Find file History
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
..
Failed to load latest commit information.
utils
README.md
Vagrantfile
id_aircraft_script_1.ipynb
jupyter_application_config.py
provision.sh
vmconfig-sample.yaml

README.md

Identify Aircraft Based On Limited Number Of Photos

This is an attempt to train a deep neural network to identify different models of commercial aircraft based on very few photos - without relying on any additional information (i.e., no EXIF data, no tags, etc.). The underlying technique can be used for other image classification tasks where we have a small training dataset.

Dataset

As of date, I have curated a dataset of 5920 photos of 39 different models of commercial aircraft (TSV, Web). They were obtained from the Yahoo Flickr Creative Commons (YFCC) dataset, Wikipedia and other sources.

Progress

  • In part 1, I train an image classifier (a convolutional neural network, aka CNN) to distinguish between photos of 4 different models of commercial aircraft. Validation accuracy 0.84-0.86, after 20 epochs. I use a VirtualBox VM with Keras and Theano installed - created using a Vagrant script (see repository).