Neural network classification system for pigmented skin neoplasms with preliminary hair removal in photographs

The article proposes a neural network classification system for pigmented skin neoplasms with preliminary processing stage to remove hair from the images. main difference of proposed is use image identify location and their further removal. This allows you prepare dermatoscopic images analysis in order carry out automated diagnosis lesions. Modeling was carried using MatLAB R2020b software package on clinical international open archive ISIC Melanoma Project. made it possible increase recognition accuracy lesion 10 diagnostically important categories up 80.81%. lesions by specialists will make diagnostic efficiency comparison methods visual diagnosis, also allow starting treatment at an earlier disease, which directly affects survival recovery rates patients.