Deep Forest-Based Monocular Visual Sign Language Recognition
Sign language recognition (SLR) is a bridge linking the hearing impaired and the general public. Some SLR methods using wearable data gloves are not portable enough to provide daily sign language translation service, while visual SLR is more flexible to work with in most scenes. This paper introduce...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/9/1945 |
| _version_ | 1819050408881946624 |
|---|---|
| author | Qifan Xue Xuanpeng Li Dong Wang Weigong Zhang |
| author_facet | Qifan Xue Xuanpeng Li Dong Wang Weigong Zhang |
| author_sort | Qifan Xue |
| collection | DOAJ |
| description | Sign language recognition (SLR) is a bridge linking the hearing impaired and the general public. Some SLR methods using wearable data gloves are not portable enough to provide daily sign language translation service, while visual SLR is more flexible to work with in most scenes. This paper introduces a monocular vision-based approach to SLR. Human skeleton action recognition is proposed to express semantic information, including the representation of signs’ gestures, using the regularization of body joint features and a deep-forest-based semantic classifier with a voting strategy. We test our approach on the public American Sign Language Lexicon Video Dataset (ASLLVD) and a private testing set. It proves to achieve a promising performance and shows a high generalization capability on the testing set. |
| first_indexed | 2024-12-21T11:47:35Z |
| format | Article |
| id | doaj.art-52bc2d7e62f34d9c8f4dcb107ea3fe0a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-21T11:47:35Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-52bc2d7e62f34d9c8f4dcb107ea3fe0a2022-12-21T19:05:08ZengMDPI AGApplied Sciences2076-34172019-05-0199194510.3390/app9091945app9091945Deep Forest-Based Monocular Visual Sign Language RecognitionQifan Xue0Xuanpeng Li1Dong Wang2Weigong Zhang3School of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSign language recognition (SLR) is a bridge linking the hearing impaired and the general public. Some SLR methods using wearable data gloves are not portable enough to provide daily sign language translation service, while visual SLR is more flexible to work with in most scenes. This paper introduces a monocular vision-based approach to SLR. Human skeleton action recognition is proposed to express semantic information, including the representation of signs’ gestures, using the regularization of body joint features and a deep-forest-based semantic classifier with a voting strategy. We test our approach on the public American Sign Language Lexicon Video Dataset (ASLLVD) and a private testing set. It proves to achieve a promising performance and shows a high generalization capability on the testing set.https://www.mdpi.com/2076-3417/9/9/1945sign language recognitionmonocular visiondeep forest |
| spellingShingle | Qifan Xue Xuanpeng Li Dong Wang Weigong Zhang Deep Forest-Based Monocular Visual Sign Language Recognition Applied Sciences sign language recognition monocular vision deep forest |
| title | Deep Forest-Based Monocular Visual Sign Language Recognition |
| title_full | Deep Forest-Based Monocular Visual Sign Language Recognition |
| title_fullStr | Deep Forest-Based Monocular Visual Sign Language Recognition |
| title_full_unstemmed | Deep Forest-Based Monocular Visual Sign Language Recognition |
| title_short | Deep Forest-Based Monocular Visual Sign Language Recognition |
| title_sort | deep forest based monocular visual sign language recognition |
| topic | sign language recognition monocular vision deep forest |
| url | https://www.mdpi.com/2076-3417/9/9/1945 |
| work_keys_str_mv | AT qifanxue deepforestbasedmonocularvisualsignlanguagerecognition AT xuanpengli deepforestbasedmonocularvisualsignlanguagerecognition AT dongwang deepforestbasedmonocularvisualsignlanguagerecognition AT weigongzhang deepforestbasedmonocularvisualsignlanguagerecognition |