Revealing the Unknown: Real-Time Recognition of Galápagos Snake Species Using Deep Learning

Anika Patel; Lisa Cheung; Nandini Khatod; Irina Matijosaitiene; Alejandro Arteaga; Joseph W Gilkey Jr

doi:10.3390/ani10050806

Revealing the Unknown: Real-Time Recognition of Galápagos Snake Species Using Deep Learning

Animals (Basel). 2020 May 6;10(5):806. doi: 10.3390/ani10050806.

Authors

Anika Patel¹, Lisa Cheung¹, Nandini Khatod¹, Irina Matijosaitiene^{1

2

3}, Alejandro Arteaga⁴, Joseph W Gilkey Jr¹

Affiliations

¹ Data Science Institute, Saint Peter's University, Jersey City, NJ 07306, USA.
² Institute of Environmental Engineering, Kaunas University of Technology, 44249 Kaunas, Lithuania.
³ Vilnius Gediminas Technical University, 10223 Vilnius, Lithuania.
⁴ Tropical Herping, Quito, Ecuador.

Abstract

Real-time identification of wildlife is an upcoming and promising tool for the preservation of wildlife. In this research project, we aimed to use object detection and image classification for the racer snakes of the Galápagos Islands, Ecuador. The final target of this project was to build an artificial intelligence (AI) platform, in terms of a web or mobile application, which would serve as a real-time decision making and supporting mechanism for the visitors and park rangers of the Galápagos Islands, to correctly identify a snake species from the user's uploaded image. Using the deep learning and machine learning algorithms and libraries, we modified and successfully implemented four region-based convolutional neural network (R-CNN) architectures (models for image classification): Inception V2, ResNet, MobileNet, and VGG16. Inception V2, ResNet and VGG16 reached an overall accuracy of 75%.

Keywords: Galápagos Islands; Pseudalsophis; artificial intelligence (AI) platform; deep learning; image classification; machine learning; racer snake; region-based convolutional neural network (R-CNN); snake species.