There are existing license plates fonts, you could use those also for training
See http://www.fontspace.com/category/license%20plate On Thursday, March 8, 2018 at 2:40:35 AM UTC+5:30, Diego Menescal wrote: > > Hello everybody, > > I am starting to get along with tesseract, and when i saw that version 4 > is using neural nets i found this awesome! > I have a project for OCR for License plates on Brazil and has to be open > source code (DIY). > > I was thinking in creating an alphabet with all chars and font used for > license plates in brazil, and then define a neural network to create a > personalized tessdata. > > I have tested several image processing methods, but there are always a new > image from client that cannot be easily treated. It is totally "No free > lunch" theory! > > If anyone could give me a direction, i appreciate! > > Best regards, > > Diego Menescal > -- 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 https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/db9798e3-6916-4552-854d-4209a2ee2052%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
