Hi,       I am using the OCR module to recognize a document and then search for a viariety of patterns at the OcrLine object level.  I can't use the word level becuse some of the patterns span multiple words.        I want to be able to search the OcrLine text and then create ...

After creating a searchable PDF, is it possible to show only the text layer of the PDF rather than the image + hidden text? I'm thinking of something along the lines of Abbyy FineReader, where it shows you the PDF *Image* on the left, and the text it has OCR'd on the right.

Instead of BinarizeCommand give the DynamicThresholdCommand a try and see how it works.  BinarizeCommand is very fast but produces output which is useless in most cases. Also, If I recall correctly the parameters for our AutoDeskewCommand algorithm were suboptimal in 6.0.  We ran a lot of tests and found that setting Precision to 5 ...

This image is AutoDeskewing correctly in 7.0. Color Deskew has some known issues 6.0. Please try converting the image to 1bpp using one of our Thresholding Commands (the availability of our more advanced versions depend on your license).  Then, take this 1bpp image and feed it to the AutoDeskewCommand.GetDeskewAngle to get the skew ...

We are using the Glyphreader OCR engine to perform both zonal and full page OCR on documents. We have noticed that for certain documents the accuracy of the zonal OCR on smaller areas is better than for the full page OCR. The types of errors we are seeing in the full page OCR are 0 being recognised as o, 9 being recognised as g and similar, or in ...

Hi ! This is some part of code to convert files to searchable pdf format. This code runs well for TIFF files and converts them into searchable PDFs. But when I load a non-searchable PDF file, the code converts only the first page of the non-searchable PDF file into the searchable PDF. I am very new user. Could you tell me what am I doing ...

I downloaded and installed Atalasoft 7.  The very last step of the installer was to request a demo license.  I checked OCR and OCR glyph and was prompted to also install the dotImage license as well.  Everything seemed to work.  I rebooted.  clicked start -> all programs -> atalasoft dotImage 7.0 -> demos -> ...

I have seen a couple of (fairly old) posts that mention planned future support for OMR (Optical Mark Recognition) within the Atalasoft DotImage library: http://www.atalasoft.com/cs/forums/thread/13484.aspxhttp://www.atalasoft.com/cs/forums/thread/7480.aspx Can anyone please confirm or deny whether we are are likely to see OMR in DotImage in ...

If I have to import PDFs into a document management application, what's the best way to handle OCR? Some PDFs are already searchable, some aren't. How do I check? Just see if there's any text? Can I turn a non-searchable PDF to a searchable PDF in the same way that I would turn an image into a searchable PDF?   Cheers,   BF

When creating searchable PDFs from images, temp files with names like tmp23.pdf appear in the same folder as the image file. This only appears to be a problem on XP. Is this a known issue? We're using 6.0d   Cheers,   Bob