Semantic segmentation of pendet dance images using multires U-Net architecture
As a cultural heritage, traditional dance must be protected and preserved. Pendet dance is a traditional dance from Bali, Indonesia. Dance recognition raises a complex problem for computer vision research because the features representing the dancer must focus on the dancer's entire body. This...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Fakultas Ilmu Komputer UMI
2022-12-01
|
| Series: | Ilkom Jurnal Ilmiah |
| Subjects: | |
| Online Access: | https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1316 |
| _version_ | 1797850413324566528 |
|---|---|
| author | Hendri Ramdan Moh. Arief Soeleman Purwanto Purwanto Bahtiar Imran Ricardus Anggi Pramunendar |
| author_facet | Hendri Ramdan Moh. Arief Soeleman Purwanto Purwanto Bahtiar Imran Ricardus Anggi Pramunendar |
| author_sort | Hendri Ramdan |
| collection | DOAJ |
| description | As a cultural heritage, traditional dance must be protected and preserved. Pendet dance is a traditional dance from Bali, Indonesia. Dance recognition raises a complex problem for computer vision research because the features representing the dancer must focus on the dancer's entire body. This can be done by performing a segmentation task process. One type of segmentation task in computer vision is the semantic segmentation. Mask R-CNN and U-NET were employed in this task. Since it was first introduced in 2015, semantic segmentation using the U-Net architecture has been widely adopted, developed, and modified. One of the new architectures applied is the MultiRes UNet. This study carries out a semantic segmentation task on the Balinese Pendet dance image using the MultiRes UNet architecture by changing the value of α (alpha) to obtain the best results. This architectural is evaluated by DC score, Jaccard index, and MSE. In this dataset, the alpha value of 1.9 resulted in the best score for DC and the Jaccard index with 98.47% and 99.23% respectively. On the other hand, an alpha value of 1.8 obtained the best score of MSE with 8.20E-04. |
| first_indexed | 2024-04-09T18:59:50Z |
| format | Article |
| id | doaj.art-0b75da3b5781441dbec167e85025bd36 |
| institution | Directory Open Access Journal |
| issn | 2087-1716 2548-7779 |
| language | English |
| last_indexed | 2024-04-09T18:59:50Z |
| publishDate | 2022-12-01 |
| publisher | Fakultas Ilmu Komputer UMI |
| record_format | Article |
| series | Ilkom Jurnal Ilmiah |
| spelling | doaj.art-0b75da3b5781441dbec167e85025bd362023-04-08T08:20:36ZengFakultas Ilmu Komputer UMIIlkom Jurnal Ilmiah2087-17162548-77792022-12-0114332933810.33096/ilkom.v14i3.1316.329-338466Semantic segmentation of pendet dance images using multires U-Net architectureHendri Ramdan0Moh. Arief Soeleman1Purwanto Purwanto2Bahtiar Imran3Ricardus Anggi Pramunendar4Dian Nuswantoro UniversityDian Nuswantoro UniversityDian Nuswantoro UniversityMataram Technology of UniversityDian Nuswantoro UniversityAs a cultural heritage, traditional dance must be protected and preserved. Pendet dance is a traditional dance from Bali, Indonesia. Dance recognition raises a complex problem for computer vision research because the features representing the dancer must focus on the dancer's entire body. This can be done by performing a segmentation task process. One type of segmentation task in computer vision is the semantic segmentation. Mask R-CNN and U-NET were employed in this task. Since it was first introduced in 2015, semantic segmentation using the U-Net architecture has been widely adopted, developed, and modified. One of the new architectures applied is the MultiRes UNet. This study carries out a semantic segmentation task on the Balinese Pendet dance image using the MultiRes UNet architecture by changing the value of α (alpha) to obtain the best results. This architectural is evaluated by DC score, Jaccard index, and MSE. In this dataset, the alpha value of 1.9 resulted in the best score for DC and the Jaccard index with 98.47% and 99.23% respectively. On the other hand, an alpha value of 1.8 obtained the best score of MSE with 8.20E-04.https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1316semantic segmentationu-netmultires unetdeep learningbalinese pendet dance. |
| spellingShingle | Hendri Ramdan Moh. Arief Soeleman Purwanto Purwanto Bahtiar Imran Ricardus Anggi Pramunendar Semantic segmentation of pendet dance images using multires U-Net architecture Ilkom Jurnal Ilmiah semantic segmentation u-net multires unet deep learning balinese pendet dance. |
| title | Semantic segmentation of pendet dance images using multires U-Net architecture |
| title_full | Semantic segmentation of pendet dance images using multires U-Net architecture |
| title_fullStr | Semantic segmentation of pendet dance images using multires U-Net architecture |
| title_full_unstemmed | Semantic segmentation of pendet dance images using multires U-Net architecture |
| title_short | Semantic segmentation of pendet dance images using multires U-Net architecture |
| title_sort | semantic segmentation of pendet dance images using multires u net architecture |
| topic | semantic segmentation u-net multires unet deep learning balinese pendet dance. |
| url | https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1316 |
| work_keys_str_mv | AT hendriramdan semanticsegmentationofpendetdanceimagesusingmultiresunetarchitecture AT mohariefsoeleman semanticsegmentationofpendetdanceimagesusingmultiresunetarchitecture AT purwantopurwanto semanticsegmentationofpendetdanceimagesusingmultiresunetarchitecture AT bahtiarimran semanticsegmentationofpendetdanceimagesusingmultiresunetarchitecture AT ricardusanggipramunendar semanticsegmentationofpendetdanceimagesusingmultiresunetarchitecture |