Welcome to Skelevision!

Skelevision is an ongoing effort to measure skeletal functional traits for the world’s birds.

The data are generated by photographing museum skeleton specimens and then using a deep learning neural network to identify the various bones and measure them.

Skelevision is led by Brian Weeks at the School for Environment and Sustainability at the University of Michigan, in collaboration with David Fouhey in the Department of Computer Science and Engineering at University of Michigan.

Any work derived from these data should cite: Weeks, B.C., Z. Zhou, B.K. O’Brien, R. Darling, M. Dean, T. Dias, G. Hassena, M. Zhang, and D. Fouhey. A deep neural network for high throughput measurement of functional traits on museum skeletal specimens.

These data are freely available for use in research; however, we have several ongoing research projects based on the data, so if you are planning on using a significant amount of skelevision data, please reach out to Brian (bcweeks@umich.edu) to be sure there is no duplication of effort!