Applying deep learning to right whale photo identification.

Photo identification is an important tool used in the field of conservation biology to estimate population abundance and monitor trends over time. However, manually matching photographs to known individuals is time-consuming. Motivated by recent developments in image recognition, we hosted a data science challenge on the crowdsourcing platform Kaggle to automate the identification of endangered North Atlantic right whales. The winning solution was able to automatically identify individual whales with 87% accuracy using a series of convolutional neural networks to identify the region of interest, rotate, and crop the images, create standardized 'passport' photographs, and identify the correct individual whale. The recent advances in deep learning coupled with this fully automated workflow have yielded impressive results and have the potential to revolutionize traditional data collection methods for the abundance and distribution of wild populations. We anticipate that presenting these results to a broad audience will further bridge the gap between the data science and conservation biology communities and encourage others to utilize computer vision in population monitoring. This article is protected by copyright. All rights reserved.