Right whale recognition using convolutional neural networks
This work addresses the problem of automated whale identification for conservation or research purposes, but it appears incremental as it applies existing CNN methods to a new dataset.
The study tackled the problem of recognizing individual right whales using convolutional neural networks, concluding that machine recognition is feasible but noting the difficulty of the task, though no concrete performance numbers were provided.
We studied the feasibility of recognizing individual right whales (Eubalaena glacialis) using convolutional neural networks. Prior studies have shown that CNNs can be used in wide range of classification and categorization tasks such as automated human face recognition. To test applicability of deep learning to whale recognition we have developed several models based on best practices from literature. Here, we describe the performance of the models. We conclude that machine recognition of whales is feasible and comment on the difficulty of the problem