Sistem Verifikasi Kekerabatan berbasis 3D ResNet-18 menggunakan Jetson Nano

FAUZAN AWWAL MUKHRODI, IKE FIBRIANI, KHAIRUL ANAM, ALI RIZAL CHAIDIR

Sari


ABSTRAK

Verifikasi kekerabatan berbasis citra wajah merupakan salah satu penerapan sistem Artificial Intelligence yang berguna dalam kehidupan, misalnya untuk penyelidikan kriminal, analisis silsilah, dan lainnya. Perancangan sistem pengenalan wajah pada verifikasi kekerabatan dapat dilakukan menggunakan salah satu algoritma deep learning yaitu metode Convolutional Neural Network. Penelitian ini dilakukan dengan tujuan untuk mengetahui kinerja dari 3D ResNet-18 pada verifikasi kekerabatan berdasarkan sistem pengenalan wajah dan mengetahui kinerja 3D ResNet-18 saat menggunakan embedded system secara real time. Hasil penelitian kinerja ResNet-18 tanpa embedded system memperoleh nilai akurasi training sebesar 0,9771 menggunakan optimizer RMSprop dengan epoch 30 dan batch size 25. Pada pengujian kinerja real time ResNet-18, optimizer SGD berhasil pada ukuran batch size 10, 15, dan 25. Namun untuk pengujian pada perangkat Jetson Nano, optimizer RMSprop gagal akibat ukuran model yang terlalu besar.

Kata kunci: embedded sistem, CNN, 3D Resnet18, RMSprop, kekerabatan

 

ABSTRACT

Face-based kinship verification is one of the applications of artificial intelligence systems that are useful in various aspects of life, such as criminal investigations, pedigree analysis, and more. The design of a face recognition system for kinship verification can be done using one of the deep learning algorithms, namely the convolutional neural network method. This research was conducted with the aim of determining the performance of 3D ResNet-18 in kinship verification based on face recognition systems and assessing the performance of 3D ResNet-18 when using an embedded system in real time. The results of the ResNet-18 performance research without an embedded system obtained a training accuracy of 0.9771 using the RMSprop optimizer with 30 epochs and a batch size of 25. In real-time performance testing of ResNet-18, the SGD optimizer succeeded with batch sizes of 10, 15, and 25. However, during testing on the Jetson Nano device, the RMSprop optimizer failed due to the size of the model being too large.

Keywords: Embedded System, CNN, 3D Resnet-18, RMSprop, Kinship


Kata Kunci


embedded sistem; CNN; 3D Resnet18; RMSprop; kekerabatan

Teks Lengkap:

PDF

Referensi


Arunnehru, J., Chamundeeswari, G., & Bharathi, S. P. (2018). Human Action Recognition using 3D Convolutional Neural Networks with 3D Motion Cuboids in Surveillance Videos. Procedia Computer Science, 133, 471–477. https://doi.org/10.1016/j.procs.2018.07.059

Chergui, A., Ouchtati, S., Mavromatis, S., Bekhouche, S. E., Lashab, M., & Sequeira, J. (2020). Kinship verification through facial images using CNN-based features. Traitement Du Signal, 37(1), 1–8. https://doi.org/10.18280/ts.370101

Dibeklioglu, H. (2017). Visual Transformation Aided Contrastive Learning for Video-Based Kinship Verification. Proceedings of the IEEE International Conference on Computer Vision, 2017-Octob(October 2017), 2478–2487. https://doi.org/10.1109/ICCV.2017.269

He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. http://image-net.org/challenges/LSVRC/2015/

IIKKA TEIVAS. (2017). Video event classification using 3D convolutional neural networks. In aster of science thesis in information technology, Tampere University of Technology (Issue December). https://dspace.cc.tut.fi/dpub/handle/123456789/24703

Kim, B.-G. (2020). Real-time Facial Expression Recognition using 3D Appearance and Geometric Network for Public Security. Journal of Defense Acquisition and Technology, 2(1), 33–37. https://doi.org/10.33530/jdaat.2020.2.1.33

Qin, X., Tan, X., & Chen, S. (2015). Tri-Subject Kinship Verification: Understanding the Core of A Family. http://arxiv.org/abs/1501.02555

Rachmadi, R. F., & Purnama, I. K. E. (2018). Paralel Spatial Pyramid Convolutional Neural Network untuk Verifikasi Kekerabatan berbasis Citra Wajah. Jurnal Teknologi Dan Sistem Komputer, 6(4), 152–157.

Sasono, M. A. H. (2022). Pengenalan Pola Gerak Tangan Fungsional Pada Bidang Pertanian Berbasis Electroencephalograph Untuk Kontrol Robot Tangan Dengan Kombinasi Metode Long Short-Term Memory Dan Stacked Autoencoder.

Sokop, S. J., Mamahit, D. J., Eng, M., Sompie, S. R. U. A., Mahasiswa, ), & Pembimbing, ). (2016). Trainer Periferal Antarmuka Berbasis Mikrokontroler Arduino Uno. Jurnal Teknik Elektro Dan Komputer, 5(3), 13–23. https://ejournal.unsrat.ac.id/index.php/elekdankom/article/view/11999

Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3D convolutional networks. Proceedings of the IEEE International Conference on Computer Vision, 2015 Inter, 4489–4497. https://doi.org/10.1109/ICCV.2015.510

Vikram, K. & Padmavathi, S. (2017). Facial Parts Detection Using Viola. International Conference on Advanced Computing and Communication Systems (ICACCS -2015), (pp. 1–4).

Viola, P., & Jones, M. (2018). Rapid Object Detection using a Boosted Cascade of Simple Feature. 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing, ICECDS 2017, 1193–1197. https://doi.org/10.1109/ICECDS.2017.8389630

Vu, D. Q., Le, N. T. H., & Wang, J.-C. (2021). Self-Supervised Learning via multi-Transformation Classification for Action Recognition. http://arxiv.org/abs/2102.10378

Wang, M., Feng, J., Shu, X., Jie, Z., & Tang, J. (2018). Photo to family tree: Deep kinship understanding for nuclear family photos. ASMMC-MMAC 2018 - Proceedings of the Joint Workshop of the 4th Workshop on Affective Social Multimedia Computing and 1st Multi-Modal Affective Computing of Large-Scale Multimedia Data, Co-Located with MM 2018, (pp. 41-46). https://doi.org/10.1145/3267935.3267936




DOI: https://doi.org/10.26760/elkomika.v11i4.919

Refbacks

  • Saat ini tidak ada refbacks.


_______________________________________________________________________________________________________________________

ISSN (cetak) : 2338-8323 | ISSN (elektronik) : 2459-9638

diterbitkan oleh :

Teknik Elektro Institut Teknologi Nasional Bandung

Alamat : Gedung 20 Jl. PHH. Mustofa 23 Bandung 40124

Kontak : Tel. 7272215 (ext. 206) Fax. 7202892

Surat Elektronik : jte.itenas@itenas.ac.id________________________________________________________________________________________________________________________

Statistik Pengunjung

Free counters!

Web Analytics Made Easy - StatCounter

Lihat Statistik Jurnal

Jurnal ini terlisensi oleh Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons License