用AI从破损泥板上识别古埃兰楔形文字，准确率超传统方法17个百分点。
Zero-Shot SAM2 Segmentation and Vision Transformer-Based Recognition of Elamite Cuneiform Symbols from Degraded Tablet Images
- 先用零样本分割生成符号掩膜，再用改进的视觉Transformer分类
- 在132类符号上达到86.41%准确率，远超现有模型
- 适合研究古代文字、文化遗产数字化的学者与团队
古楔形文字的自动识别面临复合信号退化问题：泥板三维凸起导致光照不均和阴影，表面侵蚀引入与真实符号重叠的结构噪声，且141类符号存在严重类别不平衡。我们提出EpigraphNet，一种基于分割引导的Transformer流程，在佩尔塞波利斯档案库数据集上评估。从1,239张标注泥板图像中，通过亮度自适应形态学预处理与零样本SAM2-Large分割生成干净二值符号掩膜，再由微调的Vision Transformer (ViT-B/16) 结合逆频率类别加权进行分类。EpigraphNet在132类基准上达到86.41%的top-1准确率，比最强的CNN基线ResNet-101（69.20%）提升17.21个百分点，较四种现代骨干网络（DeiT-B/16、Swin-B、ConvNeXt-B、EfficientNet-B4）提升5.31-12.91%。整个流水线在NVIDIA A100 GPU上每符号耗时约18毫秒。符号频率与分类性能的相关性较低，表明对高频与低频符号的识别更均衡。代码已开源：github.com/r11up/sam-guided-vit
原文摘要 · Abstract (English)
Automated recognition of ancient cuneiform script poses a compound signal-degradation problem: the three-dimensional relief of clay tablets creates spatially varying illumination and cast shadows, surface erosion introduces structured noise that overlaps with genuine sign impressions, and severe class imbalance across 141 sign categories undermines classifier reliability. We introduce EpigraphNet, a segmentation-guided transformer pipeline evaluated on the Persepolis Fortification Archive. From 1,239 annotated tablet images, brightness-adaptive morphological preprocessing and zero-shot SAM2-Large segmentation generate clean binary symbol masks, which a fine-tuned Vision Transformer (ViT-B/16) with inverse-frequency class weighting then classifies. EpigraphNet reaches 86.41% top-1 accuracy on a 132-class benchmark, a 17.21 percentage-point gain over the strongest CNN baseline (ResNet-101, 69.20%) and 5.31-12.91% over four modern backbones (DeiT-B/16, Swin-B, ConvNeXt-B, EfficientNet-B4) under identical conditions. The full pipeline runs at approximately 18 ms per sign on an NVIDIA A100 GPU. A lower Spearman correlation between sign frequency and per-class performance indicates more balanced recognition across frequent and rare classes. Implementation is available at: github.com/r11up/sam-guided-vit
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。