I have been using Pytesseract to extract text from image. I am currently in a restoration task of an image document. Aside from extracting text from an image, I also wanted to identify each words font, font size, whether the character is capital or not, italicized or not, bold or not and so and so forth. Is this currently possible with Tesseract? I have read the documentation of Pytesseract, but found none about it. If this is not possible, how can I make it happen? Is there any open source font recognition API's? Thanks.
Asked
Active
Viewed 599 times
3
alyssaeliyah
- 2,214
- 6
- 33
- 80
-
1did you find any solution for font size, yet? – Marzi Heidari Oct 20 '20 at 09:00
-
see the anwser here https://stackoverflow.com/questions/15679017/get-font-of-recognized-character-with-tesseract-ocr – Reed Jones Sep 06 '22 at 15:58