PawPrint: Whose Footprints Are These? Identifying Animal Individuals by Their Footprints

TL;DR

This paper introduces PawPrint and PawPrint+ datasets for identifying individual animals by their footprints, evaluating deep learning and classical methods to improve non-invasive pet identification and conservation.

Contribution

It provides the first public datasets for footprint-based animal identification and benchmarks various methods, highlighting their strengths and limitations.

Findings

Deep neural networks outperform classical features on complex substrates.

Combining global and local features improves identification reliability.

Footprint-based identification offers a non-invasive alternative to traditional methods.

Abstract

In the United States, as of 2023, pet ownership has reached 66% of households and continues to rise annually. This trend underscores the critical need for effective pet identification and monitoring methods, particularly as nearly 10 million cats and dogs are reported stolen or lost each year. However, traditional methods for finding lost animals like GPS tags or ID photos have limitations-they can be removed, face signal issues, and depend on someone finding and reporting the pet. To address these limitations, we introduce PawPrint and PawPrint+, the first publicly available datasets focused on individual-level footprint identification for dogs and cats. Through comprehensive benchmarking of both modern deep neural networks (e.g., CNN, Transformers) and classical local features, we observe varying advantages and drawbacks depending on substrate complexity and data availability. These insights suggest future directions for combining learned global representations with local descriptors to enhance reliability across diverse, real-world conditions. As this approach provides a non-invasive alternative to traditional ID tags, we anticipate promising applications in ethical pet management and wildlife conservation efforts.