I want to optimise tesseract 4 (lstm) for a set of documents I have. I managed to improve its character recognition using the documentation in https://tesseract-ocr.github.io/tessdoc/TrainingTesseract-4.00.
However, some words are not just detected. usually words inside tables. Even using --psm 6, some are missed. Is there a way to train the layout/segmentation/word detection engine and not just the character recognition? -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/e210bfe2-563a-48a5-b0bc-5363c7269bcfn%40googlegroups.com.
