Transforming crocodile traceability: Deep metric learning for identifying Siamese crocodiles

Abstract

This study introduces a novel method for identifying individual Siamese crocodiles (Crocodylus siamensis), which is a crucial requirement for conservation and sustainable industry practices. Although deep metric learning (DML) has improved identification model robustness and reduced dependency on large datasets, comprehensive field studies and long-term deployments are lacking. To address this, DML combined with convolutional neural network (CNN) was applied for enhancing accuracy using a limited and imbalanced number of images per class and distinguishing dissimilar scale patterns of the head and ventral regions. Individual crocodiles were identified using the k-nearest neighbor (KNN) and support vector machine (SVM) classifiers based on the extracted features. Data were collected from 30 individuals on a crocodile farm using photographs taken over two consecutive years. Two identification types, Type 1, based on a model trained on images collected over two years; and Type 2, based on a model trained exclusively on images from the first year, were implemented. Type 1 identification, which used a CNN combined with the KNN and SVM classifiers, exhibited an accuracy exceeding 99.75 and 92.93% for the ventral and head regions, respectively. Type 2 identification exhibited a reduced accuracy because of a comparatively smaller amount of learning information; the proposed CNN achieved 83.99% accuracy for ventral identification and 67.14 and 65.61% for head identification with KNN and SVM, respectively. This study underscores the efficacy of DML and CNN for handling small, imbalanced datasets in identifying individual crocodiles, and has significant implications for traceability and conservation initiatives in the crocodile industry.