Model for detecting globules in images of skin neoplasms

The article is devoted to digital image processing of skin neoplasms to detect significant structural elements in the diagnosis of melanoma – globules. A new processing model is proposed that allows stable selection of globules in different-contrast images without the need for manual adjustment of parameters. The results of the experiment confirming the adequacy of the model are presented. The globules recognition accuracy ranged from 81 to 89%, depending on the contrast of the original images. The experimental sample of images contained 2.868 globules.