The point is in the lang files, obviously. Tesseract uses different (English) lang files in the above two cases. Things to check: - "tessdata" folder in "c:\foldercontainingimage\" - "tessdata" folder in "c:\" - "tessdata" folder in "C:\Program Files\Tesseract-OCR\" - "TESSDATA_PREFIX" environment variable
HTH Warm regards, Dmitri Silaev www.CustomOCR.com On Fri, Aug 12, 2011 at 1:03 PM, Parmeet bhatia <[email protected]> wrote: > Please find attach the image file. The version is 3.0 > Some extra info. : I am doing automatic page layout before giving it to > tesseract but sometimes non-text blocks also got detected. The attached > image is one example. With proper text blocks, the results are same > but surprisingly not with the images like i attached. > > On Fri, Aug 12, 2011 at 2:09 PM, zdenko podobny <[email protected]> wrote: >> >> can you please provide image file and info what version of tesseract you >> used? >> Zdenko >> >> On Fri, Aug 12, 2011 at 9:03 AM, Parmeet bhatia <[email protected]> >> wrote: >>> >>> Hi All, >>> I observe something pretty strange but could not figure out whats the >>> problem. When i run tesseract from command line from the same folder in >>> which the image is i get diferent results compared to what i get when from >>> command line from different folder and give path to the image. to be more >>> clear the two command lines are: >>> c:\foldercontainingimage> tesseract 1test.jpg out >>> c:\>tesseract ./foldercontainingimage/1test.jpg out >>> the results are different in two out.txt files. Any ideas whats happening >>> around?? Please find attached image and different recognized text results. >>> Thanks, >>> Parmeet >>> >>> -- >>> 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 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 > > > > -- > Parmeet > https://sites.google.com/site/bhatiaparmeet/ > > -- > 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 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
