orionstark
/
tesseract.js
mirror of https://github.com/OrionStark/tesseract.js.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update faq.md

Browse Source
master
Balearica 6 months ago committed by GitHub
parent 71b82e8142
commit bf358a2a52
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 0 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 3
      docs/faq.md

3
docs/faq.md
Unescape View File

@ -16,6 +16,9 @@ Tesseract.js does not support .pdf directly—a separate library must be used to
## What configuration settings should I use? ## What configuration settings should I use?
Default settings should provide optimal results for most users. If you do want to experiment with configuration settings, Tesseract does include many settings to change—the vast majority are documented in the [main Tesseract project](https://github.com/tesseract-ocr/tesseract) and not here. As noted above (“what is the scope of this project”), the core recognition engine is inherited from the main Tesseract project—all of the configuration settings in Tesseract work identically in Tesseract.js. Therefore, for specific questions about configuring recognition settings (e.g. “how can I make noise removal more/less aggressive” or “what settings work best for license plates”) you are more likely to find an answer in the Tesseract documentation/discussion versus only looking in this repo. Default settings should provide optimal results for most users. If you do want to experiment with configuration settings, Tesseract does include many settings to change—the vast majority are documented in the [main Tesseract project](https://github.com/tesseract-ocr/tesseract) and not here. As noted above (“what is the scope of this project”), the core recognition engine is inherited from the main Tesseract project—all of the configuration settings in Tesseract work identically in Tesseract.js. Therefore, for specific questions about configuring recognition settings (e.g. “how can I make noise removal more/less aggressive” or “what settings work best for license plates”) you are more likely to find an answer in the Tesseract documentation/discussion versus only looking in this repo.
## Is handwritten text supported?
No. The Tesseract OCR model is built around assumptions that only hold for printed text. No combination of options will significantly improve performance with handwritten text. Unless your handwriting is so good that it closely resembles printed text, the results will be poor.
# Trained Data # Trained Data
## How does tesseract.js download and keep \*.traineddata? ## How does tesseract.js download and keep \*.traineddata?

Write Preview
Loading…
Cancel
Save