Hi Roy, Image enhancement usually means adjusting contrast and the clarity or smoothness of the text. ImageMagick (free) or Photoshop are often mentioned on this discussion list. You should show us an example image so we can see what issues you will have to deal with. Since you are dealing with sensitive images, just a fragmentary segment of numbers would be fine. Since you can use checksums (readily available in open source software) to determine if the card number is correct, you could easily eliminate possibilities. --Sven
On Wed, Dec 28, 2011 at 4:02 AM, mamoos1 <[email protected]> wrote: > Hi, > > Thank you all for your answers. > Zdenko, there is no need to worry, the need is legitimate and legal (a > small startup company) and does not involve any fraud or illegal > activity. > For the other solutions that are available today, I have only been > able to find solutions that cost money per extraction of data. > > Sven / La Monte, > > I am fairly new to image processing, to the best of your knowledge, > can you please recommend any method of doing such pre-image- > processing? (an application or known method of some sort). > > Thank you! > Roy. > > On 28 דצמבר, 08:51, zdenko podobny <[email protected]> wrote: >> http://code.google.com/p/tesseract-ocr/issues/detail?id=574&can=1&q=card >> >> Maybe I am wrong - but I can not imagine legal reason to OCR credit cards... >> For legal reason I guess there are solutions ready... >> >> Zdenko >> >> On Tue, Dec 27, 2011 at 6:24 PM, Sven Pedersen >> <[email protected]>wrote: >> >> >> >> > Hi Roy, >> > I think tesseract could do it, but you'll need to correctly process >> > the image so the pixel height and contrast of the characters is in >> > range. Then you should be able to train with just the recommended >> > number of trials. However, you may need post-processing to clear >> > things up. Tesseract has trouble with single words, which credit cards >> > would generally appear to be. >> > --Sven >> >> > On Tue, Dec 27, 2011 at 6:11 AM, mamoos1 <[email protected]> wrote: >> > > Hi, >> >> > > I want to take tesseract and use it in order to extract name/credit >> > > number for credit card photoes. >> > > I have tried to train it with 3 credit card pictures (seems like >> > > little to me, but I have no idea) - and then use the traineddata in >> > > order to re-scan them and check if it can now extract the data from >> > > them. >> > > The result was even worse than doing it with the original >> > > eng.traineddata >> >> > > my questions are: >> >> > > 1. Do you think tesseract is even able to do such a thing with proper >> > > training etc. ? or is this task simply not what tesseract was designed >> > > to do? >> >> > > if the answer is yes: >> >> > > 2. What type of training and what amount do you believe I should do >> > > before I get good results? >> >> > > Thank you very much! >> > > Roy. >> >> > > -- >> > > 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 >> >> > -- >> > ``All that is gold does not glitter, >> > not all those who wander are lost; >> > the old that is strong does not wither, >> > deep roots are not reached by the frost. >> > From the ashes a fire shall be woken, >> > a light from the shadows shall spring; >> > renewed shall be blade that was broken, >> > the crownless again shall be king.” >> >> > -- >> > 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-הסתר טקסט מצוטט- >> >> -הראה טקסט מצוטט- > > -- > 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 -- ``All that is gold does not glitter, not all those who wander are lost; the old that is strong does not wither, deep roots are not reached by the frost. >From the ashes a fire shall be woken, a light from the shadows shall spring; renewed shall be blade that was broken, the crownless again shall be king.” -- 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
