Biological object representation for identification

This thesis is concerned with the problem of how to represent a biological object for computerised identification. Images of biological objects have been generally characterised by shapes and colour patterns in the biology domain and the pattern recognition domain. Thus, it is necessary to represent the biological object using descriptors for the shape and the colour pattern. The basic requirements which a description method should satisfy are those such as invariance of scale, location and orientation of an object; direct involvement in the identification stage; easy assessment of results. The major task to deal with in this thesis was to develop a shape-description method and a colour-pattern description method which could accommodate all of the basic requirements and could be generally applied in both domains. In the colour-pattern description stage, an important task was to segment a colour image into meaningful segments. The most efficient method for this task is to apply Cluster Analysis. In the image analysis and pattern recognition domains, the majority of approaches to this method have been constrained by the problem of dealing with inordinate amounts of data, i.e. a large number of pixels of an image. In order to directly apply Cluster Analysis to the colour image segmentation, data structure, the Auxiliary Means is developed in this thesis.