Text no recognized

Aspose.OCR Product Family
1
I've downloaded your trial Java ocr library aspose-ocr-3.0.0.jar for a test to evaluate the purchase. But the characters recognition does not seem to work very well.
Below the code snippet I used and in attach the image I used.
The environment is Windows 7 and the Java IDE is NetBeans 8.1

OcrEngine ocrEngine = new OcrEngine();
//Set the Image property by loading the image from file path location
ocrEngine.setImage(ImageStream.fromFile("c:\\a\\Provaocr.jpg"));
//Process the image
if (ocrEngine.process())
{
//Display the recognized text
System.out.println(ocrEngine.getText());
}

and below the debugging output:
P<@5= gZK5 s enc <=A<mZa< < < < < < < < < < < < <
2
Hi Claudio,

Thank you for inquiry.

Note that you can get a temporary license in order to evaluate the Aspose.OCR API. Please check the below linked web page and follow the instructions on it to get your temporary license.


We have evaluated the attached file at our end. While testing it was found that the image has very low DPI value i.e. 96. Please note that the current implementation of the Aspose.OCR API works well with images having resolution of at least 300 DPI and the accuracy rate tends to decrease by decreasing the resolution. Your provided image has resolution of 96 DPI therefore it will not be possible to get 100% accuracy if you wish to scan the complete image.

Please note that we have already logged the issue of OCR operation on low DPI image with ID OCR-34250 in our system. We will update you about the progress via this thread.

Hope the above information helps. Feel free to contact us in case you have further query or comments.

3

Still don’t work fine.


I attach the new image (a passport), the recognized text is:
00,O’Av``%pmplw-945%90%9!!!.NMZ#.5%{W%;ysmie/VVWJMPNVWNN%NWN3999990%%%%%N#Wppyph%WWWWMW;pppephipp:pyWW3MVVWWFN3@W#99N3$@#c$%#&nV$q#NW9N$%%#WWFuWnWiyandyeanupp.ipZ@%p0@{%NNWL%N%/%7V’
-. dgen’cey --s-----im.m- Trf$,L:lzszlif/l$X%>N1`:,.Mifi—:*-llu-i.:iftillsat
BUILD SUCCESSFUL (total time: 48 minutes 42 seconds)

My interest is in the last 2 lines (P<HUNASCHIERO …) but I don’t see this sequence in the recognized text.
Maybe I must set some parameters to optimize the recognition ?

Thanks

4
Hi Claudio,

Thank you for providing sample image.

Please note that we have tested the scenario at our end and are able to replicate the said issue. The issue has been logged into our issue tracking system with ID OCR-34155. Our product team will further look into it. We will update you about progress via this thread.

We are sorry for the inconvenience caused.
5

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