Abstrait

A NOVEL APPROACH TO GRADIENT EDGE DETECTION

Naorah Saad Al Harbi. Supervisor: Dr. Msater Prince Syed

Edges characterize boundaries and are therefore a problem of fundamental importance in image processing. Image Edge detection significantly reduces the amount of data and filters out useless information, while preserving the important structural properties in an image. The aim of our proposed method is to obtain thin edges so that the result is more suitable for further applications such as boundary detection image segmentation, object identification and so on. In this study, we propose a new two approaches based on gradient edge detection method. We only focus on traditional Canny Edge Detection in our methods and introduce convolution masks to obtain better edges. The proposed project is implemented using MATLAB 7.0.