Art of Life


Project Overview

Note: The Art of Life project period is now complete. The project ran from May 2012-April 2015.

The Art of Life: Data Mining and Crowdsourcing the Identification and Description of Natural History Illustrations from the Biodiversity Heritage Library, which was generously funded by the National Endowment for the Humanities and ran from May 2012-April 2015, sought to liberate natural history illustrations from the digitized books and journals in the online Biodiversity Heritage Library (BHL) through development of software tools for automated identification and description of visual resources. BHL is an international consortium of the world’s leading natural history libraries, including Missouri Botanical Garden Library, that have collaborated with publishers, rights holders, and other interested parties to digitize the public domain literature documenting the world’s biological diversity within member libraries’ collections. BHL has partnered with Internet Archive for -effective and efficient mass scanning and storage of its digital library, resulting in the standards-based digitization and open access dissemination of more than 110,000 volumes and 40 million pages of core historic literature.

Contained within BHL’s digitized texts are millions of visual resources (plates, illustrations, figures, maps, and other images), many of which were produced by the finest botanical and zoological illustrators in the world, including the likes of John James Audubon, Georg Dionysus Ehret, and Pierre Redouté. These images are currently minimally described at a structural page level, enabling citation resolvers and human users to navigate to illustrations by page numbers, but the images lack sufficient descriptive metadata to enable dynamic filtering and inquiry based on factors like image type, color content, subject matter, or even names of the organisms depicted in the images.

Through this project Missouri Botanical Garden, in partnership with Indianapolis Museum of Art, built new software tools and augmented existing electronic publishing frameworks to run across the entire BHL corpus and identify the visual resources within, thereby ensuring these images are not only more useful to the current audience of scholars who consult BHL on a regular basis, and discoverable by new audiences, but also better interconnected with related materials across the Web. Scholars and educators who rely heavily on visual resources in their research and teaching (e.g. biologists, art historians, curators, historians of science) will, for the first time, be able to find and view a wealth of illustrations of plant and animal life from which to make connections between science, art, culture, and history.

A selection of illustrations from BHL’s Flickr photostream:

A full list of BHL sets at Flickr can be found at:

Any views, findings, conclusions, or recommendations expressed in this wiki page do not necessarily represent those of the National Endowment for the Humanities.

Back to top

Project Team

Missouri Botanical Garden

  • Trish Rose-Sandler, Principal Investigator
  • William UIate, Project Management/Budgeting
  • Mike Lichtenberg, Programmer
  • Doug Holland, Consultant
  • Chuck Miller, Consultant
  • Mike Blomberg, UI development

Indianapolis Museum of Art

  • Ed Bachta, Programmer
  • Kyle Jaebker, Project Management
  • Charlie Moad, Project Management

University of Colorado, Boulder

  • Gaurav Vaidya, Schema design & Wikimedia Commons liaison
  • Rob Guralnick, Consultant

Smithsonian Libraries

  • Joel Richard

Back to top

Advisory Board

Co-chairs – Kyle Jaebker and Trish Rose-Sandler

  • Doug Holland, Director, Missouri Botanical Garden Library
  • Dr. Hong Cui, Assistant Professor, University of Arizona
  • Dr. David Kohn, Director and General Editor, Darwin Manuscripts Project, American Museum of Natural History
  • Charles Miller, Chief Information Officer, Missouri Botanical Garden
  • Nancy Gwinn, Director,Smithsonian Institution Libraries
  • Robert Guralnick, Associate Professor at the University of Colorado at Boulder
  • Betty Smocovitis, Professor of Zoology and History at the University of Florida

Back to top

Original Proposal & Schedule

Back to top


Art of Life Workflow

Back to top


Both the algorithms and Macaw classification software tools are licensed as FOSS (Free and Open Source Software) and can be found on github.

Algorithms built by the Indianapolis Museum of Art Lab used to identify which pages in BHL have images:

Macaw tool built by the Smithsonian Libraries for classifying illustrations that were found by the algorithms:

Schema developed by University of Colorado Boulder and Missouri Botanical Garden for describing natural history illustrations:

Back to top


Back to top


Back to top

Media Coverage

Science Gossip on Zooniverse

Back to top

Social media comments on Science Gossip

Back to top

1 million image upload to Flickr

Back to top

NEH promotion

Back to top

Initial Announcements

Back to top

Related Projects

Back to top