Open AccessHAIR ARTIFACT REMOVAL AND SKIN LESION SEGMENTATION OF DERMOSCOPY IMAGES
Author(s) -
Julie Ann A. Salido,
Conrado Ruiz
Publication year - 2018
Publication title -
asian journal of pharmaceutical and clinical research
Language(s) - English
Resource type - Journals
eISSN - 2455-3891
pISSN - 0974-2441
DOI - 10.22159/ajpcr.2018.v11s3.30025
Subject(s) - segmentation , lesion , artificial intelligence , artifact (error) , inpainting , dilation (metric space) , pixel , computer vision , rgb color model , image segmentation , computer science , dermatoscopy , filter (signal processing) , pattern recognition (psychology) , medicine , mathematics , image (mathematics) , pathology , melanoma , combinatorics , cancer research
Objective: The objective of this research is to perform automatic hair artifact removal and skin lesion segmentation on dermoscopy images.Methods: Dermoscopy images are images from the examination of the skin lesion using a dermatoscope. There are different types of skin lesion artifacts, structures, or objects that are present in dermoscopy images. This is a pertinent problem that can inhibit the proper examination and accurately segment the skin lesion from the surrounding skin area. Artifacts, such as hair strands, introduce additional features that can also cause problems during classification. Our process starts with hair removal using 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. Then, skin lesion segmentation is performed using a binary conversion, a dilation, a perimeter detection and morphological opening, and then the removal of small connected pixels.Results: Experiments were carried out on the PH2 dermoscopy images. The border of the lesion was quantified for evaluation by four statistical metrics with the lesions identified by the PH2 as the reference image, resulting with a true detection rate (TDR) of 82.31 and a false detection rate of 5.69.Conclusions: The results obtained in the research work on hair artifacts removal and skin lesion segmentation provides acceptable results in terms of TDR and low false-positive rates.