A computational approach for detecting pigmented skin lesions in macroscopic images
作者：
Highlights：
• A discussion about the state of the art of computer-aided diagnosis methods.
• A new approach for identifying pigmented skin lesion features and types.
• The approach is based on asymmetry, border, colour and texture properties.
• It combines an anisotropic diffusion filter, an active contour model and an SVM.
• Experiments focused on skin lesion segmentation and classification.
摘要
•A discussion about the state of the art of computer-aided diagnosis methods.•A new approach for identifying pigmented skin lesion features and types.•The approach is based on asymmetry, border, colour and texture properties.•It combines an anisotropic diffusion filter, an active contour model and an SVM.•Experiments focused on skin lesion segmentation and classification.
论文关键词：Image pre-processing,Image segmentation,Image classification,Anisotropic diffusion filter,Active contour model without edges,Support vector machine
论文评审过程：Received 25 January 2016, Revised 10 May 2016, Available online 12 May 2016, Version of Record 24 May 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.05.017
