Abstract
We describe a new method of matching statistical models of appearance to images. A set of model parameters control modes of shape and gray-level variation learned from a training set. We construct an efficient iterative matching algorithm by learning the relationship between perturbations in the model parameters and the induced image errors.
| Original language | English |
|---|---|
| Pages (from-to) | 681-685 |
| Number of pages | 4 |
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Volume | 23 |
| Issue number | 6 |
| DOIs | |
| Publication status | Published - Jun 2001 |
Keywords
- Appearance models
- Deformable templates
- Model matching
Fingerprint
Dive into the research topics of 'Active appearance models'. Together they form a unique fingerprint.Impacts
-
Active Shape and Appearance Models
Taylor, C. (Participant), Cootes, T. (Participant), Graham, J. (Participant), Twining, C. (Participant), Edwards, G. (Participant) & Davies, R. (Participant)
Impact: Technological, Economic, Health and wellbeing, Society and culture
-
Ground breaking computer vision research revolutionises digital entertainment
Taylor, C. (Participant), Cootes, T. (Participant), Twining, C. (Participant), Christinacce, D. (Participant), Babalola, K. (Participant) & Petrovic, V. (Participant)
Impact: Technological, Economic, Society and culture
-
Improving healthcare and animal welfare using statistical shape models
Cootes, T. (Participant), Taylor, C. (Participant), Twining, C. (Participant), Lindner, C. (Participant) & Davies, R. (Participant)
Impact: Health and wellbeing, Economic, Technological