FishNet: A Unified Embedding for Salmon Recognition

TL;DR

FishNet is a deep learning model designed to identify individual salmon from images, offering a non-invasive, efficient alternative to traditional tagging methods, with high accuracy demonstrated on a custom dataset.

Contribution

The paper introduces FishNet, a novel deep learning architecture for salmon identification that achieves high accuracy using small neural networks, reducing the need for physical tagging.

Findings

FishNet achieves a 96% true positive rate.

False positive rate is reduced to 1%.

Effective with relatively small neural network models.

Abstract

Identifying individual salmon can be very beneficial for the aquaculture industry as it enables monitoring and analyzing fish behavior and welfare. For aquaculture researchers identifying individual salmon is imperative to their research. The current methods of individual salmon tagging and tracking rely on physical interaction with the fish. This process is inefficient and can cause physical harm and stress for the salmon. In this paper we propose FishNet, based on a deep learning technique that has been successfully used for identifying humans, to identify salmon.We create a dataset of labeled fish images and then test the performance of the FishNet architecture. Our experiments show that this architecture learns a useful representation based on images of salmon heads. Further, we show that good performance can be achieved with relatively small neural network models: FishNet achieves a false positive rate of 1\% and a true positive rate of 96\%.