TY - GEN
T1 - Using morphological operators and inpainting for hair removal in dermoscopic images
AU - Salido, Julie Ann A.
AU - Ruiz, Conrado
N1 - Funding Information:
The authors would also like to thank the anonymous referees for their valuable comments and helpful suggestions. Ms. Salido acknowledges the Commission on Higher Education, in collaboration with the De La Salle University (DLSU) and Aklan State University, for funding support through the Commission on Higher Education K-12 Transition (CHED K-12) Program. Dr. Ruiz is funded by the University Research Coordination Office (URCO) of DLSU.
Publisher Copyright:
© 2017 ACM.
PY - 2017/6/27
Y1 - 2017/6/27
N2 - The increasing incidence of melanoma has led to development of computer-aided diagnosis systems that classify dermoscopic images. A fundamental problem however during the pre-processing stage is the removal of artifacts such as hair. Hair strands introduce additional edges, which can be problematic when performing automatic skin lesion segmentation. This paper proposes a straightforward approach to automatic hair and consequently noise removal. The process starts with a median filter on each color space of RGB, a bottom hat filter, a binary conversion, a dilation and morphological opening, and then the removal of small connected pixels. The detected hair regions are then filled up using harmonic inpainting. Experiments were carried out on the PH2 datasets and compared to DullRazor. We also generated synthetic hair on skin images and measured the reconstruction quality using peak signal-to-noise ratio.
AB - The increasing incidence of melanoma has led to development of computer-aided diagnosis systems that classify dermoscopic images. A fundamental problem however during the pre-processing stage is the removal of artifacts such as hair. Hair strands introduce additional edges, which can be problematic when performing automatic skin lesion segmentation. This paper proposes a straightforward approach to automatic hair and consequently noise removal. The process starts with a median filter on each color space of RGB, a bottom hat filter, a binary conversion, a dilation and morphological opening, and then the removal of small connected pixels. The detected hair regions are then filled up using harmonic inpainting. Experiments were carried out on the PH2 datasets and compared to DullRazor. We also generated synthetic hair on skin images and measured the reconstruction quality using peak signal-to-noise ratio.
KW - Dermoscopy images
KW - Hair detection
KW - Hair removal
KW - Image processing
UR - http://www.scopus.com/inward/record.url?scp=85025426255&partnerID=8YFLogxK
U2 - 10.1145/3095140.3095142
DO - 10.1145/3095140.3095142
M3 - Conference contribution
AN - SCOPUS:85025426255
T3 - ACM International Conference Proceeding Series
BT - CGI 2017 - Proceedings of the 2017 Computer Graphics International Conference
PB - Association for Computing Machinery
T2 - 2017 Computer Graphics International Conference, CGI 2017
Y2 - 27 June 2017 through 30 June 2017
ER -