Small Animal Species Recognition with Deep Convolutional Neural Network from Ecological Camera Trap Image.
This repository contains the experiment files of masters thesis research work which is, wild animal species recognition (snake, lizard and toad) by image classification using computer vision algorithms and machine learning techniques. The goal is to train and validate a convolutional neural network (CNN) architecture that will classify three herpetofauna species: snake, lizard, and toad from the camera trap samples.
In our work, we trained, and tested machine learning models to classify three animal groups (snakes, lizards, and toads) from camera trap images. We experimented with two pre-trained model; VGG16 and Resnet50, and a self-trained convolutional neural network (CNN-1) with varying CNN layers and augmentation parameters.
Camera trap dataset: Field dataset collected from Texas (the dataset samples are not publicly available.).
Binary Multiclass