← Archive.aspx_AMID__Type__ADID_302.pdf
OCR Overlay — PaddleOCR-VL (Baidu)
Boxes are the OCR items for each page, colored and labeled by field type (numbering restarts each page). view JSON
Page 1
23 item(s)
LIST_ITEM (3)
PAGE_HEADER (3)
SECTION_HEADER (10)
TEXT (7)
1 · PAGE_HEADER
2 · PAGE_HEADER
3 · TEXT
4 · SECTION_HEADER
5 · PAGE_HEADER
6 · SECTION_HEADER
7 · TEXT
8 · SECTION_HEADER
9 · LIST_ITEM
10 · LIST_ITEM
11 · LIST_ITEM
12 · SECTION_HEADER
13 · TEXT
14 · SECTION_HEADER
15 · TEXT
16 · TEXT
17 · TEXT
18 · SECTION_HEADER
19 · SECTION_HEADER
20 · SECTION_HEADER
21 · SECTION_HEADER
22 · SECTION_HEADER
23 · TEXT
Page 2
12 item(s)
PAGE_HEADER (2)
SECTION_HEADER (3)
TABLE (2)
TEXT (5)
1 · PAGE_HEADER
2 · PAGE_HEADER
3 · TEXT
4 · TEXT
5 · TEXT
6 · TEXT
7 · SECTION_HEADER
8 · TABLE
9 · SECTION_HEADER
10 · SECTION_HEADER
11 · TABLE
12 · TEXT
Page 3
15 item(s)
LIST_ITEM (9)
PAGE_HEADER (3)
SECTION_HEADER (3)
1 · PAGE_HEADER
2 · PAGE_HEADER
3 · PAGE_HEADER
4 · SECTION_HEADER
5 · LIST_ITEM
6 · LIST_ITEM
7 · LIST_ITEM
8 · LIST_ITEM
9 · LIST_ITEM
10 · LIST_ITEM
11 · LIST_ITEM
12 · LIST_ITEM
13 · LIST_ITEM
14 · SECTION_HEADER
15 · SECTION_HEADER