An improved corner point detection using extreme value of Susan method for measuring a displacement

This paper proposes the corner point detection algorithm which uses extreme value from gray level image. There are various methods to detect corner point. Corner point includes information about the length and shape of model. Preprocessing step is required to detect corner point. First, the model image is converted to gray-level image. After removing noise from converted image, edge lines are detected by edge detection algorithm. Existing SUSAN algorithm detects edge line by using area, but also detects wrong corner points. But proposed extreme value method only detects corner point which belongs to the defined area, so detection ratio can be increased. Proposed method can be used to detect model´s exact displacement or to perform 3-D reconstruction.