ProZ.com global directory of translation services
 The translation workplace
Ideas

 
User
Thread poster: keshab
how I convert .gif image into text

keshab  Identity Verified
Local time: 03:07
Member (2006)
English to Hindi
+ ...
Oct 23, 2005

Hello everybody!
perhaps this type of problem discussed earlier.But at this moment I need your help.I know that OCR software can convert image into text.But when I am going to translate a comics,a peculiar situation arises.the OCR software( I'm using 'Simple OCR')converts everything into text i.e. alongwith text,picture also converts into characters. How can I translate the text of the comics which is originally in English and have to translate into Indic language?


Direct link Reply with quote
 

Juan Perello  Identity Verified
Local time: 17:37
Member (2005)
Japanese to Spanish
+ ...
highlighting only the text portion of the image Oct 23, 2005

Hi Keshab,

Your OCR program should allow you to highlight only some portions of the image. So, instead of applying the OCR to the whole image, you'd have to select only the text you need and leave out the images. Unfortunately, this can be a very time-consuming task.

I Hope it helps.

Juan Luis


Direct link Reply with quote
 

Samuel Murray  Identity Verified
Netherlands
Local time: 23:37
Member (2006)
English to Afrikaans
+ ...
Upgrade to GOCR, and blank out the images Oct 24, 2005


keshab wrote:
But when I am going to translate a comics,a peculiar situation arises, the OCR software (I'm using 'Simple OCR') converts everything into text ie alongwith text, picture also converts into characters.


Which version of SimpleORC are you using? AFAIK, SimpleOCR is built on the GOCR engine, and GOCR is free (open source). In fact, AFAIK GOCR's newest engine isn't even used in SimpleOCR (correct me if I'm wrong). So why not download GOCR and give it a go?

To use GOCR, you'll need to have your image in PNM format, but that can be done using DJPEG, using the command:
djpeg -gray -pnm foo.jpg > foo.pnm
The command for GOCR is:
gocr -i foo.pnm -o foo.txt

But first, open the image in a program that can edit the image (if you're using Windows, you can convert the image to BMP and then edit with MS Paint). Turn the images into white blocks so that only the text is visible. Then do the OCR on it.

http://jocr.sourceforge.net/ (latest version)
http://www.seeingwithsound.com/ocr/djpeg.exe (could be an old version, I couldn't find the home page now)


Direct link Reply with quote
 


To report site rules violations or get help, contact a site moderator:

Moderator(s) of this forum
Natalie[Call to this topic]
Prachya Mruetusatorn[Call to this topic]

You can also contact site staff by submitting a support request »

how I convert .gif image into text






Fluency Translation Suite
Come see the Fluency Difference and SAVE

The most affordable and easy to learn translation tool! Start and finish your translations faster than ever with Fluency Translation Suite 2013. TMs, Terminology, and Online Resources are fully integrated and only a click away. Download a free trial today

More info »
SDL Trados Studio 2014
The leading translation software. Save 15% on ProZ.com

SDL Trados Studio provides translators with all the tools they need for translation, terminology management, review, managing projects, machine translation and more, in one simple and easy-to-use environment.

More info »