Image investigation using higher moment statistics and edge detection for recognizing abnormal skin

This paper discusses the recognition of skin abnormalities by investigating the images using high-level statistics and edge detection. Six images of skin diseases were analyzed using several statistical parameters, including high-level moments such as skewness and kurtosis. In comparison, some images from other categories such as animal, architecture, art, vehicle, food, people, and scenery have been analyzed as well. The results were compared to skin disease images. It is expected that the general pattern of statistical parameters can distinguish skin images against images from other categories. MatLab is used as a medium to calculate the values of statistical parameters. The mean and median of the skin disease image are much larger. Meanwhile, the standard deviation is the smallest compared to other categorical images. Almost all the analyzed images close to symmetry. Nearly all images category are distributed more leaning to the left, except for the images of the art category, which is slightly more leaning to the right. Moreover, the edge detection process has been done using the Sobel algorithm. The result, however, cannot clearly distinguish a skin's abnormality. This difficulty is because of the lack of accuracy in selection the intensity.