Skip to main content
Entomology 2024 Main banner
Bayer Crop Science
Icon Legend
 
Oral Presentation
Oral Presentation
Poster Display
Poster Display
Student Competition
Student Competition
Ticketed Event
Ticketed Event
Back

Program Symposium

Publications

Artificial Intelligence (AI) in Entomology: An Aid to Publishing, Research, and Teaching

High-throughput specimen digitization using whole-drawer images and computer vision AI

Wednesday, November 13, 2024
11:05 AM – 11:25 AM MST
Location: Phoenix Convention Center, 121 C, PCC
Oral Presentation
Museum insect collections are incredibly data-rich, but processing specimens 1-by-1 is time and labor-intensive. We are working to speed up the digitizing process by combining automated whole-drawer imaging with a suite of computer vision-based AI models. From large, high-resolution photographs containing 100s of specimens, we can train AI to automatically find, crop, and extract phenotypic data (qualitative and quantitative) from each individual. We can then use these data to test hypotheses about the macroevolutionary drivers of certain traits, e.g. color patterns, for entire families of insects. These data may even be useful to train future species-ID models, which could help sort backlogs of "unidentified" specimens.