i was trying to extract all the tags available in an Engineering Document, unfortunately i got no result, as it is breaking the image into many small parts. the output is filled with garbage values and the tags are missing. if anyone can help me out in finding a solution to this problem,please let me know.
for reference i am attaching the file.
PS:
I am using Fre11 with EngineeringDrawing profile and DocumentConversion_Accuracy
Comments
1 comment
Unfortunately, I am not sure that ABBYY OCR technology is exactly what you need. This kind of engineering documents is not typical for our solutions, so the outputs could be really far from your expectation. I have processed this scheme in FREngine 12 using the TextExtraction_Accuracy and EngineeringDrawingsProcessing profiles: the text tags are mostly extracted, but the outputs still contain a lot of noise and extra recognized characters, because some parts of scheme are recognized as text.
There are no plans to significantly improve this feature in the nearest future. We apologize for the inconvenience.
Please sign in to leave a comment.