OCR Fonts

RecQuery · 06-12-2011, 08:58 AM

I'm setting up my OCR program, the tests are good but I'm just wondering if there's anything I can do to make them better, specifically I'm wondering what the most common fonts used in books are? or what other additional fonts to the default list have yielded good results?

KevinH · 06-12-2011, 10:59 PM

Hi,

If you read history books or travel books, you may want to add characters that represent other languages that can often be found mixed in English (assuming that is your language of choice). These can be found in Spanish, French, German, etc in the form of accented or umlauted characters.

I like WW2 history books on tanks and tried to OCR one and all of the French and German place names and terms really wrecked havoc with my OCR and I had to give that up since I did not (at that time) know how to add my own chars for training the OCR engine.

My 2 cents,

KevinH

06-12-2011, 08:58 AM	#1
RecQuery Junior Member Posts: 9 Karma: 10 Join Date: May 2011 Location: Scotland, UK Device: Kindle 3	OCR Fonts I'm setting up my OCR program, the tests are good but I'm just wondering if there's anything I can do to make them better, specifically I'm wondering what the most common fonts used in books are? or what other additional fonts to the default list have yielded good results?

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
Do I have to OCR?	Ceryta	Workshop	7	05-07-2011 12:03 PM
Embedded fonts, Calibre, and choice of fonts	AlexBell	ePub	8	05-30-2010 07:00 AM
Large fonts / bold fonts for Kindle DX International	tandyjames	Amazon Kindle	5	03-23-2010 07:53 AM
OCR to use	pepak	Workshop	17	05-26-2008 06:30 PM
What is an OCR Cradle?	JackieFrost	Which one should I buy?	4	05-21-2008 09:10 PM

06-12-2011, 10:59 PM	#2
KevinH Sigil Developer Posts: 9,093 Karma: 6404930 Join Date: Nov 2009 Device: many	Hi, If you read history books or travel books, you may want to add characters that represent other languages that can often be found mixed in English (assuming that is your language of choice). These can be found in Spanish, French, German, etc in the form of accented or umlauted characters. I like WW2 history books on tanks and tried to OCR one and all of the French and German place names and terms really wrecked havoc with my OCR and I had to give that up since I did not (at that time) know how to add my own chars for training the OCR engine. My 2 cents, KevinH

Advert