Detection of Turkish Sign Language Using Deep Learning and Image Processing Methods
Sign language is a physical language that enables people with disabilities to communicate using hand and facial gestures. For this reason, it is very important for people with disabilities to express themselves freely in society and to make the sign language understandable to everyone. In this study...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2021-10-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | http://dx.doi.org/10.1080/08839514.2021.1982184 |
| _version_ | 1797684857442140160 |
|---|---|
| author | Bekir Aksoy Osamah Khaled Musleh Salman Özge Ekrem |
| author_facet | Bekir Aksoy Osamah Khaled Musleh Salman Özge Ekrem |
| author_sort | Bekir Aksoy |
| collection | DOAJ |
| description | Sign language is a physical language that enables people with disabilities to communicate using hand and facial gestures. For this reason, it is very important for people with disabilities to express themselves freely in society and to make the sign language understandable to everyone. In this study, the data set was created by taking 10223 images for 29 letters in the Turkish Sign Language Alphabet. Images are made suitable for education by using image enhancement techniques. In the final stage of the study, classification processes on images were carried out by using CapsNet, AlexNet and ResNet-50, DenseNet, VGG16, Xception, InceptionV3, NasNet, EfficentNet, Hitnet, Squeezenet architectures and TSLNet, which was designed for the study. When the deep learning models were examined, it was found that CapsNet and TSLNet models were the most successful models with 99.7% and 99.6% accuracy rates, respectively. |
| first_indexed | 2024-03-12T00:35:45Z |
| format | Article |
| id | doaj.art-15d899a68df04610963cfe3a44904c9a |
| institution | Directory Open Access Journal |
| issn | 0883-9514 1087-6545 |
| language | English |
| last_indexed | 2024-03-12T00:35:45Z |
| publishDate | 2021-10-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj.art-15d899a68df04610963cfe3a44904c9a2023-09-15T09:33:59ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452021-10-01351295298110.1080/08839514.2021.19821841982184Detection of Turkish Sign Language Using Deep Learning and Image Processing MethodsBekir Aksoy0Osamah Khaled Musleh Salman1Özge Ekrem2Isparta University of Applied Sciences Technology FacultyIsparta University of Applied Sciences Technology FacultyIsparta University of Applied Sciences Technology FacultySign language is a physical language that enables people with disabilities to communicate using hand and facial gestures. For this reason, it is very important for people with disabilities to express themselves freely in society and to make the sign language understandable to everyone. In this study, the data set was created by taking 10223 images for 29 letters in the Turkish Sign Language Alphabet. Images are made suitable for education by using image enhancement techniques. In the final stage of the study, classification processes on images were carried out by using CapsNet, AlexNet and ResNet-50, DenseNet, VGG16, Xception, InceptionV3, NasNet, EfficentNet, Hitnet, Squeezenet architectures and TSLNet, which was designed for the study. When the deep learning models were examined, it was found that CapsNet and TSLNet models were the most successful models with 99.7% and 99.6% accuracy rates, respectively.http://dx.doi.org/10.1080/08839514.2021.1982184 |
| spellingShingle | Bekir Aksoy Osamah Khaled Musleh Salman Özge Ekrem Detection of Turkish Sign Language Using Deep Learning and Image Processing Methods Applied Artificial Intelligence |
| title | Detection of Turkish Sign Language Using Deep Learning and Image Processing Methods |
| title_full | Detection of Turkish Sign Language Using Deep Learning and Image Processing Methods |
| title_fullStr | Detection of Turkish Sign Language Using Deep Learning and Image Processing Methods |
| title_full_unstemmed | Detection of Turkish Sign Language Using Deep Learning and Image Processing Methods |
| title_short | Detection of Turkish Sign Language Using Deep Learning and Image Processing Methods |
| title_sort | detection of turkish sign language using deep learning and image processing methods |
| url | http://dx.doi.org/10.1080/08839514.2021.1982184 |
| work_keys_str_mv | AT bekiraksoy detectionofturkishsignlanguageusingdeeplearningandimageprocessingmethods AT osamahkhaledmuslehsalman detectionofturkishsignlanguageusingdeeplearningandimageprocessingmethods AT ozgeekrem detectionofturkishsignlanguageusingdeeplearningandimageprocessingmethods |