I think that FineReader is the best one available for now - but of course it's only my personal opinion. I've worked with FineReader a lot, once upon a time,
when we were doing educational project - we had to scan a lot of books (it was some years ago, at school) - and the results were great. The biggest problem was that all the books were written in Polish - we've tested some different OCRs and FineReader ate them all. Now, anytime I've to do something with the OCR I always look for the opportunity to use FineReader. I think it will be good also for German - although, the Polish and German are totally different (so much different, that in Polish language a German guy is called "Niemiec", which means exactly a person, which is unable to speak in any language - you can translate it to "speechless" or "silent" - but Polish word is not negative, it's neutral!
, in both written languages there are some special characters. In Polish we have those tails in "a", "e" and additional lines in "l" or a mark at the top of "o" - and so on..
, Germans have their "o" and "e" with double marks at the top or this superb "S" (long "S" - like in "fleissig" or "fleiBig"
, which looks like B for me and sometimes is written as double "s". Please excuse me, I like languages
Additionally, as far as I remember FineReader not only recognizes the symbol patterns, but also performs some additional lexical and syntax analyses if he is unable to recognize a letter (or a whole word in such case). Moreover, in my case it is tested tool
So, I'm using FineReader on any occasion, but probably everyone has his own choice (what about Recognita? It was quite nice with the English texts, as far as I know German is a language which belongs to the same group like English, so... maybe it will also be good with German - OCR is just a part of the work, after that, a good OCR should make some additional grammar analyses to generate more correct results of recognition). Anyway, do you know, that most of us are using languages (as their native languages) which belongs to the same Indo-European family? Isn't it a nice thing
Ok... Any German guy who can recommend a good OCR for German language?
Off-topic story - I just have to tell that one. As I said, in Polish, we are using a word "Niemiec" to describe a German guy. "Niemy" in Polish language means "speechless" or "silent", so "Niemiec" is a guy who is not able to speak ("Niemy" = is almost like = "Niemiec" in ancient Polish and both words are neutral)... So, "Niemiec" is a silent man, not even giving any voice - just looking at you. Why? Hmm... Thousands years ago, probably before the Poland have been stated as an European country in 966 AD (in this year we take the Christianity form Czechs, just to avoid possible, further German political influence, although we get the first King crowned thanks to Germans, it was between 1000 - 1025 AD, as Boleslaw Chrobry=>Boleslaw the Brave was the close ally of Otton III (the Third), some sources are even describing this realtion as real friendship, not only political alliance), there were mainly forests on the Polish-German border. Probably, from time to time, the guys have been meeting themselves during hunting or during harvesting the forest goods and... because Polish guys have been unable to communicate with the Germans (ok - pre-Germans and pre-Polish guys
they called "these other strange people from the forest, who are unable to speak anything in the <<one and only possible language>>" that way... I mean "Niemcy" - people who are not talking, silent ones. To be clear, it means only that these people are unable to speak, they are silent, it is not in the negative meaning, it is neutral. So, now you can imagine, we are using the word "niemiecki" in Polish (Germans = "Niemcy", German language = "niemiecki") to describe the German language - it exactly means "the language used by people who are not communicating with others using spoken language, as they are the silent ones". So... how should look such a language - it should be silence if I'm thinking correctly or maybe it should exist in written form only? But, everything I can say about my native, Polish language - it's so hard to learn, as it could seem to be illogical in many grammar things... and it's a funny language in some meanings (like with "Niemiec" word).
I hope you have fun reading this story. I just can't stop myslef as I love languages - not only programming languages but also natural ones
. You know - show me your language and I'll tell you what is your way of thinking (sloving problems).
It's good we all can use English at least to some level of communication, but... we have to remember that we all think in our own languages first. These things are called cultural differences - another example - double negation is not a mistake in Polish and all the words can be used in any order, so:
"Najlepsze pozdrowienia ze slonecznej Warszawy" - is the most common syntax and is correct, but...
... "Ze slonecznej Warszawy najlepsze pozdrowienia" - is less common but also correct, and...
..."Ze slonecznej najlepsze pozdrowienia Warszawy" - is also good, but sounds poetic and could occur in a poem
I'll not translate last 3 sentences as these are greetings - do it yourself if you want to have some fun.
LANGUAGES = FUN!
Greetings, my friends.