Integral Curvature Representation and Matching Algorithms for Identification of Dolphins and Whales

TL;DR

This paper introduces an integral curvature-based representation for identifying individual dolphins and whales from fin images, demonstrating high accuracy in real-world datasets by matching unique edge patterns despite pose variations.

Contribution

The paper presents a novel integral curvature representation and two matching algorithms for cetacean identification, improving robustness to viewpoint changes and enabling effective ranking.

Findings

Achieved approximately 95% top-1 accuracy for bottlenose dolphins.

Achieved approximately 80% top-1 accuracy for humpback whales.

Demonstrated robustness of the method across real-world datasets.

Abstract

We address the problem of identifying individual cetaceans from images showing the trailing edge of their fins. Given the trailing edge from an unknown individual, we produce a ranking of known individuals from a database. The nicks and notches along the trailing edge define an individual's unique signature. We define a representation based on integral curvature that is robust to changes in viewpoint and pose, and captures the pattern of nicks and notches in a local neighborhood at multiple scales. We explore two ranking methods that use this representation. The first uses a dynamic programming time-warping algorithm to align two representations, and interprets the alignment cost as a measure of similarity. This algorithm also exploits learned spatial weights to downweight matches from regions of unstable curvature. The second interprets the representation as a feature descriptor. Feature keypoints are defined at the local extrema of the representation. Descriptors for the set of known individuals are stored in a tree structure, which allows us to perform queries given the descriptors from an unknown trailing edge. We evaluate the top-k accuracy on two real-world datasets to demonstrate the effectiveness of the curvature representation, achieving top-1 accuracy scores of approximately 95% and 80% for bottlenose dolphins and humpback whales, respectively.