Improved text scanning
Preprocess text scans by determining the fix width used for spaces recognizing that the gaps between words can be integral spaces. Use that information to bound the locations containing characters within a box which have no room for one or more space between them.
During later text scanning make the presumption that the box contains text only and no spaces so that "2012" is not scanned as two fields such as "20 " and "12 " or as "20 I " and "2". Recognition of space wideth can also be used to determine with greater accuracy when some blob is non-text because it violates space boundaries
Breaking up words and inserting spaces is very common with this system now and takes a long time to correct. This suggestion applies to Adobe Acrobat Pro DC.
Thanks for the suggestion. We will look into this. We will update you once there is an update.