Efficient and effective contour-based corner detection methods for image matching

This thesis aims to find the location of the corners in an image and represent them in an image matching application. The main challenge is to find the correspondences between two images under different transformations. The role of the edge detectors for detecting corners is also analysed. A method for estimating the interest region around the corner location is developed to represent the corner in an image matching framework. The research can be useful in a wide range of computer vision application such as image matching and object recognition.