Klasifikasi Bahasa Isyarat Amerika menggunakan Convolutional Neural Network

Felicia Devina Siswanto, Caecilia Citra Lestari, Evan Tanuwijaya

Abstract


Bahasa Isyarat adalah bahasa untuk orang - orang yang memiliki kesulitan mendengar maupun bicara. Tetapi bahasa isyarat bukanlah bahasa yang banyak digemari oleh masyarakat, sehingga orang yang memiliki disabilitas tersebut akan semakin kesulitan. Pada jurnal ini akan menjelaskan mengenai klasifikasi bahasa isyarat Amerika dengan menggunakan Convolutional Neural Network (CNN). Pada penelitian ini akan dilakukan beberapa penelitian menggunakan parameter berbeda seperti pada preprocessing, penelitian akan dilakukan dengan melihat parameter horizontal flip. Selanjutnya penelitian juga dilakukan dengan melihat epoch. Penelitian ini dilakukan untuk memantau akurasi dan akurasi validasi. Model yang dibuat pada penelitian ini nilai akurasi yang lebih tinggi saat memprediksi huruf v, dan n. Hasil nilai akurasi dari penelitian ini adalah 82.1%


Sign Language is a language for people who have hearing and speech difficulties. But sign language is not a language  that is favored by many people, so people with disabilities will find it increasingly difficult. This journal will explain the classification of American sign language using the Convolutional Neural Network (CNN). In this study, several studies will be carried out using different parameters such as in preprocessing, research will be carried out by looking at the horizontal flip parameter. Furthermore, research was also carried out by looking at the epoch. This study was conducted to monitor the accuracy and accuracy of the validation. The model made in this study has a higher accuracy value when predicting the letters v, and n. The result of the accuracy value of this study is 82.1%


Keywords


CNN; Deep Learning; ASL

Full Text:

PDF

References


K. Kesehatan RI, "SITUASI PENYANDANG DISABILITAS", Pusdatin.kemkes.go.id, 2014. [Online]. Available: https://pusdatin.kemkes.go.id/download.php?file=download/pusdatin/buletin/buletin-disabilitas.pdf. [Accessed: 05- Jun- 2021]

"Sumbar Hanya Punya 8 Penerjemah Bahasa Isyarat |Republika Online", Republika Online, 2019. [Online]. Available: https://www.republika.co.id/berita/pzjwqr335/sumbar-hanya-punya-8-penerjemah-bahasa-isyarat. [Accessed: 05- Jun- 2021]

L. Zheng, B. Liang and A. Jiang, "Recent Advances of Deep Learning for Sign Language Recognition," 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2017, pp. 1-7, doi: 10.1109/DICTA.2017.8227483.

H. Kulhandjian, P. Sharma, M. Kulhandjian and C. D'Amours, "Sign Language Gesture Recognition Using Doppler Radar and Deep Learning," 2019 IEEE Globecom Workshops (GC Wkshps), 2019, pp. 1-6, doi: 10.1109/GCWkshps45667.2019.9024607.

M.A. Jalal, R. Chen, R.K. Moore and L. Mihaylova, “American sign language posture understanding with deep neural networks,” in Proc. of IEEE International Conference on Information Fusion (FUSION), Cambridge, UK, Jul. 2018, pp. 573-579.

G. A. Rao, K. Syamala, P. V. V. Kishore and A. S. C. S. Sastry, "Deep convolutional neural networks for sign language recognition," 2018 Conference on Signal Processing And Communication Engineering Systems (SPACES), 2018, pp. 194-197, doi: 10.1109/SPACES.2018.8316344.

A. Das, S. Gawde, K. Suratwala and D. Kalbande, "Sign Language Recognition Using Deep Learning on Custom Processed Static Gesture Images," 2018 International Conference on Smart City and Emerging Technology (ICSCET), 2018, pp. 1-6, doi: 10.1109/ICSCET.2018.8537248.

"ASL Alphabet", Kaggle.com, 2018. [Online]. Available: https://www.kaggle.com/grassknoted/asl-alphabet. [Accessed: 10- Jun- 2021]

"tf.keras.preprocessing.image.ImageDataGenerator", TensorFlow, [Online]. Available: https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/image/ImageDataGenerator. [Accessed: 05- Jun- 2021]

Suresh, S., T. P., M. H., & M.H, S. (2019). Sign Language Recognition System Using Deep Neural Network. 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS). doi:10.1109/icaccs.2019.8728411

Bheda, Vivek & Radpour, Dianna. (2017). Using Deep Convolutional Networks for Gesture Recognition in American Sign Language.

K. Team, "Keras documentation: The Sequential model", Keras.io, [Online]. Available: https://keras.io/guides/sequential_model/. [Accessed: 05- Jun- 2021]

K. Team, "Keras documentation: Conv2D layer", Keras.io. [Online]. Available: https://keras.io/api/layers/convolution_layers/convolution2d/. [Accessed: 5- Jun- 2021]

K. Team, "Keras documentation: Dropout layer", Keras.io. [Online]. Available: https://keras.io/api/layers/regularization_layers/dropout/. [Accessed: 05- Jun- 2021]

K. Team, "Keras documentation: Flatten layer", Keras.io. [Online]. Available: https://keras.io/api/layers/reshaping_layers/flatten/. [Accessed: 10- Jun- 2021]




DOI: http://dx.doi.org/10.26418/justin.v10i1.47184

Refbacks

  • There are currently no refbacks.


Copyright (c) 2022 JUSTIN (Jurnal Sistem dan Teknologi Informasi)

ara komputer
View My Stats

Creative Commons License
All article in Justin is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License