Blog
Research &
Notes
Why reversing binarization changes everything
Conventional OCR treats background as noise to be eliminated. We treat it as signal. Here's the mathematics behind the approach and why it produces 4× speedups on dense ideographic scripts.
Read more →
Building GNN glyph graphs from skeletal representations
After skeleton extraction, each glyph becomes a node in a graph neural network. With 17,831 edges across 1,675 objects, the structure encodes not just characters but their relational geometry.
Read more →
Cellular automata entropy and steganographic metadata
An entropy score of 0.618 — the golden ratio — emerges consistently from well-formed glyph fields. This paper explains why and how it serves as a steganographic fingerprint.
Read more →
Presenting at IPAI Toulouse — June 2026
A preview of our presentation at the International Patent & AI conference in Toulouse on 10 June 2026. Topics: live demo, roadmap, and applications in bioimaging and ancient scripts.
Read more →