- Face models
- Facial appearance models
- Evaluation and perturbation
- Results

- Model Evaluation
- Number of modes (in brain)
- Future paths

- Summary

- The background is omitted from all training images

- The training set becomes easier to compare

- Models can then be built from a set

- Perturbation of the landmarks affects model quality

Perturbation with `Sigma=3`

- Some of the synthetic images from the model:

- Images still need to be re-scaled to overlap

- Experiments investigate landmark noise
- Sigma ranging from 0 to 5 inclusive
- Distance measures based on 1000 syntheses
- Specificity was expected to rise as a function of sigma

- Generalisability

- Specificity

- Example distance matrix

- We investigate the effect of the number of modes
- Modes which are used to evaluate a model
- Synthetic data is generated from the appearance model
- A finite number of principal modes is selected

- Investigate the effect of the number of modes
- Referring to modes which are used to evaluate a model
- Synthetic data is generated from the appearance model
- A finite number of principal modes is selected

- If all modes are altered in generation simultaneously...
- ...distance measures become less meaningful
- Hence more synthetic data is required

- 3 models were used to learn the effect of the number of modes:
- Model I: built from the results of pair-wise registration
- Model II: built using the initialisation algorithm
- Model III: built using group-wise registration

- Generalisability

- Specificity

- Generalisability on a steady decrease
- Group-wise outperforms pair-wise regardless of number of modes
- Complex methods surpass the basic initialisation algorithm
- Specificity of group-wise almost independent of number of modes
- Specificity of pair-wise degrades approximately linearly

- Normalisation in evaluation:
- Set size
- Other factors

- Extension of training set using synthetic data
- Larger experiments

- Deadline is mid-April for both
*Wiki*:- A Wiki can be set up
- Used for collaborated editing of content
- Web-based and database driven
- Easy rollback, backup, '
`diff`

'

- Pair-wise versus group-wise
- Automatic model-building
- Model evaluation
- Proof of group-wise being most desirable

- Explanation of the algorithm/s
- Hopefully tetrahedronisation
- If 3-D results are available:
- Pick a slice from the volume to evaluate the 3-D model
- This will provide an approximation

- Initialisation algorithm in 3-D

- Explanation of the methods:
- Shuffle distance
- Normalisation, scaling issues
- Deriving Spec. and Gen. in relation to work on shape

- Sigma of noise versus Spec. and Gen.
- Spec. and Gen. versus the number of modes
- Spec. (maybe also Gen.) for different registration methods

- Show faces from the model
- Show noise being applied to face mark-up and the resulting model/s
- Experiments with noise - an explanation
- Specificity and Generalisability versus sigma

- Repeating the main points from the sections above
- Future work:
- Full 3-D (if not already done)
- Larger training set (possibility of creating pseudo-training data)
- Further investigation of registration methods
- Investigation of evaluation parameters