Example Based Image Processing

This thesis is concerned with example based image processing. Example based image processing is a general term for any class of image processing operation where the manipulation and analysis of the image in question is guided by some set of example images. This thesis focuses on two applications, texture synthesis and image segmentation, in which example based image processing is proposed. Given an example texture, the goal of a successful texture synthesis algorithm is to generate new texture which is perceptually similar to the sample texture. One of the main challenges in this process is the modelling of the example texture. Previous work has shown that those algorithms based on implicit modelling are more successful than those based on the more rigid explicit models. Based on this observation a new texture synthesis algorithm is developed which combines the strength of the implicit modelling technique with wavelet based image analysis. The Dual-Tree Complex Wavelet Transform used in this work has associated with it good directional selectivity and shift invariance. Both of these properties make it well suited for texture analysis. The new synthesis algorithm exploits this by performing synthesis in the wavelet domain. The result is a scale independent efficient process which is robust enough to work for a wide range of textures. Building on the strength of this texture synthesis algorithm, the focus then turns to image segmentation. The goal of any image segmentation process is to assign to each pixel in an observed image a label indicating to which region or class that pixel belongs. Fully automated or unsupervised segmentation is an ill-posed problem and so in order to constrain the solution an example image set whose content is similar to that to be segmented is given as an input. This example image set has been segmented a priori and so can be used to guide the segmentation process. This type of semi-automated segmentation can be viewed as the interleaving of segmentation and object recognition. As part of this work on example based processing, a new segmentation algorithm has been developed. This example based segmentation algorithm is based on the same implicit modelling technique as the synthesis process. However, in order to regularise the solution, implicit modelling of the observed image is combined with an explicit modelling of the label field. The Bayesian framework provides a natural expression for such parallel modelling techniques. The new algorithm is presented under this framework and some sample segmentation results are given.