PERBANDINGAN SEGMENTASI CITRA SENI TARI PENDET DAN SENI BELA DIRI PENCAK SILAT: PENDEKATAN DENGAN MULTIRES UNET
DOI:
https://doi.org/10.23960/jitet.v12i3.4331Abstract Views: 227 File Views: 236
Abstract
This research compares image segmentation of the Pendet dance art and the Pencak Silat martial art using the MultiRes U-Net approach. Research methods include data collection, data pre-processing, data sharing, evaluation, and results. Evaluation results using the Dice coefficient, Jaccard index, and Mean Squared Error (MSE) metrics show the best scores for each dataset. The results of this research can increase understanding of these two arts and cultures through deeper visual analysis. The results of the image segmentation evaluation between Pendet dance and Pencak Silat martial arts using the MultiRes UNET approach show the best scores for Dice Coefficient (DC), Jaccard index, and Mean Squared Error (MSE). The best scores for the Pendet dance dataset are 98.47, 99.23, and 8.20E-04, while for the Pencak Silat dataset they are 88.29, 85.98, and 4.52E-04. Evaluation shows a good level of similarity between the segmented image and the original image.Downloads
References
K. V. V Kumar and P. V. V Kishore, “Indian Classical Dance Mudra Classification Using HOG Features and SVM Classifier,” International Journal of Electrical and Computer Engineering (IJECE), vol. 7, no. 5, pp. 2537–2546, 2017, doi: 10.11591/ijece.v7i1.pp2537-2546.
F. Sun, V. Ajith Kumar, G. Yang, A. Zhang, and Y. Zhang, “Circle-u-net: An efficient architecture for semantic segmentation,” Algorithms, vol. 14, no. 6. MDPI AG, 2021. doi: 10.3390/a14060159.
N. Ibtehaz and M. S. Rahman, “MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation,” Neural Networks, vol. 121, pp. 74–87, Jan. 2020, doi: 10.1016/j.neunet.2019.08.025.
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” May 2015, [Online]. Available: http://arxiv.org/abs/1505.04597
Data Science meets Cyber Security, “IMAGE SEGMENTATION: A COMPREHENSIVE GUIDE.” Accessed: Mar. 21, 2024. [Online]. Available: https://medium.com/@datasciencemeetscybersecurity/image-segmentation-a-comprehensive-guide-c5ccded8af70
S. Ediyono, S. Teguh, W. Fakultas, and I. Budaya, “Memahami Makna Seni dalam Pencak Silat.”
L. Y. MENG and Y. KARULUS, “THE INDONESIA-MALAYSIA CULTURAL HERITAGE DISPUTES: A CASE STUDY OF THE PENDET DANCE AND RASA SAYANGE FOLK SONG,” MANU Jurnal Pusat Penataran Ilmu dan Bahasa (PPIB), Jun. 2019, doi: 10.51200/manu.v0i0.1880.
K. Armanious, V. Kumar, S. Abdulatif, T. Hepp, S. Gatidis, and B. Yang, “ipA-MedGAN: INPAINTING OF ARBITRARY REGIONS IN MEDICAL IMAGING,” 2020.
K. B. Soulami, N. Kaabouch, M. N. Saidi, and A. Tamtaoui, “Breast cancer: One-stage automated detection, segmentation, and classification of digital mammograms using UNet model based-semantic segmentation,” Biomed Signal Process Control, vol. 66, Apr. 2021, doi: 10.1016/j.bspc.2021.102481.
K. Sanjar, O. Bekhzod, J. Kim, J. Kim, A. Paul, and J. Kim, “Improved U-net: Fully convolutional network model for skin-lesion segmentation,” Applied Sciences (Switzerland), vol. 10, no. 10, May 2020, doi: 10.3390/app10103658.
C. Mythili and V. Kavitha, “Color Image Segmentation using ERKFCM,” 2012.
Z. Alom, C. Yakopcic, T. M. Taha, and V. K. Asari, Nuclei Segmentation with Recurrent Residual Convolutional Neural Networks based U-Net (R2U-Net). 2018.
