Does tesseract have an option to set the expected character count of an image?
I am processing images containing handwritten numbers (paper based filling system references), using tesseractDotNet (wrapper for 3.01). I do a lot of preprocessing to make the images as clean as possible, and the results are very good, but occasionally, usually when the characters are slightly joined, tesseract will detect an extra non existent number. At present the return value is counted and if it contains too many characters (the expected character count is fixed) then the image is flagged to human processing. I am now looking to improve this, so before i write a segmentation routine into preprocessing, i wanted to check if tesseract has any kind of setting to tell it how many characters to expect? Any help appreciated -- 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
