I don't know what's available in the command-line tools or other tools but the API supports it via the "costs" array (where a high cost means low confidence). Last time I check, even though each box gets its own cost in actuality all letters in a word get the same cost which should be seen as the cost of the word. We really wanted to use the confidence level for ScanBizCards but very quickly gave up on it because we found it to have a poor correlation with actual accuracy - instead we have various other ways to tell when a word can be trusted such as: presence of lowercase letters which are really uppercase based on their height (or vice-versa), digits in the middle of letters (or vice-versa), odd punctuation marks at unexpected places.
Patrick On Jul 27, 4:06 am, emre <[email protected]> wrote: > patrick i can get coordinates but how can i get confidence level or > score for each words ? > > On 27 Temmuz, 11:04, patrickq <[email protected]> wrote: > > > As Zdenko pointed out Tesseract does NOT release the input image - nor > > would it make any sense if it did as it would force the calling app to > > make a copy of the image buffer every time it called Tesseract if it > > needed to reuse it for other calls. Note also that all output > > parameters such as text, coordinate or confidence arrays are also not > > automatically released - even if you delete the Tesseract class > > instance. > > > Patrick > > > On Jul 27, 12:01 am, Sandeep Parmar <[email protected]> > > wrote: > > > > Hello everyone, > > > > I am using the following code snippet, within this I would like to know > > > whether 'GetUTF8Text' will destroy my source image 'arr_image' or not > > > after performing recognition. > > > > *api.SetImage((const unsigned char*)arr_image[loop_index3],* > > > * ** width[loop_index3],* > > > * ** height[loop_index3],1,* > > > * ** widthstep[loop_index3]);* > > > * * > > > * char* text = api.GetUTF8Text();** * > > > > Any help highly appreciated. > > > > Thanks & Regards > > > Sandeep -- 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
