Back Home: A Computer Vision Solution to Seashell Identification for Ecological Restoration

TL;DR

This paper presents BackHome19K, a large-scale image dataset and a real-time mobile-compatible computer vision system for identifying the origin of seashells to aid ecological restoration and combat illegal collection.

Contribution

It introduces the first large-scale seashell image dataset with coast labels and a lightweight, robust classifier pipeline for real-time provenance inference on mobile devices.

Findings

Achieved 86.3% balanced accuracy in classification.

Rejected 93% of out-of-domain objects with zero false negatives.

Processed 70,000 shells in under three seconds each as a deployed web app.

Abstract

Illegal souvenir collection strips an estimated five tonnes of seashells from Costa Rica's beaches each year. Yet, once these specimens are seized, their coastal origin -- Pacific or Caribbean -- cannot be verified easily due to the lack of information, preventing their return when confiscated by local authorities. To solve this issue, we introduce BackHome19K, the first large-scale image corpus (19,058 photographs, 516 species) annotated with coast-level labels, and propose a lightweight pipeline that infers provenance in real time on a mobile-grade CPU. A trained anomaly filter pre-screens uploads, increasing robustness to user-generated noise. On a held-out test set, the classifier attains 86.3% balanced accuracy, while the filter rejects 93% of 180 out-of-domain objects with zero false negatives. Deployed as a web application, the system has already processed 70,000 shells for wildlife officers in under three seconds per image, enabling confiscated specimens to be safely repatriated to their native ecosystems. The dataset is available at https://huggingface.co/datasets/FIFCO/BackHome19K