metadata
language: en
license: mit
...
Page Filtering
Model to identify pages in children's books of the long 19th century (ca. 1789-1914) that contain illustrations. It is used to filter non-relevant pages without illustrations trained on hand-coded data.
Results on our validation dataset:
| f1score | precision | recall | accuracy | |
|---|---|---|---|---|
| not-relevant | 99.09 | 99.39 | 98.79 | - |
| relevant-cover | 100 | 100 | 100 | - |
| relevant-page | 95.65 | 94.29 | 97.06 | - |
| Macro Avg. | 98.25 | 97.89 | 98.62 | 98.5 |