Feature Extraction and Simplification from colour images based on Colour Image Segmentation and Skeletonization using the Quad-Edge data structure

Abstract

Region features in colour images are of interest in applications such as mapping, climatology, change detection, medicine, etc. This research work is an attempt to automate the process of extracting feature boundaries from colour images. This process is an attempt to eventually replace manual digitization process by computer assisted boundary detection and conversion to a vector layer in a spatial database. In colour images, various features can be distinguished based on their colour. The features thus extracted as object border can be stored as vector maps in a spatial database after labelling and editing. Here, we present a complete methodology of the boundary extraction and skeletonization process from colour imagery using a colour image segmentation algorithm, a crust extraction algorithm and our new skeleton extraction algorithm. We also present a prototype application for completely automated or semi-automated processing of (satellite) imagery and scanned maps with an application to coastline extraction. Other applications include extraction of fields, clear cuts, clouds, as well as heating or pollution monitoring and dense forest mapping among others.