用深度学习自动分割古迹马赛克碎片，提升文物数字化精度。
Automated Mosaic Tesserae Segmentation via Deep Learning Techniques
- 基于SAM 2模型微调，实现马赛克碎片精准分割
- 分割准确率提升至91.02%（IoU），召回率达95.89%
- 新构建数据集支持后续研究，适合文化遗产保护者
艺术是文明的体现，马赛克作为文化遗产的重要组成部分，由小块称为 tesserae 的碎片粘贴而成。由于年代久远且脆弱，易受损，亟需数字保存。本文针对马赛克图像的数字化问题，提出一种基于 Meta AI 的 Segment Anything Model 2（SAM 2）的自动分割方法。由于该领域公开数据集稀缺，我们构建了一个标注的马赛克图像数据集用于模型微调与评估。在测试集上，相比原始 SAM 2 模型，本方法的交并比（IoU）从 89.00% 提升至 91.02%，召回率从 92.12% 提升至 95.89%。此外，在先前方法提出的基准上，本模型的 F-measure 高出 3%，预测与实际碎片数的绝对误差由 0.20 降至 0.02。微调后的 SAM 2 模型与新数据集为马赛克图像的实时分割提供了可能。
原文摘要 · Abstract (English)
Art is widely recognized as a reflection of civilization and mosaics represent an important part of cultural heritage. Mosaics are an ancient art form created by arranging small pieces, called tesserae, on a surface using adhesive. Due to their age and fragility, they are prone to damage, highlighting the need for digital preservation. This paper addresses the problem of digitizing mosaics by segmenting the tesserae to separate them from the background within the broader field of Image Segmentation in Computer Vision. We propose a method leveraging Segment Anything Model 2 (SAM 2) by Meta AI, a foundation model that outperforms most conventional segmentation models, to automatically segment mosaics. Due to the limited open datasets in the field, we also create an annotated dataset of mosaic images to fine-tune and evaluate the model. Quantitative evaluation on our testing dataset shows notable improvements compared to the baseline SAM 2 model, with Intersection over Union increasing from 89.00% to 91.02% and Recall from 92.12% to 95.89%. Additionally, on a benchmark proposed by a prior approach, our model achieves an F-measure 3% higher than previous methods and reduces the error in the absolute difference between predicted and actual tesserae from 0.20 to just 0.02. The notable performance of the fine-tuned SAM 2 model together with the newly annotated dataset can pave the way for real-time segmentation of mosaic images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。