Does OCR read kyrillic and greek alphabet?

Hi,
does aspose OCR recognize kyrillic and greek letters? Also other special characters for european languages, like è, à and all eastern and north european chars?

Which code pages are supported?

Herbert

@herbert.angermann

Can you please share a sample image with us that contains all of these language characters? We will surely test the case at our end and share our feedback with you.

bulgarian: bulgarian example.pdf (96.7 KB)
Greek: Greek Image.gif (12.9 KB)
French: modele-de-facture.jpg (48.3 KB)

But this actually means, that you don’t really support it yet. Otherwise you would know, I guess.

@herbert.angermann

We have been adding support for different languages in the API. Support for German Amulets has also been added recently. You can check all supported languages in the Language Enumeration offered by the API and it can be used like below:

Aspose.OCR.AsposeOcr api = new OCR.AsposeOcr();
var result = api.RecognizeImage(dataDir + "modele-de-facture.jpg", new Aspose.OCR.RecognitionSettings { Language = Aspose.OCR.Language.Fra });
result.Save(dataDir + "recResults.txt", Aspose.OCR.SaveFormat.Text);

We are further gathering details about other languages you have inquired about and will share our feedback with you shortly.

Ok. Which CodePage is given out the Java API? UTF-8 possible?

One more question concerning other european languages that do not use latin letters, like greek or bulgarian. Do you have planned to add these to your portfolio? Short term or mid term?
We look for a tool we can use internationally. Off course, greek and bulgarian are not in the first row, but we have for example just recently bought a hungarian company. If we want to offer our services there, the language must be available for us also in OCR tools.

Best regards
Herbert

@herbert.angermann

We do intend to add support for maximum languages in the API in order to make it feasible to use internationally. Feature requests are logged in our issue tracking system as following:

  • OCRJAVA-145 (Greek Support)
  • OCRJAVA-146 (Bulgarian Support)
  • OCRJAVA-147 (Hungarian Support)

Please also note that Aspose.OCR already supports Finnish and Estonian Alphabets which are closest neighbors of the Hungarian Language. We will surely investigate the feasibility of these languages support and let you know as soon as we have some more updates regarding tickets resolution. Please give us some time.

We are afraid that we could not understand this question. Could you please elaborate a bit more?

Thanks.
Any idea how long it will take for OCRJAVA-147 (Hungarian Support) being implemented in Aspose OCR? For this language we already have a requirement on the table. A rough information if we talk about days, wekks, months or years.

In case we buy a Site OEM Licence for OCR, do we have to pay extra for language updates?
If so, how much is the cost for update with this licence?

@herbert.angermann

Aspose.OCR supports Finnish and Estonian alphabets as shared earlier. These languages ​​lie in one group of Finno-Ugric languages. You can use Finnish or Estonian, they just don’t recognize the two letters - Ű ű. We will add support for recognizing these characters in future releases after updating the language model (this will take up to several months).

You will not have to pay extra for the language updates. The license validity is one year and you will be entitled to upgrade the API to the latest version for free during this period. For example, if your license gets expired on August 2022 and language support is added in API release of September 2022, you will need to re-new your license in order to use the latest version.

Hi Ali. What does “re-new” mean? Buy the same licence again?
Greetings
Herbert

@herbert.angermann

Yes. You will be renewing your subscription by getting a new license which will be valid for another complete year. Please note that it will also support all the previously released versions of the API. For further information on this topic, you may please create a post in our Purchase forum where our Sales Team will assist you accordingly.

ok. But that means, that if a new language is added and I want to use it, I pay several thousend $ for it.
Hmm. When do you plan to release hungarian?
Greetings
Herbert

@herbert.angermann

No, we did not mean that. If a new language is released in a version which is already supported by your existing license, you will be able to use it for free as mentioned in one of our previous responses. You will only need to pay for new license when existing license has been expired and new API update is released after the date of expiry of the license.

As shared earlier, we have this feature in our plans and it will take several months to implement it. You will receive a notification in this forum thread as soon as the feature is added.

Thanks for this information.

Concerning your previous message.
I understand. But Site OEM never expires. The only thing that expires is the update permission for this licence. Update is valid only for 1 year.
Thus, if I want to use a language, that is released more than 1 year after I buy my licence, I have to buy a new Site OEM licence. I don’t see a price for “update SITE OEM licence”.

Is there a chance that Site OEM licences are taken out of product range and that one is forced to use a metered licence? Because that is not interesting for us. I can buy a new Site OEM licence every 5 years to get an updated software. That calculates as average 1000$/year for licence update. But I cannot pay permanently for using the software.

@herbert.angermann

Your inquiry is more related to sales. Please post it in our Purchase forum as requested earlier, where you will be entertained accordingly and specifically.