Segmentation and visualization of the Shampula dragonfly eye glass bead CT images using a deep learning method
Abstract Micro-computed tomography (CT) of ancient Chinese glass dragonfly eye beads has enabled detailed exploration of their internal structures, contributing to our understanding of their manufacture. Segmentation of these CT images is essential but challenging due to variation in grayscale value...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-11-01
|
| Series: | Heritage Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40494-024-01505-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846171742011129856 |
|---|---|
| author | Lingyu Liao Qian Cheng Xueyan Zhang Liang Qu Siran Liu Shining Ma Kunlong Chen Yue Liu Yongtian Wang Weitao Song |
| author_facet | Lingyu Liao Qian Cheng Xueyan Zhang Liang Qu Siran Liu Shining Ma Kunlong Chen Yue Liu Yongtian Wang Weitao Song |
| author_sort | Lingyu Liao |
| collection | DOAJ |
| description | Abstract Micro-computed tomography (CT) of ancient Chinese glass dragonfly eye beads has enabled detailed exploration of their internal structures, contributing to our understanding of their manufacture. Segmentation of these CT images is essential but challenging due to variation in grayscale values and the presence of bubbles. This study introduces a U-Net-based model called EBV-SegNet, which enables efficient and accurate segmentation and visualization of these beads. We developed, trained, and tested the model using a dataset comprising four typical Shampula dragonfly eye beads, and the results demonstrated high-precision segmentation and precise delineation of the beads’ complex structures. These segmented data were further analyzed using the Visualization Toolkit for advanced volume rendering and reconstruction. Our application of EBV-SegNet to Shampula beads suggests the likelihood of two distinct manufacturing techniques, underscoring the potential of the model for enhancing the analysis of cultural artifacts using three-dimensional visualization and deep learning. |
| format | Article |
| id | doaj-art-6904288e5ea943e9b99717351a96d1e8 |
| institution | Kabale University |
| issn | 2050-7445 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Heritage Science |
| spelling | doaj-art-6904288e5ea943e9b99717351a96d1e82024-11-10T12:37:11ZengSpringerOpenHeritage Science2050-74452024-11-0112111510.1186/s40494-024-01505-wSegmentation and visualization of the Shampula dragonfly eye glass bead CT images using a deep learning methodLingyu Liao0Qian Cheng1Xueyan Zhang2Liang Qu3Siran Liu4Shining Ma5Kunlong Chen6Yue Liu7Yongtian Wang8Weitao Song9Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of TechnologySTARC, The Cyprus InstituteDepartment of Conservation Standards, The Palace MuseumDepartment of Conservation Standards, The Palace MuseumInstitute for Cultural Heritage and History of Science & Technology, University of Science and TechnologyBeijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of TechnologyInstitute for Cultural Heritage and History of Science & Technology, University of Science and TechnologyBeijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of TechnologyBeijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of TechnologyBeijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of TechnologyAbstract Micro-computed tomography (CT) of ancient Chinese glass dragonfly eye beads has enabled detailed exploration of their internal structures, contributing to our understanding of their manufacture. Segmentation of these CT images is essential but challenging due to variation in grayscale values and the presence of bubbles. This study introduces a U-Net-based model called EBV-SegNet, which enables efficient and accurate segmentation and visualization of these beads. We developed, trained, and tested the model using a dataset comprising four typical Shampula dragonfly eye beads, and the results demonstrated high-precision segmentation and precise delineation of the beads’ complex structures. These segmented data were further analyzed using the Visualization Toolkit for advanced volume rendering and reconstruction. Our application of EBV-SegNet to Shampula beads suggests the likelihood of two distinct manufacturing techniques, underscoring the potential of the model for enhancing the analysis of cultural artifacts using three-dimensional visualization and deep learning.https://doi.org/10.1186/s40494-024-01505-wDragonfly eye glass beadsCT image segmentationU-Net3D visualization |
| spellingShingle | Lingyu Liao Qian Cheng Xueyan Zhang Liang Qu Siran Liu Shining Ma Kunlong Chen Yue Liu Yongtian Wang Weitao Song Segmentation and visualization of the Shampula dragonfly eye glass bead CT images using a deep learning method Heritage Science Dragonfly eye glass beads CT image segmentation U-Net 3D visualization |
| title | Segmentation and visualization of the Shampula dragonfly eye glass bead CT images using a deep learning method |
| title_full | Segmentation and visualization of the Shampula dragonfly eye glass bead CT images using a deep learning method |
| title_fullStr | Segmentation and visualization of the Shampula dragonfly eye glass bead CT images using a deep learning method |
| title_full_unstemmed | Segmentation and visualization of the Shampula dragonfly eye glass bead CT images using a deep learning method |
| title_short | Segmentation and visualization of the Shampula dragonfly eye glass bead CT images using a deep learning method |
| title_sort | segmentation and visualization of the shampula dragonfly eye glass bead ct images using a deep learning method |
| topic | Dragonfly eye glass beads CT image segmentation U-Net 3D visualization |
| url | https://doi.org/10.1186/s40494-024-01505-w |
| work_keys_str_mv | AT lingyuliao segmentationandvisualizationoftheshampuladragonflyeyeglassbeadctimagesusingadeeplearningmethod AT qiancheng segmentationandvisualizationoftheshampuladragonflyeyeglassbeadctimagesusingadeeplearningmethod AT xueyanzhang segmentationandvisualizationoftheshampuladragonflyeyeglassbeadctimagesusingadeeplearningmethod AT liangqu segmentationandvisualizationoftheshampuladragonflyeyeglassbeadctimagesusingadeeplearningmethod AT siranliu segmentationandvisualizationoftheshampuladragonflyeyeglassbeadctimagesusingadeeplearningmethod AT shiningma segmentationandvisualizationoftheshampuladragonflyeyeglassbeadctimagesusingadeeplearningmethod AT kunlongchen segmentationandvisualizationoftheshampuladragonflyeyeglassbeadctimagesusingadeeplearningmethod AT yueliu segmentationandvisualizationoftheshampuladragonflyeyeglassbeadctimagesusingadeeplearningmethod AT yongtianwang segmentationandvisualizationoftheshampuladragonflyeyeglassbeadctimagesusingadeeplearningmethod AT weitaosong segmentationandvisualizationoftheshampuladragonflyeyeglassbeadctimagesusingadeeplearningmethod |