Show HN: Perspective recovery of text with Python+OpenCV(mzucker.github.io) |
Show HN: Perspective recovery of text with Python+OpenCV(mzucker.github.io) |
I don't understand why you use a graph to detect the position of x an y separately and not a scatter plot of x and y together.
Does it work with characters with more than one part, like "ij:;!?"? Is it confused by comas and periods ".;" that are much smaller? What about accented letters like "ñÑáÁ"?