Using Convolutional Neural Networks to Explore Over 400 Years of Book Illustrations: Starting from February 2016, as part of the British Library Labs Competition, we embarked on a collaboration with the British Library Labs and the British Museum to tag and caption the entire British Library 1M Collection, a set of 1 million book illustrations scanned from books published between 1500 and 1900. We proposed to use convolutional neural networks (CNNs) to perform this automatic tagging and captioning. In addition, we proposed deeper analysis of temporal trends in these images using the explanatory power provided by neural networks.
|File name||Date Uploaded||Visibility||File size|
|README-SHERLOCKNET.txt||31 Jan 2019||Public||2.02 kB|
|sherlocknet_lookup_python_picklefiles.zip||31 Jan 2019||Public||48.5 MB|
|sherlocknet_tags_csv.zip||31 Jan 2019||Public||45.1 MB|
- Resource type
- Place of publication
- Official URL
- Related URL
- Rights statement
- Rights holder
British Library Board
- Additional information
See the readme file for content notes.