Hi Dean, Scanning numbers like this works well under our ScanBizCards application - perhaps we can help you out? If your operating context is a mobile app, ScanBizCards has a "remote control" interface designed to help any app with OCR needs get it done at near zero efforts, whereby your app could call out to our app, get something scanned and then ScanBizCards gets right back to the calling app.
Works rather nicely and almost feels to the user like a single app. We use Tesseract 3.01 (with extensive additional corrections and passes) and our own image processing before calling Tesseract - all work that you should not spend time doing if you can help it ... in essence, think of ScanBizCards as an image processing + OCR library available to you, except it's packaged as an app (which has some drawbacks but also plenty of advantages). If your app runs on iOS (iPhone, iPad) or Android devices let me know if you'd like the technical information to test it out. Patrick On Jun 29, 9:11 am, "[email protected]" <[email protected]> wrote: > Correction. The line that reads: > The results show up as <picture name>.tif:<picture name>.txt. > > Should be: > The results show up as <picture name>.tif:<Meter Number that matched>. > > For example, the sample file submitted in the parent thread would have > a result like so: > CIMG0005.tif:76 207 799 -- 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
