Advances in active appearance models
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 137-142 vol.1
Abstract
This paper presents advances in the construction and use of Active Appearance Models (AAMs) for image interpretation. AAMs are photo-realistic generative models of object appearance that can be used to rapidly locate deformable objects in images. We extend the AAM method to include coloured texture and present an enhanced search algorithm with the ability to locate partially occluded objects. Previously, AAMs have been limited by the need for good manual initialisation. In this paper, we describe a hierarchical search algorithm that overcomes this drawback. The extended AAM method provides a complete, unified scheme for model based image interpretation. We demonstrate the application of the scheme to the task of locating faces in images.Keywords
This publication has 8 references indexed in Scilit:
- Statistical models of face images — improving specificityImage and Vision Computing, 1998
- Interpreting face images using active appearance models1998
- Face recognition using active appearance models1998
- Probabilistic visual learning for object representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Statistical grey-level models for object location and identificationImage and Vision Computing, 1996
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995
- View-based and modular eigenspaces for face recognition1994
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991