Multispectral skin patterns analysis using fractal methods

作者：

Highlights：

• A solution of skin cancer pattern recognition using fractal methods on multispectral images is proposed.

• Lacunarity and box dimension is used to get the pattern characteristic.

• Multiple image binarization methods are tested together with different classification methods.

• Proposed solution shows that fractal methods can be combined with binarization methods for some skin cancer patterns.

摘要

•A solution of skin cancer pattern recognition using fractal methods on multispectral images is proposed.•Lacunarity and box dimension is used to get the pattern characteristic.•Multiple image binarization methods are tested together with different classification methods.•Proposed solution shows that fractal methods can be combined with binarization methods for some skin cancer patterns.

论文关键词：Medical imaging,Fractal analysis,Malignant melanoma,Spectrophotometric,Skin images,Dermoscopy,Support vector machine,Neural networks,Image binarization,SIAscope,Fractals,Fractal dimension,Box dimension,Lacunarity,Multilevel images,Multi-layered images,Skin cancer,Skin lesions

论文评审过程：Received 24 September 2016, Revised 4 July 2017, Accepted 10 July 2017, Available online 12 July 2017, Version of Record 18 July 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.07.011