On knot detection via picture recognition
This work addresses knot recognition for applications in fields like biology or materials science, but it is incremental as it presents an expository strategy and simple baselines rather than a fully implemented system.
The paper tackles the problem of automatically recognizing knots from photos by combining machine learning for image analysis with traditional algorithms for computing quantum invariants, demonstrating that lightweight CNN and transformer architectures can predict crossing numbers from images.
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.