Litcius/Paper detail

Automated Identification of Individuals in Wildlife Population Using Siamese Neural Networks

Nkosikhona Dlamini, Terence L. van Zyl

202011 citationsDOI

Abstract

Similarity learning coupled with semi-hard pair mining has been applied successfully in human individual identification using images of faces. This approach is coupled with innovative training data sampling techniques, trained to optimise a ranking loss function, aimed at increasing model performance at a minimal additional computational cost. We demonstrate that similarity learning coupled with semi-hard negative pair mining, minimising a triplet loss function, can be applied in the identification of wild animals: Lions, Zebra, Nyalas, and Chimpanzees. There is varying performance depending on the dataset being studied and the network architecture. There is improved performance on models trained using semi-hard triplets on the Chimpanzees hold out test-set data; VGG-19 achieves a 96% accuracy and DenseNet-201 90.1% accuracy. Mean average precision was measured for the different network architectures, varying performances were obtained depending on dataset and network depth.

Topics & Concepts

Computer scienceRanking (information retrieval)Artificial intelligenceSimilarity (geometry)Artificial neural networkIdentification (biology)Machine learningSampling (signal processing)PopulationPattern recognition (psychology)Data miningSet (abstract data type)Function (biology)Image (mathematics)Computer visionDemographyFilter (signal processing)BotanyEvolutionary biologyBiologySociologyProgramming languageFace recognition and analysisVideo Surveillance and Tracking MethodsAnimal Vocal Communication and Behavior