How to improve recognition of some problematic fields (FlexiLayout)

Question

In some cases because of certain field traits or document's quality, it may be hard to correctly recognize and extract a field in FlexiCapture/FlexiLayout:

mceclip0.pngmceclip1.png

Answer

One way that this could be improved is to convert the CharacterString search element to a Region:

mceclip2.png

Using Relations to correctly set the region on the document so it correctly includes the necessary area:

mceclip3.png

This, in combination with using correct parameters for the text field (data type and the textbox type in this case) improves the extraction results, as so:

mceclip4.pngmceclip5.png

Have more questions? Submit a request

Comments

0 comments

Please sign in to leave a comment.