Please use this identifier to cite or link to this item:
|Title:||Investigation of image processing algoriths for medical applications||Authors:||Aung, Htet Myet Chel||Keywords:||DRNTU::Engineering::Electrical and electronic engineering||Issue Date:||2017||Abstract:||Medical imaging is a crucial technique of digital imaging to help human’s life. Medical imaging is practically taking images of human’s organs, body parts, tissues and so on. However, any electronic device whether analog or digital device can be affected from unwanted signal known as noise. Noise is an undesired signal which can contaminate any image. It is very important to remove noises in digital image processing. The ideal noise removal process is that it can remove all the affected noises and preserve the image’s edges. Noise reduction is a vital process in medical imaging such as CT scan, MRI scan to avoid the improper diagnosis. The challenge in this noise reduction of medical imaging is that the noise removal process must provide an effective process and be able to do analysis on the noisy images. The outcome of the analysis advances to provide information of extracting, measuring and interpreting the medical image data. It is very helpful to the medical practitioners to achieve the better insightful approach to the diagnosis and treatment. There are various noise removal algorithms for image processing which are developed fully ranged from traditional ways to advanced methods. In this report, noise removal using filters are the main focus. In order to indicate the rightful and appropriate filter that can provide an optimal outcome, comparing the performance of the different noise removal filters is significantly important for any particular medial image. In this report, 4 different types of filters which are Median filter, Gaussian smoothing, Wiener filter and Wavelet filter are applied to remove noises from 3 types of medical images (FMRI, X-Ray and Cancer images. Those medical images are added with 4 different types of noises. Moreover, two performance metrics such as Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR) will be assessed in order to obtain the most efficient filter by comparing and analyzing the performance metrics data.||URI:||http://hdl.handle.net/10356/72065||Rights:||Nanyang Technological University||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Student Reports (FYP/IA/PA/PI)|
Updated on May 6, 2021
Updated on May 6, 2021
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.