Fast Algorithms for Fitting Active Appearance Models to Unconstrained Images

Georgios Tzimiropoulos, Maja Pantic

    Research output: Contribution to journalArticleAcademicpeer-review

    30 Citations (Scopus)
    100 Downloads (Pure)


    Fitting algorithms for Active Appearance Models (AAMs) are usually considered to be robust but slow or fast but less able to generalize well to unseen variations. In this paper, we look into AAM fitting algorithms and make the following orthogonal contributions: We present a simple “project-out‿ optimization framework that unifies and revises the most well-known optimization problems and solutions in AAMs. Based on this framework, we describe robust simultaneous AAM fitting algorithms the complexity of which is not prohibitive for current systems. We then go on one step further and propose a new approximate project-out AAM fitting algorithm which we coin Extended Project-Out Inverse Compositional (E-POIC). In contrast to current algorithms, E-POIC is both efficient and robust. Next, we describe a part-based AAM employing a translational motion model, which results in superior fitting and convergence properties. We also show that the proposed AAMs, when trained “in-the-wild‿ using SIFT descriptors, perform surprisingly well even for the case of unseen unconstrained images. Via a number of experiments on unconstrained human and animal face databases, we show that our combined contributions largely bridge the gap between exact and current approximate methods for AAM fitting and perform comparably with state-of-the-art face alignment systems.
    Original languageEnglish
    Pages (from-to)17-33
    Number of pages17
    JournalInternational journal of computer vision
    Issue number1
    Publication statusPublished - 24 Sept 2016


    • HMI-HF: Human Factors
    • EC Grant Agreement nr.: FP7/645094
    • EWI-27574
    • IR-103789
    • In-the-wild
    • Face alignment
    • Active Appearance Models
    • n/a OA procedure


    Dive into the research topics of 'Fast Algorithms for Fitting Active Appearance Models to Unconstrained Images'. Together they form a unique fingerprint.

    Cite this