We’re considering adding OCR capability to our application. The issue is that it would sometimes need to OCR large files ( 200 pages or more) and this tends to be very time-consuming and impractical when done in Adobe Acrobat desktop. How does the speed of your OCR app compare with that of Adobe Acrobat?
Hi there,
Thanks for your inquiry. I'm afraid, currently Aspose.OCR OCR capabilities are not up to mark. So its very difficult to compare it with Adobe Acrobat. Our development team is working hard to improve the performance and capabilities of the product. For the purpose some new algorithms are under testing for improvement of supported fonts recognition accuracy and performance.
Sorry for the inconvenience faced.
Best Regards,
Do you have any idea when you expect to release an OCR product you are happy with?
Hi there,
One more feature we would like to see added to the OCR function:
We would like the OCR feature to be able to determine if the PDF contains searchable text. If yes, no OCR would be performed and our application would know to bypass the doc.
Hi Tom,
- Check whether PDF is image only using Aspose.PDF
- Extract image from PDF using Aspose.Pdf
- OCR the extracted image using Aspose.OCR