Abstract
We propose an algorithm that renders a desired input string in an author’s handwriting. An annotated sample of the author’s handwriting is required; the system is flexible enough that historical documents can usually be used with only a little extra effort. Experiments show that our glyph-centric approach, with learned parameters for spacing, line thickness, and pressure, produces novel images of handwriting that look hand-made to casual observers, even when printed on paper.
| Original language | English |
|---|---|
| Article number | 26 |
| Pages (from-to) | 1-19 |
| Number of pages | 19 |
| Journal | ACM Transactions on Graphics |
| Volume | 35 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 30 Jun 2016 |
Fingerprint
Cite this
My Text in Your Handwriting. / Haines, Tom S.F.; Mac Aodha, Oisin; Brostow, Gabriel J.
In: ACM Transactions on Graphics, Vol. 35, No. 3, 26, 30.06.2016, p. 1-19.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - My Text in Your Handwriting
AU - Haines, Tom S.F.
AU - Mac Aodha, Oisin
AU - Brostow, Gabriel J.
PY - 2016/6/30
Y1 - 2016/6/30
N2 - There are many scenarios where we wish to imitate a specific author’s pen-on-paper handwriting style. Rendering new text in someone’s handwriting is difficult because natural handwriting is highly variable, yet follows both intentional and involuntary structure that makes a person’s style self-consistent. The variability means that naive example-based texture synthesis can be conspicuously repetitive.We propose an algorithm that renders a desired input string in an author’s handwriting. An annotated sample of the author’s handwriting is required; the system is flexible enough that historical documents can usually be used with only a little extra effort. Experiments show that our glyph-centric approach, with learned parameters for spacing, line thickness, and pressure, produces novel images of handwriting that look hand-made to casual observers, even when printed on paper.
AB - There are many scenarios where we wish to imitate a specific author’s pen-on-paper handwriting style. Rendering new text in someone’s handwriting is difficult because natural handwriting is highly variable, yet follows both intentional and involuntary structure that makes a person’s style self-consistent. The variability means that naive example-based texture synthesis can be conspicuously repetitive.We propose an algorithm that renders a desired input string in an author’s handwriting. An annotated sample of the author’s handwriting is required; the system is flexible enough that historical documents can usually be used with only a little extra effort. Experiments show that our glyph-centric approach, with learned parameters for spacing, line thickness, and pressure, produces novel images of handwriting that look hand-made to casual observers, even when printed on paper.
UR - https://doi.org/10.1145/2886099
U2 - 10.1145/2886099
DO - 10.1145/2886099
M3 - Article
VL - 35
SP - 1
EP - 19
JO - ACM Transactions on Graphics
JF - ACM Transactions on Graphics
SN - 0730-0301
IS - 3
M1 - 26
ER -