#homography — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #homography, aggregated by home.social.
-
Except for naming the shapes I figure something like following might work?
- Render each Unicode script in several fonts.
- Training per-script classifiers (OCRs) on those.
- Run the per-script classifiers on each others training data to identify homographs.
There's a tricky bits, like creating non-confusable out-of-script scribbles to include in training data, etc.
Still... this doesn't seem like all that impossible?
What am I missing?
-
Except for naming the shapes I figure something like following might work?
- Render each Unicode script in several fonts.
- Training per-script classifiers (OCRs) on those.
- Run the per-script classifiers on each others training data to identify homographs.
There's a tricky bits, like creating non-confusable out-of-script scribbles to include in training data, etc.
Still... this doesn't seem like all that impossible?
What am I missing?
-
Except for naming the shapes I figure something like following might work?
- Render each Unicode script in several fonts.
- Training per-script classifiers (OCRs) on those.
- Run the per-script classifiers on each others training data to identify homographs.
There's a tricky bits, like creating non-confusable out-of-script scribbles to include in training data, etc.
Still... this doesn't seem like all that impossible?
What am I missing?
-
Except for naming the shapes I figure something like following might work?
- Render each Unicode script in several fonts.
- Training per-script classifiers (OCRs) on those.
- Run the per-script classifiers on each others training data to identify homographs.
There's a tricky bits, like creating non-confusable out-of-script scribbles to include in training data, etc.
Still... this doesn't seem like all that impossible?
What am I missing?
-
Except for naming the shapes I figure something like following might work?
- Render each Unicode script in several fonts.
- Training per-script classifiers (OCRs) on those.
- Run the per-script classifiers on each others training data to identify homographs.
There's a tricky bits, like creating non-confusable out-of-script scribbles to include in training data, etc.
Still... this doesn't seem like all that impossible?
What am I missing?
-
You know what should exist?
A Unicode Codepoint => basic shape map.
Ie. something that would tell you that Greek Ο, Latin O, and Cyrillic О all have the same basic shape - and ideally give it a name, like FULL_UPRIGHT_OVAL.
EDIT: I completely ignored massive glyph variation. Please read "shape" as "category of things that sometimes render similarly". So "a" would map to a category that includes things similar to both single- and double-story a.
-
You know what should exist?
A Unicode Codepoint => basic shape map.
Ie. something that would tell you that Greek Ο, Latin O, and Cyrillic О all have the same basic shape - and ideally give it a name, like FULL_UPRIGHT_OVAL.
EDIT: I completely ignored massive glyph variation. Please read "shape" as "category of things that sometimes render similarly". So "a" would map to a category that includes things similar to both single- and double-story a.
-
You know what should exist?
A Unicode Codepoint => basic shape map.
Ie. something that would tell you that Greek Ο, Latin O, and Cyrillic О all have the same basic shape - and ideally give it a name, like FULL_UPRIGHT_OVAL.
EDIT: I completely ignored massive glyph variation. Please read "shape" as "category of things that sometimes render similarly". So "a" would map to a category that includes things similar to both single- and double-story a.
-
You know what should exist?
A Unicode Codepoint => basic shape map.
Ie. something that would tell you that Greek Ο, Latin O, and Cyrillic О all have the same basic shape - and ideally give it a name, like FULL_UPRIGHT_OVAL.
EDIT: I completely ignored massive glyph variation. Please read "shape" as "category of things that sometimes render similarly". So "a" would map to a category that includes things similar to both single- and double-story a.
-
You know what should exist?
A Unicode Codepoint => basic shape map.
Ie. something that would tell you that Greek Ο, Latin O, and Cyrillic О all have the same basic shape - and ideally give it a name, like FULL_UPRIGHT_OVAL.
EDIT: I completely ignored massive glyph variation. Please read "shape" as "category of things that sometimes render similarly". So "a" would map to a category that includes things similar to both single- and double-story a.
-
CNC Toolpath Visualisation With OpenCV - [Tony Liechty] has been having a few issues getting into CNC machining — starting ... - https://hackaday.com/2022/03/31/cnc-toolpath-visualisation-with-opencv/ #homography #cncrouter #cnchacks #charuco #opencv #image
