Revealing the Unknown: Real-Time Recognition of Galápagos Snake Species Using Deep Learning
Open Access
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
This publication has 16 references indexed in Scilit:
- DOG: A new background removal for object recognition from imagesNeurocomputing, 2019
- Origin and hidden diversity within the poorly known Galápagos snake radiation (Serpentes: Dipsadidae)Systematics and Biodiversity, 2018
- The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Automatic identification of species with neural networksPeerJ, 2014
- Pseudalsophis hoodensis: Cisneros-Heredia, D.F. & Márquez, C.2014
- Pseudalsophis dorsalis: Márquez, C., Cisneros-Heredia, D.F. & Yánez-Muñoz, M.2014
- Pseudalsophis occidentalis: Márquez, C. & Yánez-Muñoz, M.2014
- Pseudalsophis biserialis: Márquez, C., Cisneros-Heredia, D.F. & Yánez-Muñoz, M.2014
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989