Blackhat Morphological Operations and Telea’s Inpainting for Effective Hair Artifact Removal in Dermatoscopic Images
Hassan, Rana Muthanna, Lina
Hassan, Rana
Muthanna, Lina
Type
Supervisor
Subject
Date
2025-11-20
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
This study addresses a significant challenge in dermatoscopic image analysis; removing hair artifacts to enhance image quality, which is crucial for accurate skin lesion diagnosis. Combining BlackHat morphological operations with Telea’s inpainting method represents a novel and practical approach to artifact removal in medical imaging. The proposed technique effectively enhances image quality across various skin lesion types by minimizing the interference of hair artifacts. We evaluated the algorithm’s performance using the HAM10000 dataset, which consists of 10,015 images, assessing the effectiveness of hair removal through the Hair Pixel Removal Rate (HPRR) and the Structural Similarity Index (SSIM). Results demonstrate that the algorithm maintains high SSIM values, preserving critical diagnostic features while achieving significant HPRR, particularly in images with pronounced hair artifacts. This approach underscores the robustness and adaptability of morphological operations in preprocessing dermoscopic i
Department
Publisher
Sponsor
Effat University
Copyright
CC0 1.0 Universal