This paper presents a comparative study of four fractional order filters used for edge detection. The noise performance of these filters is analyzed upon the addition of random Gaussian noise, as well as the addition of salt and pepper noise. The peak signal to noise ratio (PSNR) of the detected images is numerically compared. The mean square error (MSE) of the detected images as well as the execution time are also adopted as evaluation methods for comparison. The visual comparison of the filters capability in medical image edge detection is presented, that can help in the diagnosis of Alzheimer disease (AD) through magnetic resonance imaging (MRI) images. © 2016 IEEE.
Ismail S.M., Radwan A.G., Madian A.H., Abu-Elyazeed M.F.
Edge detection; Fractional order mask; MRI; PSNR
2016 39th International Conference on Telecommunications and Signal Processing, TSP 2016, Art. No. 7760979, PP. 720 to 723, Doi: 10.1109/TSP.2016.7760979