search

jacklicn / tesseract-ocr

Automatically exported from code.google.com/p/tesseract-ocr
Other
0 stars 0 forks source link

how to imporve correctness of chinese language recogntion? #570

Closed GoogleCodeExporter closed 9 years ago

GoogleCodeExporter commented 9 years ago 
I used tesseract with the cmd:
tesseract myimg myresult -l chi_sim

but I  can't get the right answer.

If I use the image in attaches, I got

rb1.jpg  走过 垌台
rb1.tif  帼 十治

Original issue reported on code.google.com by wangjava...@gmail.com on 3 Nov 2011 at 7:55

Attachments:

GoogleCodeExporter commented 9 years ago 
First of all - get image in reasonable resolution: suggested is 300 DPI
Than try to have some space around text/letters
Than try psm option (see output of 'tesseract' command for explanation).

Original comment by zde...@gmail.com on 25 Feb 2012 at 8:27

GoogleCodeExporter commented 9 years ago 
moved to FAQ
http://code.google.com/p/tesseract-ocr/wiki/FAQ?ts=1331068532&updated=FAQ#Output
_it_without_result_or_wrong

Original comment by zde...@gmail.com on 6 Mar 2012 at 9:20