Microscopic bubbles segmentation of porcelain relics based on improved UNet ++

LIU Yangyang; GENG Guohua; LIU Xinda; LI Zhan; LU Zhenghan

doi:10.16152/j.cnki.xdxbzr.2025-01-011

您当前的位置：

首页 >

文章列表页 >

Microscopic bubbles segmentation of porcelain relics based on improved UNet ++

The digital protection of cultural heritage | 更新时间：2025-02-08

- Microscopic bubbles segmentation of porcelain relics based on improved UNet ++
- Journal of Northwest University (Natural Science Edition) Vol. 55, Issue 1, Pages: 129-138(2025)
- 作者机构：
  
  1.西北大学　文化遗产数字化国家地方联合工程研究中心，陕西　西安　 710127
  2.西北大学　可视化技术研究所，陕西　西安　 710127
- 作者简介：
- 基金信息：
- DOI：10.16152/j.cnki.xdxbzr.2025-01-011
  CLC： TP391.41
- Published：25 February 2025，
  
  Received：20 April 2024，
- 稿件说明：
移动端阅览
LIU YANGYANG, GENG GUOHUA, LIU XINDA, et al. Microscopic bubbles segmentation of porcelain relics based on improved UNet ++. [J]. Journal of northwest university (natural science edition), 2025, 55(1): 129-138.
DOI：

LIU YANGYANG, GENG GUOHUA, LIU XINDA, et al. Microscopic bubbles segmentation of porcelain relics based on improved UNet ++. [J]. Journal of northwest university (natural science edition), 2025, 55(1): 129-138. DOI： 10.16152/j.cnki.xdxbzr.2025-01-011.

摘要

对瓷器文物显微气泡的分割，可以更加清晰地观察瓷器表面微观气泡的形态、数量以及分布规律，进而辅助文物专家进行瓷器碎片分类和文物鉴定等工作。但瓷器显微图像中气泡复杂多变，大小及分布不均匀，现有图像分割方法难以适应瓷器显微气泡特征。因此，该文提出一种基于卷积激活单元的网络AGUNet ++，该网络重新设计密集跳跃连接，节点间采用Z字形连接方式，充分提取图像语义特征，防止信息丢失；同时，在卷积单元的密集跳跃连接处，结合注意力门控模块Attention Gate提出卷积激活单元CAU，增强与瓷器文物显微气泡分割任务相关的气泡区域学习，抑制不相关的区域；在训练过程中对每一层子网络的输出采用深度监督和交叉熵损失，有效增强瓷器文物显微气泡特征提取能力，细化分割结果。该方法在SD-saliency-900以及PRMI数据集上的实验结果表明，与经典图像分割网络相比，AGUNet ++在MIoU、Precision、Recall和F1分数中均有一定的提升，表现出更好的分割效果。

Abstract

The segmentation of microscopic bubbles of porcelain relics can provide a clearer observation of the morphology

quantity

and distribution of micro bubbles on the surface of porcelain

which is of great significance in assisting relic experts in classifying porcelain cultural relic fragments and identifying porcelain cultural relics. However

the bubbles in porcelain microscopic images are complex and varied

with uneven size and distribution. Existing image segmentation methods are difficult to adapt to the characteristics of porcelain microscopic bubbles. Therefore

a network named AGUNet ++ based on convolution attention unit is proposed. This network utilizes a zigzag connection approach between nodes to fully extract image semantic features and prevent information loss. Meanwhile

a convolution attention unit is introduced by combining the dense skip connection of the convolution unit with the attention gate. The CAU enhances the learning of bubble regions relevant to the task of microscopic bubble segmentation in porcelain artifacts while suppressing irrelevant regions. Deep supervision and cross entropy loss are applied to the output of each sub network layer during the training process

which effectively enhance the ability to extract microscopic bubble features in porcelain artifacts and refine the segmentation results. The experimental results of this method on the SD-saliency-900 and PRMI demonstrate that AGUNet ++ exhibits certain improvements in MIoU

Precision

Recall

and F1_score

showing better segmentation performance compared to classical image segmentation networks.

关键词

瓷器文物显微图像显微图像分割UNet ++注意力门

Keywords

porcelain relics micro imagemicroimage segmentationU-Net++attention gate

references

耿国华, 冯龙, 李康, 等. 秦陵文物数字化及虚拟复原研究综述[J]. 西北大学学报(自然科学版), 2021, 51(5): 710-721.

GENG G H, FENG L, LI K, et al. A literature review on the digitization and virtual restoration of cultural relics in the Mausoleum of Emperor Qinshihuang[J]. Journal of Northwest University (Natural Science Edition), 2021, 51(5): 710-721.

李春龙, 周明全, 成欣, 等. 轴对称破碎文物的虚拟复原方法[J]. 计算机辅助设计与图形学学报, 2006, 18(5): 620-624.

LI C L, ZHOU M Q, GENG X, et al. Virtual restoration of axisymmetric relic fragments[J]. Journal of Computer-Aided Design and Computer Graphics, 2006, 18(5): 620-624.

王飘, 耿国华, 张雨禾. 基于表面纹理特征定义的碎片拼接方法[J]. 激光与光电子学进展, 2018, 55(8): 81012.

WANG P, GENG G H, ZHANG Y H. Fragment splicing method based on surface texture characteristic[J]. Laser & Optoelectronics Progress, 2018, 55(8): 081012.

张雨禾, 耿国华, 魏潇然, 等. 基于形状骨架图匹配的文物碎片自动重组方法[J]. 自动化学报, 2017, 43(4): 622-633.

ZHANG Y H, GENG G H, WEI X R, et al. Reassembly of fractured fragments based on skeleton graphs matching[J]. Journal of Automation, 2017, 43(4): 622-633.

LI R X, GENG G H, WANG X Z, et al. LBCapsNet: A lightweight balanced capsule framework for image classification of porcelain fragments[J]. Heritage Science, 2024, 12(1): 1-14.

律海明. 浅析古陶瓷的几种鉴定方法[J]. 文物鉴定与鉴赏, 2014(4): 90-94.

LYU H M. A brief analysis of several identification methods for ancient ceramics[J]. Identification and Appreciation to Cultural Relics, 2014(4): 90-94.

汤辉. 标准化技术在古陶瓷眼学鉴定中的应用[J]. 景德镇陶瓷, 2020(5): 8-11.

TANG H. The application of standardization techniques in visual identification of ancient porcelain[J]. Jingdezhen Ceramics, 2020(5): 8-11.

金信苗. 微观痕迹在古陶瓷鉴定中的有效性探索[J]. 科技风, 2022(32): 145-147.

JIN X M. Exploration of the effectiveness of microscopic traces in the authentication of ancient porcelain[J]. Technology Wind, 2022(32): 145-147.

王克刚. 基于数字图像特征的古瓷片分类研究[D]. 西安: 西北大学, 2009.

鱼跃华. 破损文物碎片的深度学习分类方法研究[D]. 西安: 西北大学, 2022.

陆正杰, 李纯辉, 耿国华, 等. 基于多特征描述子自适应权重的文物碎片分类[J]. 激光与光电子学进展, 2020, 57(4): 321-329.

LU Z J, LI C H, GENG G H, et al. Classification of cultural fragments based on adaptive weights of multi-feature descriptions[J]. Laser & Optoelectronics Progress, 2020, 57(4): 321-329.

耿国华, 薛米妍, 周蓬勃, 等. 基于对比学习与多尺度结合的陶瓷显微图像分类方法[J]. 西北大学学报(自然科学版), 2021, 51(5): 734-741.

GENG G H, XUE M Y, ZHOU P B, et al. Ceramic microscopic image classification based on the combination of contrastive learning and multi-scale methods[J]. Journal of Northwest University (Natural Science Edition), 2021, 51(5): 734-741.

刘景怡. 基于显微特征的古代瓷器碎片分类方法的研究与实现[D]. 西安: 西北大学, 2021.

张佳宏. 论古瓷器的气泡[J]. 收藏界, 2012(12): 118-119.

ZHANG J H. On the bubbles of ancient porcelain[J]. Collection World, 2012(12): 118-119.

李庆武, 王珺, 盛惠兴, 等. 基于小波包分析的陶瓷显微图像处理[C]//第十二届全国信号处理学术年会论文集. 苏州，中国: 中国电子学会信号处理分会, 2005: 321-324.

朱顺龙. 古陶瓷显微科技气泡测定研究初探：以越窑青瓷研究为例[J]. 中国文物科学研究, 2008(1): 38-41.

ZHU S L. Preliminary exploration of microscopic bubble measurement in ancient ceramics: A case study of Yue kiln celadon porcelain[J]. China Cultural Heritage Scientific Research, 2008(1): 38-41.

刘国高. 基于快速曲波变换的陶瓷显微图像处理[J]. 中国陶瓷工业, 2008, 15(2): 17-21.

LIU G G. Ceramic microscopic image procession based on fast curvelet transform[J]. China Ceramic Industry, 2008, 15(2): 17-21.

LONG J, SHELHAMER E, DARREL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4): 640-651.

RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich, Germany: Springer International Publishing, 2015:234-241.

ZHOU Z W, SIDDIQUEE M M R, TAJBAKHSH N, et al. UNet ++: A nested U-Net architecture for medical image segmentation[J]. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support, 2018, 11045: 3-11.

SU L Z, XIE Q Y, ZHAO F J, et al. Change detection for multispectral images using modified semantic segmentation network[J]. Journal of Applied Remote Sensing, 2022, 16(1): 014518.

ARDIYANTO I. Edge devices-oriented surface defect segmentation by ghostNet Fusion block and global auxiliary layer[J]. Journal of Real-Time Image Processing, 2024, 21(1): 13.

LIU X D, WANG L L, HAN X G. Transformer with peak suppression and knowledge guidance for fine-grained image recognition[J]. Neurocomputing, 2022, 492: 137-149.

WANG X L, GIRSHICK R, GUPTA A, et al. Non-local neural networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake, USA: IEEE, 2018: 7794-7803.

CHEN L C, YANG Y, WANG J, et al. Attention to scale: Scale-aware semantic image segmentation[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE, 2016: 3640-3649.

LUONG M T, PHAM H, MANNING C D. Effective approaches to attention-based neural machine translation[EB/OL](2015-08-17) [2024-02-14]. https://arxiv.org/abs/1508.04025https://arxiv.org/abs/1508.04025.

BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[C]//3rd International Conference on Learning Representations. San Diego, USA: ICLR, 2015: 1-15.

BRITZ D, GOLDIE A, LUONG M T, et al. Massive exploration of neural machine translation architectures[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Copenhagen, Denmark: USAACL, 2017: 1442.

MINAEE S, BOYKOV Y, PORIKLI F, et al. Image segmentation using deep learning: A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(7): 3523-3542.

苏虎, 张家斌, 张博豪, 等. 基于视觉感知的表面缺陷检测综述[J]. 计算机集成制造系统, 2023, 29(1): 169-191.

SU H, ZHANG J B, ZHANG B H, et al. A review of research on the inspection of surface defects based on visual perception[J]. Computer Integrated Manufacturing Systems, 2023, 29(1): 169-191.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰