You will have much better success here by developing a routine that crops out the area of the meter containing the numbers before running it into OCR. If for instance all your meters look the same, you can guide the creation of the photo with for instance an app with an overlay of where to position the meter in the camera view (see card.io for an example). Then you can focus on OCR for the digits and there are many other posts on this forum about improving OCR for these kinds of display I think.
The red one is hard because it looks like it can be partially in-view and so you won't get a good read off of any non-fully-rotated numbers. Solving that part is beyond what I know but I would be surprised if OCR will do it. Maybe better to look at template matching perhaps. I guess if you follow what I said about getting an image of just the number strip then you can partition that into each number. You can then crop the borders away leaving 6 images and then you can measure the amount of white at top and bottom. If you find there is a certain amount beyond a threshold it tells you the number is rotated and maybe you tell the user (if an app) that they need to wait for numbers to fully rotate. Manual fallback is always worth considering. E.g. card.io and Apple Pay scan the card BUT always offer the user the ability to modify just in case. Don't really 100% on OCR. Dirt/grease/moisture that affects the number area will also be hard to tackle in all cases. Some cases will probably be solvable with some image processing techniques but you can never say for sure what you're going to get in the field hence manual input always worth having. Cheers On 21 July 2015 at 07:40, Marc Bruins <[email protected]> wrote: > Hello all, > > I was wondering if it was possible to scan the cubical meters and the > liters on a water meter. > > There are a lot of circumstances possible where it is harder to scan the > image which are > > - The reflection of the camera on the glass > - Numbers can be half way down or up > - Most of the time these meters are found in very dark places > - It happens a lot that there is moist under the glass > - There are different fonts and sizes > > The meter which im talking about is this: > > <https://www.dwrcymru.com/eng/forms/meterreading/_images/meter.gif> > > So my question, is it even possible? If so what would you guys recommend > to create a good OCR for this (Which steps do i need to take?). > > Kind regards, > > Wickpick > > -- > 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]. > To post to this group, send email to [email protected]. > Visit this group at http://groups.google.com/group/tesseract-ocr. > To view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/8c39934a-2c3c-4d3e-8355-466bf11eeec9%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/8c39934a-2c3c-4d3e-8355-466bf11eeec9%40googlegroups.com?utm_medium=email&utm_source=footer> > . > For more options, visit https://groups.google.com/d/optout. > -- 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]. To post to this group, send email to [email protected]. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAORW5vgJ%2B6z2L1Ko-UVDonoJegjVOFnO9arq5PSyMEVoeG1DKw%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
