PENGENALAN SISTEM ISYARAT BAHASA INDONESIA (SIBI) MENGGUNAKAN GRADIENT-CONVOLUTIONAL NEURAL NETWORK

DARMATASIA DARMATASIA

Abstract


Penelitian ini bertujuan untuk melakukan pengenalan alfabet pada Sistem Isyarat Bahasa Indonesia (SIBI). Penelitian ini memiliki dua kontribusi utama,  Pertama dilakukan pengumpulan dataset alfabet SIBI. Kedua, pengenalan alfabet SIBI menggunakan algoritma Convolutional Neural Network (CNN). Pada penelitian ini, citra masukan berupa alfabet bahasa isyarat pada lapisan input diberikan filter gradient agar bentuk objek menjadi lebih jelas. Hasil penelitian menunjukkan bahwa pemberian filter pada lapisan input dapat meningkatkan akurasi pengenalan yaitu sekitar 85%. Citra masukan yang tidak difilter hanya memperoleh akurasi sebesar 25%. Akurasi terbaik yang diperoleh yaitu 98% dengan meningkatkan jumlah iterasi. Metode yang diusulkan juga diuji menggunakan tiga benchmark dataset. Hasil pengujian menunjukkan  bahwa metode yang diusulkan dapat meningkatkan akurasi pengenalan pada benchmark dataset yang memiliki background yang kompleks.

Kata Kunci: Convolutional Neural Network; Gradient; Sistem Isyarat Bahasa Indonesia

 


Full Text:

PDF

References


Hartanto, Rudy, Susanto, A., & Santosa, P. I. 2013. Preliminary design of static indonesian sign language recognition system. 2013 International Conference on Information Technology and Electrical Engineering (ICITEE), 2, 187–192. https://doi.org/10.1109/ICITEED.2013.6676236

Jie Huang, Wengang Zhou, Houqiang Li, & Weiping Li. 2015. Sign Language Recognition using 3D convolutional neural networks. 2015 IEEE International Conference on Multimedia and Expo (ICME), 1–6. https://doi.org/10.1109/ICME.2015.7177428

Kawulok, M., Tomasz, G., Nalepa, J., & Knyc, M. 2013. Database for hand gesture recognition. http://sun.aei.polsl.pl/~mkawulok/gestures/

Lee, J. S., & Park, J.-H. 2008. Dynamic hand gesture recognition using a CNN model with 3D receptive fields. 2008 International Conference on Neural Networks and Signal Processing, 14–19. https://doi.org/10.1109/ICNNSP.2008.4590300

Massey, U. 2012. Gesture Dataset. Massey University. http://www.massey.ac.nz/~albarcza/gesture_dataset2012.html

Michael Nielsen. 2015. Deep Learning. http://neuralnetworksanddeeplearning.com/chap6.html

Molchanov, P., Gupta, S., Kim, K., Kautz, J., & Clara, S. 2015. Hand Gesture Recognition with 3D Convolutional Neural Networks. 1–7.

Nagi, J., Ducatelle, F., Caro, G. a. Di, Ciresan, D., Meier, U., Giusti, A., Nagi, F., Schmidhuber, J., & Gambardella, L. M. 2011. Max-pooling convolutional neural networks for vision-based hand gesture recognition. 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), 342–347. https://doi.org/10.1109/ICSIPA.2011.6144164

Panwar, M. 2012. Hand gesture recognition based on shape parameters. 2012 International Conference on Computing, Communication and Applications, 1–6. https://doi.org/10.1109/ICCCA.2012.6179213

Santoni, M. M., Sensuse, D. I., Arymurthy, A. M., & Fanany, M. I. 2015. Cattle Race Classification Using Gray Level Co-occurrence Matrix Convolutional Neural Networks. Procedia Computer Science, 59(October), 493–502. https://doi.org/10.1016/j.procs.2015.07.525

Sebastian, M. 2012. Hand Posture and Gesture Datasets. https://sites.google.com/site/autosignlan/source/image-data-set

Triesch, J., & von der Malsburg, C. 2001. A system for person-independent hand posture recognition against complex backgrounds. Pattern Analysis and Machine Intelligence, IEEE Transactions On, 23(12), 1449–1453. https://doi.org/10.1109/34.977568

Yamashita, T., & Watasue, T. 2014. Hand posture recognition based on bottom-up structured deep convolutional neural network with curriculum learning. Image Processing (ICIP), 2014 IEEE International Conference On, 853–857. https://doi.org/10.1109/ICIP.2014.7025171




DOI: https://doi.org/10.24252/instek.v6i1.18637

Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 DARMATASIA DARMATASIA

Jurnal INSTEK (Informatika Sains dan Teknologi) is indexed by

  pkp_index_k2  

Creative Commons License

Jurnal INSTEK (Informatika Sains dan Teknologi)

ISSN Print: 2541-1179 ISSN Online: 2581-1711

Jl. H. M. Yasin Limpo No. 36 Samata, Gowa, Sulawesi Selatan
Email: instek@uin-alauddin.ac.id

 View Instek Stats