期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2019
卷号：10
期号：1
页码：90-98
DOI：10.14569/IJACSA.2019.0100111
出版社：Science and Information Society (SAI)
摘要：A prototype of skin cancer detection system for melanoma diagnoses in early stages is very important. In this paper, a novel technique is proposed for Skin malignant growth identification based on feature parameters, color shading histogram, to improve the diagnosis method by optimizing the ABCD formula. Features are extracted like Shape, Statistical, GLCM texture, Color, Wavelet transform, Texture. Once the features are extracted we found the most prominent features by assigning a rank. We have calculated parameters such as sensitivity, specificity, accuracy for checking the imperceptibility and robustness of the proposed approach. Also, Correlation analysis is made between traditional and proposed TDS equation using Karl Pearson’s method.
