An automated mean-shift based segmentation for pigmented skin lesions
Zhao, L., Sun, J., Smith, M., Smith, L. and Warr, R. (2010) An automated mean-shift based segmentation for pigmented skin lesions. In: 2010 Proceedings of Medical Image Understanding and Analysis (MIUA), Warwick, July 2010.
Full text not available from this repository
This paper presents an unsupervised segmentation scheme to isolate pigmented skin lesion from surrounding normal skin. An adaptive mean-shift algorithm combined with maximal similarity based region merging is applied with a colour-spatial feature space to improve the efficiency and robustness of the segmentation approach. Upon comparison, the proposed method demonstrates good performance in achieving an automatic segmentation on various real skin data collected by ourselves and those downloaded from public dataset.