Researchers at the University of Wyoming, teamed with the U.S. Department of Agriculture’s Center for Epidemiology and Animal Health, have successfully programmed computers to efficiently identify wild animals in photos captured from camera-traps.

UW News reports the research was published in the science journal Methods in Ecology and Evolution and that the lead authors of the paper are UW Department of Zoology and Physiology Ph.D. graduates Michael Tabak and Ryan Miller, both of whom are with the U.S. Department of Agriculture’s Center for Epidemiology and Animal Health in Fort Collins, Colo.

The published work details how this will help to rapidly identify images from camera traps which "can fundamentally change the way ecologists design and implement wildlife studies."

UW published a similar study this year in the Proceedings of the National Academy of Science that sparked the newest research. In the first paper, 3.2 million images were analyzed and categorized by an artificial intelligence system at a 96.6 percent accuracy rate, the same as human volunteers achieved, but faster.

Computer science Ph.D. graduate Mohammad Sadegh (Arash) Norouzzadeh is the lead author of the PNAS article and also a contributor to the newest paper. Other researchers from UW that are involved are Department of Computer Science Associate Professor Jeff Clune and postdoctoral researcher Elizabeth Mandeville of the Wyoming Cooperative Fish and Wildlife Research Unit.

The newer research shows the model was tested on nearly 375,000 animal images at a rate of about 2,000 images per minute on a laptop at 97.6 percent accuracy.

The computer model, “Machine Learning for Wildlife Image Classification in R (MLWIC),” has been made available in a free software package. This will allow others to utilize the program to classify their images containing the 27 species in the database, and will also allow users to train their own machine models using images from new data.

Contributing organizations include the USDA’s National Wildlife Research Center, Arizona State University, California’s Tejon Ranch Conservancy, the University of Georgia, the University of Florida, Colorado Parks and Wildlife, the University of Saskatchewan and the University of Montana.