I believe this file needs to be supplied before the final combined trained
data is compiled, therefore perhaps you should look for if jTessBoxEditor
supports its creation.
https://tesseract-ocr.googlecode.com/svn/trunk/doc/unicharambigs.5.html
On 7 January 2015 at 22:17, newbie wrote:
> Thanks
Thanks Allistair for your response. I have the final crunched eng/
trained_data, not sure if that has merged in unicharambigs. How would i
know ?
On Wednesday, January 7, 2015 4:47:10 PM UTC-5, Allistair C wrote:
>
> You've tried unicharambigs right (bottom of this page
> https://code.google.co
You've tried unicharambigs right (bottom of this page
https://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3)
On Thursday, 20 November 2014 12:53:43 UTC, Mark Beylis wrote:
>
> Hello
>
> I am making use of Tesseract OCR to perform number plate recognition on
> vehicles
>
> I am making u
Mark,
Did you find a solution to line below(extracted from your original
msg) ? If so , please let me know. Thanks
*What I have picked up is that the OCR struggles with certain problem
characters : O vs 0, 5 vs S, 2 vs Z, B vs 8*
On Thursday, November 20, 2014 7:53:43 AM UTC-5, Mark Bey
4 matches
Mail list logo
