OCR Image Creating RecognitionBlock

Aspose.OCR Product Family
1

I am working with an image, and trying to get all the numbers in the image.

What is the best way to make RecognitionBlock in code based on the size of the image?
What is the Best resolution for the images to be at?

Right now if I make the boxes in code, and give it the points it works fine to find the text.
But when I start doing it programmatically, not only does it take a long time 50,000 RecognitionBlocks, but it does not grab half of the numbers on the image.

Here is how I am making the RecognitionBlocks

for (xCord = 0; xCord < img.Width - 60; xCord += 25)
{
for (yCord = 0; yCord < img.Height - 70; yCord += 25)
{
ocrEngine.Config.AddRecognitionBlock(RecognitionBlock.CreateTextBlock(xCord, yCord, 60, 70));
}
}

2
Hi John,

Thank you for your inquiry.

Minimum resolution that is required to perform OCR operation is 300 DPI. 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. It will not be possible to get 100% accuracy if you wish to scan the complete image. On the other hand, if you intend to get some specific contents from a portion of the image, you can use the custom recognition blocks to get better accuracy.

Please note, the above mentioned solution is useful in scenario when you have documents/images following the similar structure, that is; the contents to be scanned are always on the same location for each image.

For creating custom recognition block it all depends upon programming convention and image layout.

3

Thanks, I have raised the Resolution - but coming from a base, it might work any better. When I assign the blocks, they work fine and are able to pull the info. But we don’t know where those blocks will be. Perhaps this is not the solution for us.
Thanks for the input, I will continue testing.

4
Hi John,

Thank you for update.

We also will further investigate it at our end and will update you about our findings via this forum thread.

5
Hi John,

This is to update you that we have investigated the issue of making the custom recognition boxes in code and doing it programmatically. Initial investigation shows that the issue persists. The issue has been logged into our system with ID OCRNET-1393. Our product team will further look into it. we will update you with our findings via this forum thread.

6

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