The Menpo Project


The Python framework for deformable modelling 
Go to



The Menpo Project is a set of Python frameworks and associated tooling that provides end-to-end solution for 2D and 3D deformable modeling. The project includes training and fitting code for various state-of-the-art methods such as:

  • Active Appearance Model (AAM)
  • Supervised Descent Method (SDM)
  • Ensemble of Regression Trees (ERT) (powered by dlib)
  • Constrained Local Model (CLM)
  • Active Shape Model (ASM)
  • Active Pictorial Structures (APS)
  • Lucas-Kanade (LK) and Active Template Model (ATM)

The Menpo Project also provides:

  • a web-based tool for annotation of bulk data for model training live at 
  • a command line tool for landmark localisation with state-of-the-art pre-trained models
  • generic object detection in terms of a bounding box
  • an elegant standard library with simple dependencies, useful for many areas of computer vision
  • sophisticated visualization with interactive IPython widgets



The Menpo Team

Joan Alabort-i-Medina
Epameinondas Antonakos
James Booth
Patrick Snape
Stefanos Zaferiiou



If you're using the Menpo Project, please cite:

J. Alabort-i-Medina, E. Antonakos, J. Booth, P. Snape, S. Zafeiriou. "Menpo: A Comprehensive Platform for Parametric Image Alignment and Visual Deformable Models", In Proceedings of the ACM International Conference on Multimedia, MM ’14, New York, NY, USA, pp. 679-682, 2014. ACM.