Wrong out put for OCR

Hi I have used the Java OCR lib with a scanned copy but i got some invalid characters

I have attached the input image


and Out put is


B.V N.D!e.Sn !-!?.U:.B,L l.:K:… D… :e.NT,N::.C . N, …L lN.M.D.:T 2 2 o 0 0 1 2 9
pERsoNALANswEls v4-‘II’vill-II-‘vr’N’‘III
i’s.;’’:-3’-’‘1’‘4’::;.`‘J-’’’’,. W % l 11 p l /AI . 4 irld?----bludlal?II-I/II/I^o-ful-nlobl;1-1-M/IIblolheoVJ-vll)–1-16–://w npw/i:n–>Nl-:-IJI–liMoh-,*:9/:!(3:;81’N -!;W V/6/w /,



Hi Nayana,

Thank you for considering Aspose APIs.

We have evaluated your presented scenario while using the latest version of Aspose.OCR for Java 2.2.0 and the following piece of code.

Java

//Initialize an instance of OcrEngine
OcrEngine ocrEngine = new OcrEngine();

//Remove the graphics from the image
ocrEngine.getConfig().setRemoveNonText(true);
//Set the Image property by loading the image from file path location
ocrEngine.setImage(ImageStream.fromFile(imagePath));
//Process the image
if (ocrEngine.process())
{
System.out.println(ocrEngine.getText());
}

The results returned on my end are different from what you have received, however both results are incorrect. The most probable reason for the incorrect output is that your provided sample image has a combination of German & English language characters. Aspose.OCR for Java currently does not support the German language. Due to this reason when you perform the OCR operation on the complete image, the returned result does not portray any useful information. If you are interested to read all the text from this sample then you have to wait for the German language support, that is already on our road map of Aspose.OCR APIs under the ticket OCR-31611. However, if you wish to read some part of the textual contents from the given image then we would suggest you to add Custom Recognition Blocks for the OcrEngine.

Please feel free to contact us back in case you have any concerns or questions.

The issues you have found earlier (filed as ) have been fixed in this Aspose.Words for JasperReports 18.3 update.