Skip to main content

Research Repository

Advanced Search

An automated mean-shift based segmentation for pigmented skin lesions

Zhao, Liu; Sun, Jiuai; Smith, Melvyn; Smith, Lyndon; Warr, Robert

Authors

Liu Zhao

Jiuai Sun

Profile Image

Melvyn Smith Melvyn.Smith@uwe.ac.uk
Research Centre Director Vision Lab/Prof

Lyndon Smith Lyndon.Smith@uwe.ac.uk
Professor in Computer Simulation and Machine

Robert Warr



Abstract

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.

Citation

Zhao, L., Sun, J., Smith, M., Smith, L., & Warr, R. (2010, July). An automated mean-shift based segmentation for pigmented skin lesions. Paper presented at 2010 Proceedings of Medical Image Understanding and Analysis (MIUA), Warwick

Presentation Conference Type Conference Paper (unpublished)
Conference Name 2010 Proceedings of Medical Image Understanding and Analysis (MIUA)
Conference Location Warwick
Start Date Jul 1, 2010
End Date Jul 1, 2010
Publication Date Jul 1, 2010
Peer Reviewed Peer Reviewed
Public URL https://uwe-repository.worktribe.com/output/977893