Hi is there way to do easy training with following concept: - I know font of program messages that need recognition - I know background - Even amount of messages is limited Could I? : - Just pass to training pairs (the screenshot of the error message + the text on that screenshot). - Pass/train to Tesseract number of those pairs Get training result and use Tesseract with it expecting that those images (aka screenshots) with texts that I've supplied will be recognized very correctly? (Up to the exact texts that I've been training them with)
In other words is it conceptually wrong way of thinking? Sort of I know my images I know exact text on them - can I just tell Tesseract to train against the images to give me the texts that are paired with those images) Sort of not getting deep into boxes and stuff :) *Kinda training light?* :) Thank you for any help. -- 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/6fa97f2e-ec76-4a02-b6d2-549c662cf0a6%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
