Flow-guided hair removal for automated skin lesion identification.

Kang, D., Kim, S. and Park, S., 2018. Flow-guided hair removal for automated skin lesion identification. Multimedia Tools and Applications, 77 (8), 9897- 9908.

Full text available as:

[img] PDF
revised.pdf - Accepted Version
Restricted to Repository staff only until 25 January 2019.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

4MB

DOI: 10.1007/s11042-018-5672-7

Abstract

In this paper, we propose a method for removing hairs automatically from skin lesion images. To achieve this, we employ an edge-detection technique based on edge-tangent flow. To detect only hair-like structures, rather than contour boundaries, we propose a novel, specialized method for detecting hairs. Regardless of the personal characteristics of the hairs, hairy regions are detected because our method detects coherent thin lines of consistent width. We then restore the hairy regions detected by the proposed method by using the texture synthesis method. Our method restores the regions occluded by hairs with very few remarkable artifacts, because we utilize pixels that actually exist in the source image to restore the occluded areas by searching for the best matching pixels.

Item Type:Article
ISSN:1380-7501
Group:Faculty of Science & Technology
ID Code:30439
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:05 Mar 2018 09:33
Last Modified:14 May 2018 15:04

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -