When I made my tests it came out that most time was consumed by init of language data (try chi_tra instead of eng ;-)) for such a small image. If you have a lot of such image to OCR, than it make sense to use tesseract API - you init tesseract once and then you send it your images...
Zdenko On Wed, Jun 12, 2013 at 5:00 PM, Šarūnas S. <[email protected]> wrote: > Yes, OCR it :) I just use tesseract v3.0.2 on windows 7 command line with > config file as above with faulty line removed :) > > Also tried using -psm 10 but the effect seems to be marginal > > Sarunas > > 2013 m. birželis 12 d., trečiadienis 16:23:44 UTC+2, zdenop rašė: >> >> To read it or to OCR it ;-) ? Please be more specific... Also please >> specify how you measure it, how you read/OCR it (API, executable)... >> >> Zdenko >> >> >> On Wed, Jun 12, 2013 at 3:43 PM, Šarūnas S. <[email protected]> wrote: >> >>> Haha, it seems it is never too late to make noob mistakes ;) Thanks guys! >>> >>> Also, do you have any ideas how to speed up the OCR of the image >>> attached before? Currently it takes around 0.3s to read it, which I find >>> quite costly for just one char. >>> >>> Cheers >>> Sarunas >>> >>> 2013 m. birželis 12 d., trečiadienis 12:47:59 UTC+2, zdenop rašė: >>>> >>>> You specified in your config file (user_words_suffix 0) that tesserect >>>> have to use user dictionary with name "eng.0" (or <lang>.0). >>>> Why you did it if there is no such file? >>>> >>>> Zdenko >>>> >>>> >>>> On Wed, Jun 12, 2013 at 10:14 AM, Šarūnas S. <[email protected]> wrote: >>>> >>>>> No, but when I looked at >>>>> >>>>> https://code.google.com/p/**tess**eract-ocr/downloads/**detail?** >>>>> name=tesseract-ocr-3.**02.eng.**tar.gz&can=2&q=<https://code.google.com/p/tesseract-ocr/downloads/detail?name=tesseract-ocr-3.02.eng.tar.gz&can=2&q=> >>>>> >>>>> there was no eng.0 here as well. Is there such a file? >>>>> >>>>> Kind regards, >>>>> Sarunas >>>>> >>>>> 2013 m. birželis 12 d., trečiadienis 08:22:02 UTC+2, zdenop rašė: >>>>>> >>>>>> On Tue, Jun 11, 2013 at 6:28 PM, Šarūnas S. <[email protected]>wrote: >>>>>> >>>>>>> Hi, >>>>>>> >>>>>>> For the past couple of days I've been battling with Tesseract 3.02. >>>>>>> I am using the installable version on Windows 7 x64. Tell me what I'm >>>>>>> doing >>>>>>> wrong here: >>>>>>> >>>>>>> I create a file fast_custom and put it in C:\Program Files >>>>>>> (x86)\Tesseract_OCR\tessdata\**c****onfigs\fast_custom >>>>>>> with text: >>>>>>> >>>>>>> load_system_dawg False >>>>>>> user_words_suffix 0 >>>>>>> textord_fast_pitch_test 1 >>>>>>> tessedit_char_whitelist 0123456789-.,$JQKA >>>>>>> >>>>>>> However when I run the following on administrator cmd: >>>>>>> tesseract 1.bmp temp -psm 10 fast_custom >>>>>>> >>>>>>> I get the error: >>>>>>> Could not open file, C:\Program Files(x86)\Tesseract-OCR\**tessd**** >>>>>>> ata/eng.0 >>>>>>> >>>>>>> And does that file exist? >>>>>> >>>>>> >>>>>>> Can anyone help me with this? >>>>>>> >>>>>>> The image in cosideration is attached >>>>>>> >>>>>>> -- >>>>>>> -- >>>>>>> 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 >>>>>>> tesseract-oc...@**googlegroups.**c**om >>>>>>> >>>>>>> For more options, visit this group at >>>>>>> http://groups.google.com/**group****/tesseract-ocr?hl=en<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 tesseract-oc...@**googlegroups.**c**om. >>>>>>> >>>>>>> For more options, visit https://groups.google.com/**grou**** >>>>>>> ps/opt_out <https://groups.google.com/groups/opt_out>. >>>>>>> >>>>>>> >>>>>>> >>>>>> >>>>>> -- >>>>> -- >>>>> 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 >>>>> tesseract-oc...@**googlegroups.**com >>>>> For more options, visit this group at >>>>> http://groups.google.com/**group**/tesseract-ocr?hl=en<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 tesseract-oc...@**googlegroups.**com. >>>>> For more options, visit >>>>> https://groups.google.com/**grou**ps/opt_out<https://groups.google.com/groups/opt_out> >>>>> . >>>>> >>>>> >>>>> >>>> >>>> -- >>> -- >>> 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 >>> tesseract-oc...@**googlegroups.com >>> For more options, visit this group at >>> http://groups.google.com/**group/tesseract-ocr?hl=en<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 tesseract-oc...@**googlegroups.com. >>> For more options, visit >>> https://groups.google.com/**groups/opt_out<https://groups.google.com/groups/opt_out> >>> . >>> >>> >>> >> >> -- > -- > 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. > > > -- -- 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.
