Enhancement, Extraction and Analysis of Curvilinear Structure in Biomedical Images

An important subeld of image processing is the analysis and detection of curvilinear structures. A wide range of real-life applications rely on its usage for analysing biomedical images and these could be categorised as enhancement, segmentation, skeletonisation and ridge detection; regression and classication. Understanding the nature of the relationship between the aforementioned applications can lead to hybrid techniques never investigated in the literature before, enriching and expanding our knowledge. To our knowledge, such attempts have not yet been reported in the literature. This thesis has been carried out in search for new computerised methods to improve the detection and analysis of biomedical images.