arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.06284cs.LGcs.CVmath.GT
收藏

基于图像识别的绳结检测

On knot detection via picture recognition

The University of Sydney, School of Mathematics(悉尼大学数学系)

Anne Dranowski, Yura Kabkov, Daniel Tubbenhauer

AI总结:

本文提出结合CNN/Transformer与量子不变量计算的两阶段方法,实现从绳结图像直接预测交叉数并生成PD码,以支持自动识别与稳健分类。

摘要:

我们的目标是有朝一日能够拍摄一张绳结的照片,并让手机自动识别它。在这篇说明性工作中,我们阐述了一种逼近这一目标的策略,该策略结合了现代机器学习方法(特别是用于图像识别的卷积神经网络和变换器)与传统算法(用于计算量子不变量,如琼斯多项式)。我们提出了直接从图像预测交叉数的简单基线模型,表明即使是轻量级的CNN和变换器架构也能恢复有意义的结构信息。长期目标是将这些感知模块与符号重建相结合,生成平面图(PD)代码,从而支持下游的不变量计算,以实现稳健的绳结分类。这种两阶段方法凸显了机器学习(处理噪声视觉数据)与不变量(强制执行严格的拓扑区分)之间的互补性。

英文摘要:

Our goal is to one day take a photo of a knot and have a phone automatically recognize it. In this expository work, we explain a strategy to approximate this goal, using a mixture of modern machine learning methods (in particular convolutional neural networks and transformers for image recognition) and traditional algorithms (to compute quantum invariants like the Jones polynomial). We present simple baselines that predict crossing number directly from images, showing that even lightweight CNN and transformer architectures can recover meaningful structural information. The longer-term aim is to combine these perception modules with symbolic reconstruction into planar diagram (PD) codes, enabling downstream invariant computation for robust knot classification. This two-stage approach highlights the complementarity between machine learning, which handles noisy visual data, and invariants, which enforce rigorous topological distinctions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑