Simple object detection within the Menpo project environment. We do not attempt to implement novel techniques, but instead wrap existing projects so that they integrate nicely with Menpo. At the moment the current libraries are wrapped:

• dlib (Boost Software License - Version 1.0)
  Frontal face detection, arbitrary dlib models and training code is all wrapped.
• opencv (BSD) Frontal face detection, profile face detection, eye detection and arbitrary OpenCV cascade files (via loading from disk) are all provided.
• pico (Academic Only) Frontal face detection and arbitrary pico models are provided. Loading arbitrary Pico models is likely to be very difficult, however.
• ffld2 (GNU AGPL) Frontal face detection using the DPM Baseline model provided by Mathias et. al.. Training code is also wrapped, but requires explicit negative samples.

This project aims to wrap existing object detection libraries for easy integration with Menpo. The core project is under a BSD license, but since other projects are wrapped, they may not be compatible with this BSD license. Therefore, we urge caution be taken when interacting with this library for non-academic purposes.

Here in the Menpo team, we are firm believers in making installation as simple as possible. Unfortunately, we are a complex project that relies on satisfying a number of complex 3rd party library dependencies. The default Python packing environment does not make this an easy task. Therefore, we evangelise the use of the conda ecosystem, provided by Anaconda. In order to make things as simple as possible, we suggest that you use conda too! To try and persuade you, go to the Menpo website to find installation instructions for all major platforms.

If you want to try pip installing this package, note that you will need to satisfy the dependencies as specified in the meta.yaml BEFORE install.