I find tesseract-ocr's segmentation is not good for some images. So i do the segmentation by myself.
I have tried "setRectangle", but it will recognize character by character. And the result is worse than sending the whole image to ocr engine. I guess tesseract's post-procesing have fix many error result with context information. So how can i just replace all the segmentation of Tesseract? something like set the "block_list"? -- 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 http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/a67da154-4e54-47b5-ab68-20f9dff14ab7%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
