PDF version of this entire document
A key step in building a combined appearance model is that of establishing a dense correspondence across the set of training images. In practice, this is often achieved by marking up the training set manually with a set of key landmarks and interpolating between them. Recently there has been considerable interest in automating this process. One approach is to use non-rigid registration methods, developed for use in medical image analysis, to align the images by optimising a measure of image similarity [11,14]. An alternative approach refines an initial estimate of correspondence so as to code the training set of images as efficiently as possible [5]. Twining et al have recently described an approach based on optimising the total description length of the training set, using the model [16].
In section 4.1 we validate our approach to model evaluation by deliberately perturbing the correspondences in models built using manual annotation to establish correspondence. In section 4.3 we use our method of evaluation to compare models built using non-rigid registration [11,14] and the minimum description length groupwise registration approach of Twining et al [16].