Structured document layout produced by Florence-2 or similar
document understanding models.
Captures the spatial arrangement of text, tables, figures, headings,
and other semantic blocks within a multi-page document. The Florence-2
tier gives one page with a text block for each line it reads, with the
line's bounding box.
Structured document layout produced by Florence-2 or similar document understanding models.
Captures the spatial arrangement of text, tables, figures, headings, and other semantic blocks within a multi-page document. The Florence-2 tier gives one page with a
textblock for each line it reads, with the line's bounding box.