Development of Edge Detection Technique Using Mathematics Methods for MRI Images

Abstract

Edge detection in medical image is an important task for object recognition of the human organs, and it is an essential pre-processing step in medical image segmentation and 3D reconstruction. Successful results of image analysis extremely depend on edge detection. Up to now many edge detection methods have been developed. But, they are sensitive to noise. This research discusses eight edge detection techniques in general, proposing Mathematics Edge Technique Filtering (METF)as a better technique. The mentioned technique goes through several steps, Starting with sharpening the image and separate it from the image, the filters will be applied to the resulting images. ( wavelet filter and the bilateral filter) which were chosen based on a comparison with other filters applied MRI images after adding Gaussian noise to it, finally Graphical User Interface (GUI) was created with multiple options to edit images with different buttons offering variety of options, all what mentioned will be explained thoroughly on this thesis.Edge detection helps in optimizing network bandwidth and it is needed to keep track of data flowing in and out of the network. It helps to extract useful features for pattern recognition. Experiments results reveal that The METF technique is the best technique for our goals, were it had lower MSE and better SNR and PSNR.