I followed the thread https://groups.google.com/forum/?fromgroups=#!topic/tesseract-ocr/S9CIK3jOMWw and thought I got it working but was surprised to find tesseract confusing "B" for "8" even though I specified the format for alphabet. So I think I must have some misunderstanding somewhere.
I have a config file named "neric" in folder "..\Tesseract-OCR\tessdata\configs" whose contents are: load_system_dawg F load_freq_dawg F user_patterns_suffix neric I have a pattern file named "eng.neric" in "..\Tesseract-OCR\tessdata" whose contents are: \A\d\d\d\d\d\d\d\A where first and last characters are uppercase alphabets with 7 digits in-between. I have also changed kSaneNumConcreteChars to 0. I used the command: tesseract neric.tif neric neric (output to neric.txt, using config neric) Most of the time it recognised fine, but for the letter "B" at the last character position it returns "8" even though the pattern file showed "\A", That made me suspicious that my understanding is wrong all along. tesseract version 3.02 neric.tif captured from webcam with no compression containing only that 9-character image in Helvetica font using OpenCV's captureframe. Would be most grateful for any pointers here. Thank you all. -- -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en --- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/groups/opt_out.
