Deep learning is a form of machine learning, typically employing large neural networks to learn data representations from training data. Since 2012, all the winners of the premier computer vision contest, ImageNet Large Scale Visual Recognition Challenge, have utilized deep learning. Machine learning is already being applied to numerous wildlife classification and recognition problems.
Deep learning applications for human face recognition routinely achieve greater than 99% mean classification accuracy. Our goal is to adapt a deep learning human face recognition algorithm for use with bears. We call this application bearid. The bearid application will automatically scan images and videos from camera traps and citizen scientists to find and identify any bears present in the data. This will vastly reduce the amount of time bear researchers need to spend manually analyzing data.
For more details on how we got started, check out the post BearID Backstory. For the latest updates on the bearid application, check out our blog and our GitHub repository.