Open AccessArtifacts Removal in Melanoma Using Various Preprocessing Filters
Author(s) -
R. Ramya Ravi,
Raj Kumar,
N. Shanila
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.27.17664
Subject(s) - preprocessor , artificial intelligence , median filter , computer science , noise (video) , pattern recognition (psychology) , wiener filter , computer vision , segmentation , filter (signal processing) , gaussian filter , gaussian noise , gaussian , noise reduction , image processing , image (mathematics) , chemistry , computational chemistry
Preprocessing plays an important role for artifacts removal and quality improvement. In this paper, noise and hair removal techniques for melanoma in dermoscopic images is proposed. Here the performance of four filters for noise removal namely Wiener, Mean, Median, and Gaussian Filters are studied. Of these the performance of Gaussian filter is proved to be best. In addition Morphological Filter is used for hair removal. The noise and hair removal filtering processes help to enhance the quality of the image and thus aid to improve the segmentation results. The performance of the preprocessing filters is compared using quantifying parameters like MSE, PSNR, and SSIM.