This problem isresolved now. we can call function ClearAdaptiveClassifier();
/** * Call between pages or documents etc to free up memory and forget * adaptive data. */ On Friday, December 4, 2015 at 11:39:39 PM UTC+8, [email protected] wrote: > > Dear all: > > I find one interesting problem when use tesseract 3.02. > > I read one simple image (attatched), parameter is > "char_digit-reappear-fail.bmp result -l eng -psm 10 DigitLimit". If we open > ocr engine, then continue to read 3 times, result of first and second is 0, > while result of third is 3. If we restart program, the result is 0. It > seems that some paramter is adaptive update according to previous > recognition. > Thanks. > -- 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]. To post to this group, send email to [email protected]. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/667ffe84-0592-4c4c-b550-786d21614462%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
