发表机构
University of Georgia; University of Pennsylvania（佐治亚大学; 宾夕法尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出LinePilot Digitizer，结合三种校准模式与DigitizerBench基准，通过FPC-NRMSE评估，实现线图数据的高效准确恢复。
AI 中文摘要
从线图中恢复数值序列需要精确的轴校准和可靠的曲线提取。我们提出了LinePilot Digitizer（LinePilot），它将基于连续颜色的曲线恢复与三种校准模式相结合：LinePilot（标准）、LinePilot（增强）和LinePilot（OCR）。我们还引入了DigitizerBench，这是第一个专门用于系统评估数字化器性能的基准，采用正交设计，涵盖信号、渲染和图结构因素，并辅以自动和人工引导的评估。我们使用失败惩罚上限归一化均方根误差（FPC-NRMSE）来评估性能，该指标对缺失、不可用或灾难性不准确的输出分配单位损失。在DigitizerBench-Full上，LinePilot（OCR）在测试的自动流程中实现了最低的平均FPC-NRMSE（0.672）和最高的可信可用性（38.2%）。在DigitizerBench-Lite上，LinePilot（增强）实现了最低的平均FPC-NRMSE（0.081）、100%的输出成功率和最高的可信可用性（93.3%）。正交基准设计还支持因子分析，以识别对数字化器性能影响最显著的因素。总之，三种校准模式在共享的曲线恢复工作流程中提供了自动化、用户控制和准确性之间的实用权衡。
英文摘要
Recovering numerical series from line plots requires accurate axis calibration and reliable curve extraction. We present LinePilot Digitizer (LinePilot), which combines continuous color-based curve recovery with three calibration modes: LinePilot (standard), LinePilot (enhanced), and LinePilot (OCR). We also introduce DigitizerBench, the first dedicated benchmark for systematically evaluating digitizer performance, using an orthogonal design spanning signal, rendering, and plot-structure factors with complementary automatic and human-guided evaluations. We evaluate performance using failure-penalized capped normalized root-mean-square error (FPC-NRMSE), which assigns unit loss to missing, unusable, or catastrophically inaccurate outputs. On DigitizerBench-Full, LinePilot (OCR) achieves the lowest mean FPC-NRMSE (0.672) and highest trusted usability (38.2%) among the tested automatic pipelines. On DigitizerBench-Lite, LinePilot (enhanced) achieves the lowest mean FPC-NRMSE (0.081), 100% output success, and highest trusted usability (93.3%). The orthogonal benchmark design further enables factor analysis to identify the factors that most significantly affect digitizer performance. Together, the three calibration modes provide a practical trade-off between automation, user control, and accuracy within a shared curve-recovery workflow.
