@ARTICLE\{IMM2003-01918,
    author       = "M. B. Stegmann and B. K. Ersb{\o}ll and R. Larsen",
    title        = "{FAME} - A Flexible Appearance Modelling Environment",
    year         = "2003",
    keywords     = "Active Appearance Models, public domain training data and software, left ventricular segmentation, face segmentation",
    pages        = "1319-1331",
    journal      = "{IEEE} Transactions on Medical Imaging",
    volume       = "22",
    editor       = "Max A. Viergever",
    number       = "10",
    publisher    = "Institute of Electrical and Electronics Engineers (IEEE)",
    url          = "http://www2.compute.dtu.dk/pubdb/pubs/1918-full.html",
    abstract     = "Combined modelling of pixel intensities and shape has proven to be a very robust and widely applicable approach to interpret images. As such the Active Appearance Model (AAM) framework has been applied to a wide variety of problems within medical image analysis. This paper summarises {AAM} applications within medicine and describes a public domain implementation, namely the Flexible Appearance Modelling Environment (FAME). We give guidelines for the use of this research platform, and show that the optimisation techniques used renders it applicable to interactive medical applications. To increase performance and make models generalise better, we apply parallel analysis to obtain automatic and objective model truncation. Further, two different {AAM} training methods are compared along with a reference case study carried out on cross-sectional short-axis cardiac magnetic resonance images and face images. Source code and annotated data sets needed to reproduce the results are put in the public domain for further investigation."
}