Annotated Bark Image Bank
Research to develop an annotated bark image bank of hardwood trees in the Central Hardwood region, as well as an AI algorithm for bark-based species recognition and a smartphone app for bark-based tree species identification.
- Rado Gazo, Professor, Forestry & Natural Resources, Purdue University
- Bedrich Benes, George W. McNelly Professor of Technology, Computer Graphics Technology, Purdue University
- Songlin Fei, Professor, Forestry & Natural Resources, Purdue University
The main goal of this project is to develop smartphone app to correctly identified tree speciesby their bark for hardwood trees in the Central Hardwood region. Specific objectives are:
- Develop a standard protocol for data collection.
- Develop a smartphone app that will allow users to acquire images of tree bark and associated data in the field, and transmit this data to a central database.
- Develop a central database that will house the collected information, allow for verification and data labeling, query, and sharing among researchers.
- Develop Bark ID app
- Organize workshops to train professionals and the public on using the bark ID app. Additionally, organize an international workshop for researchers working on AI approaches to tree bark identification.