Running a test with your OCR Engine using a TIF file that has been part of our test suite for 9 years. (I can provide other TIF files that fail, but those take even longer.)
Given the attached code and TIF file (2 pages, 300 dpi, 1 bpp), the OCR engine churns for just about 12 minutes and then throws an exception. (see below)
At the moment, we have returned to MODI.OCR (deprecated by Microsoft, but still available). It does this files in well under a minute - about 20 seconds.
Is there a problem with our code, or do we just need to wait for your OCR engine to be more mature?
The exception info:
Aspose.OCR.OcrException: Alphabet of english language doesn't contains symbol:
at ‼.☺.GetClassName(Char ch)
at ¶.♫.↕(☼ fuzzyWord)
at ¶.♫.☺( ocrResult)
at ¶.♣.‼(‼ bitmap, ♦ fontCollection, § blob)
at ¶.♣.↕(‼ bitmap, ♦ fontCollection, § blob)
at ¶.♣.‼(‼ pBitmap)
at ¶.♣.↕(‼ bitmap)