Ieee, 2007, pp. 1–8" }, { "key": "ref5", "doi": "10.1109/tpami.2012.59", "unstructured": "Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu, “3D convolutional neural networks for human action recognition,” IEEE TPAMI, vol. 35, no. 1, pp. 221–231, 2013" }, { "key": "ref6", "doi": "10.1109/icsmc.1997.625742", "unstructured": "Kirsti Grobel and Marcell Assan, “Isolated sign language recognition using hidden markov models,” in Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on. IEEE, 1997, vol. 1, pp. 162–167" }, { "key": "ref7", "doi": "10.1109/34.735811", "unstructured": "Thad Starner, Joshua Weaver, and Alex Pentland, “Realtime american sign language recognition using desk and wearable computer based video,” IEEE TPAMI, vol. 20, no. 12, pp. 1371–1375, 1998" }, { "key": "ref8", "doi": "10.1109/iccv.1999.791206", "unstructured": "Christian Vogler and Dimitris Metaxas, “Parallel hidden markov models for american sign language recognition,” in Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on. IEEE, 1999, vol. 1, pp. 116–122" }, { "key": "ref9", "doi": "10.1145/108844.108900", "unstructured": "Kouichi Murakami and Hitomi Taguchi, “Gesture recognition using recurrent neural networks,” in Proceedings of the SIGCHI conference on Human factors in computing systems. ACM, 1991, pp. 237–242" }, { "key": "ref10", "doi": "10.1007/s001380050080", "unstructured": "Chung-Lin Huang and Wen-Yi Huang, “Sign language recognition using model-based tracking and a 3D hopfield neural network,” Machine vision and applications, vol. 10, no. 5-6, pp. 292–307, 1998" } ], "record": { "registrant": "Longman Publishers", "registered": "2026-09-18", "updated": "2026-09-21", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "url_after": "https://www.jst.org.in/index.php/pub/article/view/713", "sha256_before": null, "sha256_after": "e0d1cb99ed72b21a240eec00eb534de09eea602729280bdcaead9e8a063155c7" }, { "seq": 2, "kind": "update", "at": "2026-09-30 00:00:01", "by": "Administrator (admin)", "by_kind": "user", "note": "record re-read from api.crossref.org", "changes": [ { "path": "container.titles.0.value", "from": "Journal of Science & Technology", "to": "Journal of Science & Technology" } ], "record_after": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2023.v8.i07.pp47-57", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "SIGN LANGUAGE RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2023.v8.i07.pp47-57" } ], "agents": [ { "role": "author", "name": { "given": "DR.N.", "family": "SREEKANTH" }, "sequence": "first" }, { "role": "author", "name": { "given": "", "family": "PRACHI" }, "sequence": "additional" }, { "role": "author", "name": { "given": "K.SAI", "family": "KIRTHANA" }, "sequence": "additional" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2023-07-24", "date_type": "PublicationDate", "online": "2023-07-24" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "08", "issue": "07", "pages": { "first": "47", "last": "57" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/713", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/713/643", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/713/4084", "purpose": "text-mining", "return_type": "application/xml" }, { "url": "https://www.jst.org.in/index.php/pub/article/view/713/643", "purpose": "similarity-checking" } ], "abstract": { "value": "Sign Language Recognition (SLR) targets on interpreting the sign language into text or speech, so as to facilitate the communication between deaf-mute people and ordinary people. This task has broad social impact, but is still very challenging due to the complexity and large variations in hand actions. Existing methods for SLR use hand-crafted features to describe sign language motion and build classification models based on those features. However, it is difficult to design reliable features to adapt to the large variations of hand gestures. To approach this problem, we propose a novel convolutional neural network (CNN) which extracts discriminative spatial-temporal features from raw video stream automatically without any prior knowledge, avoiding designing features. To boost the performance, multi-channels of video streams, including color information, depth clue, and body joint positions, are used as input to the CNN in order to integrate color, depth and trajectory information. We validate the proposed model on a real dataset collected with Microsoft Kinect and demonstrate its effectiveness over the traditional approaches based on hand-crafted features", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2023-07-24", "applies_to": "vor" }, "references": [ { "key": "ref1", "doi": "10.1145/3065386", "unstructured": "Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in neural information processing systems, 2012, pp. 1097–1105" }, { "key": "ref2", "doi": "10.1109/cvpr.2014.223", "unstructured": "Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, and Li Fei-Fei, “Large-scale video classification with convolutional neural networks,” in CVPR, 2014" }, { "key": "ref3", "doi": "10.1109/5.726791", "unstructured": "Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick ´ Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998" }, { "key": "ref4", "doi": "10.1109/iccv.2007.4408988", "unstructured": "Hueihan Jhuang, Thomas Serre, Lior Wolf, and Tomaso Poggio, “A biologically inspired system for action recognition,” in Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on. Ieee, 2007, pp. 1–8" }, { "key": "ref5", "doi": "10.1109/tpami.2012.59", "unstructured": "Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu, “3D convolutional neural networks for human action recognition,” IEEE TPAMI, vol. 35, no. 1, pp. 221–231, 2013" }, { "key": "ref6", "doi": "10.1109/icsmc.1997.625742", "unstructured": "Kirsti Grobel and Marcell Assan, “Isolated sign language recognition using hidden markov models,” in Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on. IEEE, 1997, vol. 1, pp. 162–167" }, { "key": "ref7", "doi": "10.1109/34.735811", "unstructured": "Thad Starner, Joshua Weaver, and Alex Pentland, “Realtime american sign language recognition using desk and wearable computer based video,” IEEE TPAMI, vol. 20, no. 12, pp. 1371–1375, 1998" }, { "key": "ref8", "doi": "10.1109/iccv.1999.791206", "unstructured": "Christian Vogler and Dimitris Metaxas, “Parallel hidden markov models for american sign language recognition,” in Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on. IEEE, 1999, vol. 1, pp. 116–122" }, { "key": "ref9", "doi": "10.1145/108844.108900", "unstructured": "Kouichi Murakami and Hitomi Taguchi, “Gesture recognition using recurrent neural networks,” in Proceedings of the SIGCHI conference on Human factors in computing systems. ACM, 1991, pp. 237–242" }, { "key": "ref10", "doi": "10.1007/s001380050080", "unstructured": "Chung-Lin Huang and Wen-Yi Huang, “Sign language recognition using model-based tracking and a 3D hopfield neural network,” Machine vision and applications, vol. 10, no. 5-6, pp. 292–307, 1998" } ], "record": { "registrant": "Longman Publishers", "registered": "2026-09-18", "updated": "2026-09-21", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "url_after": "https://www.jst.org.in/index.php/pub/article/view/713", "sha256_before": "e0d1cb99ed72b21a240eec00eb534de09eea602729280bdcaead9e8a063155c7", "sha256_after": "59e257264adb9e18cf1b83b7d52c8e7c4608d716c0ebc7072b8348b8e3f75444" } ] }