When I use LayoutParser on scientific documents that have watermarks, the generation of bounding boxes completely falls apart, and the information in the entire region covered by the watermark is not segmented/identified.
Can someone please clarify how to use LayoutParser in a way so as to avoid watermark interference?
When I use LayoutParser on scientific documents that have watermarks, the generation of bounding boxes completely falls apart, and the information in the entire region covered by the watermark is not segmented/identified.
Can someone please clarify how to use LayoutParser in a way so as to avoid watermark interference?
Thanks!