Learning by example for parametric font design

Abstract

We describe a novel learning-based font model for knowledge representation and parametric font design. A working font design system has been built which can capture the graphical constraints and design knowledge from limited glyph samples. The system can then generate variations of glyph with the knowledge and inferred constraints. It facilitates the re-use of glyph primitives in an object-oriented fashion, thus allowing collaboration in font design work. The proposed model can represent and process visual knowledge of font design, and is a new tool and representation method for font design, storage and creation.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 8 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.