Book layout

Detect structure of given page.

Format

Each clipping found in a corresponding PDF/DjVu file. Each clipping should be given as L:P/X0,Y0,X1,Y1:PROB, where:

L — (optional) label
P — DjVu page number (starting from 1, optional if one-page documents are assumed)
X0, Y0, X1, Y1 — clipping coordinates (in pixels)
PROB — (optional) probability

Directory structure

• README.md — this file
• config.txt — configuration file
• train/ — directory with training data
• train/in.tsv — input data for the train set
• train/expected.tsv — expected (reference) data for the train set
• dev-0/ — directory with dev (test) data
• dev-0/in.tsv — input data for the dev set
• dev-0/expected.tsv — expected (reference) data for the dev set
• test-A — directory with test data
• test-A/in.tsv — input data for the test set
• test-A/expected.tsv — expected (reference) data for the test set