Active shape models - their training and application

    Research output: Contribution to journalArticlepeer-review

    45 Downloads (Pure)

    Abstract

    Model-based vision is firmly established as a robust approach to recognizing and locating known rigid objects in the presence of noise, clutter, and occlusion. It is more problematic to apply model-based methods to images of objects whose appearance can vary, though a number of approaches based on the use of flexible templates have been proposed. The problem with existing methods is that they sacrifice model specificity in order to accommodate variability, thereby compromising robustness during image interpretation. We argue that a model should only be able to deform in ways characteristic of the class of objects it represents. We describe a method for building models by learning patterns of variability from a training set of correctly annotated images. These models can be used for image search in an iterative refinement algorithm analogous to that employed by Active Contour Models (Snakes). The key difference is that our Active Shape Models can only deform to fit the data in ways consistent with the training set. We show several practical examples where we have built such models and used them to locate partially occluded objects in noisy, cluttered images.
    Original languageEnglish
    Pages (from-to)38-59
    Number of pages21
    JournalComputer Vision and Image Understanding
    Volume61
    Issue number1
    DOIs
    Publication statusPublished - Jan 1995

    Keywords

    • Journal

    Fingerprint

    Dive into the research topics of 'Active shape models - their training and application'. Together they form a unique fingerprint.

    Cite this