|
IMAGE PROCESSING, PATTERN RECOGNITION
Neural network classification system for pigmented skin neoplasms with preliminary hair removal in photographs
P. A. Lyakhov, U. A. Lyakhova North-Caucasus Federal University
Abstract:
The article proposes a neural network classification system for pigmented skin neoplasms with a preliminary processing stage to remove hair from the images. The main difference of the proposed system is the use of the stage of preliminary image processing to identify the location of the hair and their further removal. This stage allows you to prepare dermatoscopic images for further analysis in order to carry out automated classification and diagnosis of pigmented skin lesions. Modeling was carried out using the MatLAB R2020b software package on clinical dermatoscopic images from the international open archive ISIC Melanoma Project. The proposed system made it possible to increase the recognition accuracy of pigmented skin lesion images in 10 diagnostically important categories up to 80.81
Keywords:
digital image processing, convolutional neural networks, dermatoscopic images, pigmented skin lesions, hair removal, melanoma
Received: 18.01.2021 Accepted: 15.03.2021
Citation:
P. A. Lyakhov, U. A. Lyakhova, “Neural network classification system for pigmented skin neoplasms with preliminary hair removal in photographs”, Computer Optics, 45:5 (2021), 728–735
Linking options:
https://www.mathnet.ru/eng/co961 https://www.mathnet.ru/eng/co/v45/i5/p728
|
Statistics & downloads: |
Abstract page: | 21 | References: | 12 |
|