The character coordinates which I get through FineReader Engine API (ICharParams interface) seem not to match the source image. What's the reason?
Text coordinates do not match the image
Was this article helpful?
0 out of 0 found this helpful
Comments
1 comment
Most probably the ImageDocument was preprocessеd (deskewed, rotated, so on) in this or that way before recognition. For example, the default setting in FineReader Engine is to correct skew while preparing the image. The coordinates you get from engine refer to the deskewed image, to convert them back to source image you need to use ImageDocument.ConvertCoordinates method.
Please sign in to leave a comment.