A bootstrapping algorithm for learning linear models of object classes
- 1 June 1997
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
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.Keywords
This publication has 12 references indexed in Scilit:
- A unified approach to coding and interpreting face imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Alignment by maximization of mutual informationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Image Representations for Visual LearningScience, 1996
- 3D position, attitude and shape input using video tracking of hands and lipsPublished by Association for Computing Machinery (ACM) ,1994
- Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and SymmetriesPublished by Defense Technical Information Center (DTIC) ,1992
- Active Shape Models - 'smart snakes'Published by British Machine Vision Association and Society for Pattern Recognition ,1992
- A Generic System for Image Interpretation Using Flexible TemplatesPublished by British Machine Vision Association and Society for Pattern Recognition ,1992
- Recognition by linear combinations of modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- A system of analyzing and synthesizing facial imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Application of the Karhunen-Loeve procedure for the characterization of human facesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990