Hello, I want to use tesseract to check if there is printed the correct freshness date on a product. After teaching tesseract i still have about 10% of dates read wrong. Mostly 5 and 6 are mixed up.
However, since I know the what the date should be I can set a whitelist with the according character for each region and just check if the confidence level is high enough. When I was using SetRectangle for the entire text field I was getting high confidences for each character. Now I iterated through all regions using their bounding boxes for SetRectangle and setting a new whitelist the confidences were much lower. Any ideas what I am doing wrong? Any easier ways to use ocv with tesseract? Or an entirely different approach? -- 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/df2b9a7d-034a-4c49-942c-9a3309cfd813%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
