Hi all, I'm looking a non-deeplearning-based textlines detection/segmentation algorithm, since my problem is relatively easy (without complexed background). I wrote several scripts with a combination of OpenCV ops like dilate, erode and findContours etc.. But I found it's very sensitive to hyperparam changes (like iterations of dilate).
I know Tesseract're using a non-deeplearning-based textlines detection (as a part of Page Segmentation) and believe many efforts have been put on tuning it. Did you guys have any idea about the paper/code I could refer to? Thanks, Xiaoyi -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/1ff5486b-4a47-4629-bf1a-e74e6d430b0cn%40googlegroups.com.
