Since comers is such a rarely used and archaic word in English, almost always with the word all before it, any time English OCR software thinks it sees "comers" it should be flagged, tagged and bagged as corners unless all is right before it.
http://www.thefreedictionary.com/All+comers
OCR software needs a lot more work on discriminating between lowercase m and rn. I've seen books where nearly every instance of each was recognized as the other. Same thing for some other troublesome letter pairs. A "Does this word really exist in English?" sanity check would cure tons of OCR errors. Of course that would require OCR software to include spelling and grammar checking too.