Finished! Looks like this project is out of data at the moment!
Thank you for contributing! Our project is now complete! Click here for more details. To browse other active projects that still need your classifications, check out zooniverse.org/projects.
FAQ
What is the point of this project?
This project is all about generating and further enhancing data associated with archival photographs. Although most photographs in collections will have some metadata associated with it, we are keen to explore what other data can be generated through crowdsourcing to help enhance the searchability and accessibility of these photographs.
What will you do with the data created for this project?
All data generated from this project will be ingested back into their appropriate collections. Data from Zooniverse will be incorporated in comparative analysis with data generated by machine learning models to explore the differences between the outputs of both approaches. Some data will also be used to train a machine learning model as further experimentation (see below).
Will my responses to the workflows be used to train AI?
We will be using responses to some of the workflows (mainly the object identification workflow) to help train a machine learning model which will undertake a similar task using photographs. This will be entirely experimental, and only used for the purposes of this research. We are mainly looking to see if crowdsourced data can be used to improve machine learning models undertaking similar tasks and further our understanding of how these two approaches to data generation and enhancement can work together.