期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2017
卷号：6
期号：1
页码：1339
DOI：10.15680/IJIRSET.2017.0601151
出版社：S&S Publications
摘要：Tele-dermatology is becoming an important tool for early skin cancer detection in public health, butlow-cost cameras tend to cause image blurring, which affect diagnosis quality. Obtaining cost-effective images withdiagnosis quality is a current challenge, and this paper proposes a noise removal algorithm for color images corruptedby additive Gaussian noise and a robust open close sequence filter based on mathematical morphology for highprobability additive Gaussian noise removal is given. First, an additive Gaussian noise detector using mathematicalresidues is to identify pixels that are contaminated by the additive Gaussian noise. Then the image is restored usingspecialized open-close sequence algorithms that apply only to the noisy pixels. But the color blocks that degrade thequality of the image will be recovered by a block smart erase method. This algorithm can be applied to highly corruptedimages. Mathematical morphology is a nonlinear image processing methodology that is based on the application oflattice theory to spatial structures. In color images, algorithms are developed for boundary extraction via amorphological gradient operation and for region partitioning based on texture content. Mathematical morphologicaloperations are useful in smoothing and sharpening, which often are useful as per or post processing steps.
