search

JohnWang0512 / tesseract-ocr

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

jpn.traindeddata does not include circled number characters #1023

Open GoogleCodeExporter opened 9 years ago

GoogleCodeExporter commented 9 years ago 
What steps will reproduce the problem?

run tesseract with -l jpn

What is the expected output? What do you see instead?

jpn.traineddata does not include the circled number characters like ①②③...
These characters are commonly used in Japanese document.
(please try Google Search by "①")
Please include these characters in jpn.traindeddata.

What version of the product are you using? On what operating system?

v3.02, r903

Please provide any additional information below.

Original issue reported on code.google.com by sdkn...@yahoo.co.jp on 23 Nov 2013 at 1:15

GoogleCodeExporter commented 9 years ago 
[note]

Japanese Wikipedia article on circled numbers:
http://ja.wikipedia.org/wiki/%E4%B8%B8%E6%95%B0%E5%AD%97

Might be useful as a reference for the different kinds of circled numbers.

Original comment by clements...@gmail.com on 9 Dec 2013 at 11:09