I'd like to bump this topic. I am new to OCR and I find weird enough that there's no hardware for OCR nowadays (dedicated ICs), no libraries for embedded architectures and the only option is to use ARM platforms with linux and tesseract.
BTW running a test on a digit-only image on a raspberry Pi (armv6) with debian, I needed 34Mb of virtual mem, 1.5s of 99% CPU load. Embedding it into low capabilities cores can be surely hard. On Thursday, June 9, 2011 3:28:26 PM UTC+2, Yura Komlyk wrote: > > Hello! > I'm interested in system with minimum computational possibilities (the > most 'slowest' CPU and minimum RAM) on which tesseract could still work. > The goal is to use it in minimized pc-platform device. > Maybe someone know another way to make minimized device with OCR > capability. BTW only digits recognition is enough here. > > 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 --- 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]. For more options, visit https://groups.google.com/d/optout.
