FFXiV Translator add-on (not injecting nor modifying client)

[Varacolaci]

Hello FFXiV Community!
Fist of all, sorry for my bad english (there is my main reason why I want to do this) hope I can be as clear as possible.

I've been playing a while now but just 2days ago I purchased another copy for my nephew which understands very few English so the questing is hard from him somethimes. Even worst I feel he is missing a looot of the beauty of FFXiV by not beeing able to understand the story behind the quests (some of the are meeh but some other are awesome).

So I just decided to start working on a translator ... now I know modifiying or injecting the game client is againt the EULA but I have this idea (made first test today with very prommising results) of translating it using OCR on the fly.

And I would like to know if this is against the EULA or I can try to make it live.
Also some toughts would be welcome.

Since I have this serious forum limitations the full article is http://ffxivadventures.com/tools/translator
Plese go there and ask the questions I can't post here much

Just to pose some questions (just to keep a discussion going):
- Are you taking an entire screenshot and looking for the image patterns you pointed out? (which would include chat being part of the original image)
- What's preventing the software reading of chat log?
- Are you going to be OCR'ing from within your add-on or sending the image off to a service to have it OCR'd?
- Why not change the language setting on your client?" (as someone else asked, is your language not supported?)
- With current OCR technology it's fairly slow in processing (unless you've got decent hardware behind it). How do you plan on making this faster than what's currently out there?

I do never take fullscreen shots ...
First because the ocr would take forever to make it text and because the simpler the image gets to the OCR app the better.

Second, I'm using an OCR from withing the app (using ocrac http://www.gnu.org/software/ocrad/) and sending to a translate API (using BING at the moment).
The app runs locally until it sends the petition to the API of bing. the screenshot are not stored are taken, processed and overwritten.

here I leave an overview image