Thanks for the reply Bernard. It's good to know that my traineddata size is normal. I will now focus on improving my samples, hopefully I can improve the performance. Seems like a case of overtraining.
The *.tr tip is a gem, really appreciate it :) Thanks again! Fred On Wednesday, February 26, 2014 8:19:28 PM UTC+8, Bernard Polarski wrote: > > > If you do not include a word-dawg, freq-dawg then the only big file is > inttemp. > For 34000 character I am surprised to see it at the size of around 100k. > However your 6000 represents only 10 digit so it is very possible. > As of the poor performance, I think that the size is very detrimental : > the character are usually 20 to 40 pixel high and 20 to 50 wide ( only for > 'm' or 'w' ) > Too much precision is not good. > > All he others files are usually rather small (pffmtable, normproto, > font_properties. shapetable, unicharset, unicharambigs) > and combined are less than 100k. > > In this respect your traineddata seems normal. > > Beside that you could write using wildcard: > > shapeclustering *.tr > mftraining *.tr > cntraining*.tr > > > Le mardi 25 février 2014 17:51:39 UTC+1, Frederico Ferro Schuh a écrit : > >> Hello all, >> >> I'm training Tesseract to recognize handwritten digits, and I have >> provided it about 6000 samples of each digit, in 10 different box files, >> one for each digit. Each box file is a 2152x2152 TIF file. However, the >> resulting traineddata file I get after completing the training procedure is >> only 137 kb. >> I went through the process again, providing smaller sample files (1000 >> samples of each digit), and ended up with the same traineddata size of 137 >> kb. >> Is this size reasonable or am I doing something wrong? >> I assume something is wrong because my results are pretty bad so far. >> >> I've attached the sample image I am using for the digit 0. >> >> Thanks in advance, >> Fred >> > -- -- 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.
