Hierarchical Morphable Models

This paper presents a new technique for modelling object classes (such as faces) and matching the model to novel images from the object class. The technique can be used for a variety of image analysis applications including face recognition, object veri cation and facial expression analysis. The model, called a hierarchical morphable model, is \learned" from example images (partioned into components) and their correspondences. This is an extension to the work on morphable models described in previous papers ( 6], 5], 12]). Hierarchical morphable models are shown to nd good matches to novel face images and are also robust to partial occlusion.

• Type: Conference
• Year: 1998
• Where: CVPR
• Authors: Michael J. Jones, Tomaso Poggio
• Keywords: Computer Vision, CVPR 1998, Facial Expression Analysis, Hierarchical Morphable Model, Hierarchical Morphable Models, Object Class, Object Veri Cation