A bootstrapping algorithm for learning linear models of object classes
Thomas Vetter, Michael Jones, Tomaso Poggio · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2002
Flexible models of object classes, based on linear combinations of prototypical images, are capable of matching novel images of the same class and have been shown to be a powerful tool to solve several fundamental vision tasks such as recognition, synthesis and correspondence. The key problem in creating a specific flexible model is the computation of pixelwise correspondence between the prototypes, a task done until now in a semiautomatic way. In this paper we describe an algorithm that automatically bootstraps the correspondence between the prototypes. The algorithm -which can be used for 2D images as well as for 3D models-is shown to synthesize successfully a flexible model of frontal face images and a flexible model of handwritten digits.
Cited by 122 works. doi:10.1109/cvpr.1997.609295 Open-access PDF
Authors
References
- Application of the Karhunen-Loeve procedure for the characterization of human faces
- Recognition by linear combinations of models
- Alignment by maximization of mutual information
- Image Representations for Visual Learning
- Example Based Image Analysis and Synthesis
- Active Shape Models — ‘Smart Snakes’
- Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetries
- A unified approach to coding and interpreting face images
- A Generic System for Image Interpretation Using Flexible Templates
- Active Shape Models - 'smart snakes'