부산대학교 도서관

Image processing is an active research area in which medical image processing is a highly challenging field. Medical imaging techniques are used to image the inner portion of human body for medical diagnosis. In this research work, retinal colour fundus images and MRI brain images noise level has been improved. Fundus Fluorescein Angiography (FFA) is the invasive based technique used to give high contrast retinal images but it used contrast injection and other side Magnetic Resonance Imaging (MRI) is a medical used to produce the high contrast image. The biomedical images are mostly suffered from the varied contrast and due to varied contrast, the details of images are not observed properly even after the image enhancement techniques because the presence of noise. In this research, The High-Resolution Fundus (HRF) database is used and it contained 36 images of two pairs (18 good quality images and 18 bad quality images). Oasis MRI brain image database is also used and it contained 30 images. Radial Basis Function (RBF) neural network gave highest PSNR improvement of 53% and 56% in HRF retinal images database and Oasis MRI Brain images database as compared to wavelet technique (18%,35%) and sub space method( 29%,9%). The optimal denoised method is one important step to get better result of contrast normalisation techniques and give accurate results to diagnose the disease progress.