try by setting to 300 dpi resolution and not 93dpi. it should work. On Tue, Jun 2, 2009 at 3:39 PM, Denis E. <[email protected]> wrote:
> His, > > thanks for your message, I really should have scrutinized the documentation > first. > I tried scaling the image to 1779x100px and set resolution to 92dpi (all in > gimp) > > Tesseract produces then: > HHhhhhhhhhhhhhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVHHHHHHhhhhhhhhhhhhVhVhVhVhVhVHHHHHH$lll > 444l<W<<il4 IUJWWIIIIIIIIWNUWWWlUJ <|1U > > Could you please advise if I am heading in the right direction by trying to > scale image to get a meaningful text out even though the original is ocr > averse? > > thanks > > > On Fri, May 29, 2009 at 7:06 PM, Ray Smith <[email protected]> wrote: > >> RTFM. See the FAQ on small text.Ray. >> >> >> On Tue, May 19, 2009 at 1:33 PM, denis56 <[email protected]>wrote: >> >>> >>> Here is the link to three files that I mentioned (original, converted >>> with java imageio package, and with Image Converted utility) >>> http://www.speedyshare.com/732780799.html >>> >>> Thanks >>> >>> On 19 Mai, 16:27, denis56 <[email protected]> wrote: >>> > His again, >>> > >>> > after having installed tesseract, I ran it against tif files. >>> > Unfortunately text is not being recognized. >>> > >>> > The tiff files were produced by converting a png images (yellow >>> > background, red font) >>> > 1) with java ImageIO >>> > boolean b = ImageIO.write(image, "tiff", fileName); >>> > >>> > - when running tesseract against this type an empty file will be >>> > outputted >>> > >>> > 2) with Image Converter .EXE utility on Windows >>> > >>> > - tesseract churns out following text >>> > \\\\\\\\\\\\\\\\\\\\\HHHHHHHHHHHH\\\\\\\\\\\\\\\\\UU\\\\\\\\\\\\\\\H\W >>> > >>> > While feeding tesseract with eurotext.tif sample file produces perfect >>> > output. >>> > >>> > Could anyone suggest possible reasons for failure. Maybe background >>> > and text flow together, special care should be taken by converting png >>> > into tiffs? >>> > >>> > Thanks >>> >>> >> >> >> > > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
