TY - JOUR

T1 - Recognition of skin lesions from image

AU - Гориховский, Вячеслав Игоревич

AU - Ледовских, Михаил Андреевич

PY - 2023

Y1 - 2023

N2 - The growing number of skin cancer patients has highlighted the need for diagnostic expert systems to help detect lesions with high accuracy. The detection of dangerous diseases associated with skin lesions, especially malignant neoplasms, requires the detection of pigmented skin lesions. Methods of image recognition and computerized classification capabilities can improve the accuracy of skin cancer detection. In this paper, an approach based on leverage algorithm has been proposed. Statistical analysis based on feature acquisition from image is used to optimize the lightweight classification methods. Numerical experiments have shown the high efficiency of the approach, and the accuracy is comparable to the use of deep learning neural networks.

AB - The growing number of skin cancer patients has highlighted the need for diagnostic expert systems to help detect lesions with high accuracy. The detection of dangerous diseases associated with skin lesions, especially malignant neoplasms, requires the detection of pigmented skin lesions. Methods of image recognition and computerized classification capabilities can improve the accuracy of skin cancer detection. In this paper, an approach based on leverage algorithm has been proposed. Statistical analysis based on feature acquisition from image is used to optimize the lightweight classification methods. Numerical experiments have shown the high efficiency of the approach, and the accuracy is comparable to the use of deep learning neural networks.

M3 - Article

JO - Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika)

JF - Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika)

SN - 0027-1349

ER -